Only content delivered through the publication boundary on this date is included.
arXiv The study builds a fully graph-based natural language inference pipeline in which premise and hypothesis are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and serialised together with a retrieved ConceptNet subgraph for a fine-tuned Qwen3.5-0.8B-Base classifier that never sees the original text; it reaches 89.7% accuracy on SNLI, only 1.9 points below an identically trained text model, matches published RoBERTa-large on ANLI rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) while trailing by 16 points on R1, giving an overall gap of 9 to 14 points against its text counterpart, which the authors call the price of interpretability and attribute to representational rather than data limitations.
The study builds a fully graph-based natural language inference pipeline in which premise and hypothesis are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and serialised together with a retrieved ConceptNet subgraph for a fine-tuned Qwen3.5-0.8B-Base classifier that never sees the original text; it reaches 89.7% accuracy on SNLI, only 1.9 points below an identically trained text model, matches published RoBERTa-large on ANLI rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) while trailing by 16 points on R1, giving an overall gap of 9 to 14 points against its text counterpart, which the authors call the price of interpretability and attribute to representational rather than data limitations.
The study builds a fully graph-based natural language inference pipeline in which premise and hypothesis are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and serialised together with a retrieved ConceptNet subgraph for a fine-tuned Qwen3.5-0.8B-Base classifier that never sees the original text; it reaches 89.7% accuracy on SNLI, only 1.9 points below an identically trained text model, matches published RoBERTa-large on ANLI rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) while trailing by 16 points on R1, giving an overall gap of 9 to 14 points against its text counterpart, which the authors call the price of interpretability and attribute to representational rather than data limitations.
The study builds a fully graph-based natural language inference pipeline in which premise and hypothesis are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and serialised together with a retrieved ConceptNet subgraph for a fine-tuned Qwen3.5-0.8B-Base classifier that never sees the original text; it reaches 89.7% accuracy on SNLI, only 1.9 points below an identically trained text model, matches published RoBERTa-large on ANLI rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) while trailing by 16 points on R1, giving an overall gap of 9 to 14 points against its text counterpart, which the authors call the price of interpretability and attribute to representational rather than data limitations.
IBM Research The work proposes a theoretical separation between quantum computers and large language models, noting that recent research further demonstrates the theoretical abilities of quantum computing, but the loaded text contains only the title and a one-sentence summary without specific methods, proofs, or results.
The work proposes a theoretical separation between quantum computers and large language models, noting that recent research further demonstrates the theoretical abilities of quantum computing, but the loaded text contains only the title and a one-sentence summary without specific methods, proofs, or results.
The work proposes a theoretical separation between quantum computers and large language models, noting that recent research further demonstrates the theoretical abilities of quantum computing, but the loaded text contains only the title and a one-sentence summary without specific methods, proofs, or results.
The work proposes a theoretical separation between quantum computers and large language models, noting that recent research further demonstrates the theoretical abilities of quantum computing, but the loaded text contains only the title and a one-sentence summary without specific methods, proofs, or results.
Journal of Theoretical and Applied Information Technology This study presents a framework called DiText-OCR (Dual-integrated Text Extraction using Hybrid OCR Engines), which leverages multiple OCR tools and domain-specific dictionaries to digitize diverse text types including printed text and low-quality scans, then processes the extracted text with Large Language Models (LLMs) for named entity recognition, relationship extraction, and data structuring, integrating the resulting structured data into healthcare databases and systems to support clinical decision support, research, and analytics while ensuring interoperability; the text also notes challenges in handling non-standard report formats, maintaining patient privacy, and addressing current limitations of OCR and LLM technologies in medical contexts, with future work aiming to integrate the
This study presents a framework called DiText-OCR (Dual-integrated Text Extraction using Hybrid OCR Engines), which leverages multiple OCR tools and domain-specific dictionaries to digitize diverse text types including printed text and low-quality scans, then processes the extracted text with Large Language Models (LLMs) for named entity recognition, relationship extraction, and data structuring, integrating the resulting structured data into healthcare databases and systems to support clinical decision support, research, and analytics while ensuring interoperability; the text also notes challenges in handling non-standard report formats, maintaining patient privacy, and addressing current limitations of OCR and LLM technologies in medical contexts, with future work aiming to integrate the
This study presents a framework called DiText-OCR (Dual-integrated Text Extraction using Hybrid OCR Engines), which leverages multiple OCR tools and domain-specific dictionaries to digitize diverse text types including printed text and low-quality scans, then processes the extracted text with Large Language Models (LLMs) for named entity recognition, relationship extraction, and data structuring, integrating the resulting structured data into healthcare databases and systems to support clinical decision support, research, and analytics while ensuring interoperability; the text also notes challenges in handling non-standard report formats, maintaining patient privacy, and addressing current limitations of OCR and LLM technologies in medical contexts, with future work aiming to integrate the
This study presents a framework called DiText-OCR (Dual-integrated Text Extraction using Hybrid OCR Engines), which leverages multiple OCR tools and domain-specific dictionaries to digitize diverse text types including printed text and low-quality scans, then processes the extracted text with Large Language Models (LLMs) for named entity recognition, relationship extraction, and data structuring, integrating the resulting structured data into healthcare databases and systems to support clinical decision support, research, and analytics while ensuring interoperability; the text also notes challenges in handling non-standard report formats, maintaining patient privacy, and addressing current limitations of OCR and LLM technologies in medical contexts, with future work aiming to integrate the
Chemical Communications This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
Acta radiologica (Stockholm, Sweden : 1987) This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
Research Square This paper proposes an evidence-informed conceptual framework that links multimodal clinical data (electronic health records, laboratory data, imaging, physiological monitoring, surgical video, device telemetry) through a modular AI architecture, domain adaptation, uncertainty estimation, and safety controls to a clinician-facing decision-support interface, explicitly separating the proposed architecture from evidence already reported in the literature and noting that clinical effectiveness of surgical AI remains to be established prospectively.
This paper proposes an evidence-informed conceptual framework that links multimodal clinical data (electronic health records, laboratory data, imaging, physiological monitoring, surgical video, device telemetry) through a modular AI architecture, domain adaptation, uncertainty estimation, and safety controls to a clinician-facing decision-support interface, explicitly separating the proposed architecture from evidence already reported in the literature and noting that clinical effectiveness of surgical AI remains to be established prospectively.
This paper proposes an evidence-informed conceptual framework that links multimodal clinical data (electronic health records, laboratory data, imaging, physiological monitoring, surgical video, device telemetry) through a modular AI architecture, domain adaptation, uncertainty estimation, and safety controls to a clinician-facing decision-support interface, explicitly separating the proposed architecture from evidence already reported in the literature and noting that clinical effectiveness of surgical AI remains to be established prospectively.
This paper proposes an evidence-informed conceptual framework that links multimodal clinical data (electronic health records, laboratory data, imaging, physiological monitoring, surgical video, device telemetry) through a modular AI architecture, domain adaptation, uncertainty estimation, and safety controls to a clinician-facing decision-support interface, explicitly separating the proposed architecture from evidence already reported in the literature and noting that clinical effectiveness of surgical AI remains to be established prospectively.
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery This article reviews advances in applying artificial intelligence across the full chain of head and neck tumor care from screening and diagnosis to follow-up management, noting that endoscopic images, CT/MRI imaging, digital pathology, ultrasound, and multi-omics data are the main data modalities, that AI-assisted endoscopic interpretation and imaging analysis can improve lesion recognition accuracy, reduce operator dependence, and support non-invasive prediction of occult lymph node metastasis, while current evidence comes mostly from single-center retrospective studies and prospective evidence for treatment response prediction remains limited.
This article reviews advances in applying artificial intelligence across the full chain of head and neck tumor care from screening and diagnosis to follow-up management, noting that endoscopic images, CT/MRI imaging, digital pathology, ultrasound, and multi-omics data are the main data modalities, that AI-assisted endoscopic interpretation and imaging analysis can improve lesion recognition accuracy, reduce operator dependence, and support non-invasive prediction of occult lymph node metastasis, while current evidence comes mostly from single-center retrospective studies and prospective evidence for treatment response prediction remains limited.
This article reviews advances in applying artificial intelligence across the full chain of head and neck tumor care from screening and diagnosis to follow-up management, noting that endoscopic images, CT/MRI imaging, digital pathology, ultrasound, and multi-omics data are the main data modalities, that AI-assisted endoscopic interpretation and imaging analysis can improve lesion recognition accuracy, reduce operator dependence, and support non-invasive prediction of occult lymph node metastasis, while current evidence comes mostly from single-center retrospective studies and prospective evidence for treatment response prediction remains limited.
This article reviews advances in applying artificial intelligence across the full chain of head and neck tumor care from screening and diagnosis to follow-up management, noting that endoscopic images, CT/MRI imaging, digital pathology, ultrasound, and multi-omics data are the main data modalities, that AI-assisted endoscopic interpretation and imaging analysis can improve lesion recognition accuracy, reduce operator dependence, and support non-invasive prediction of occult lymph node metastasis, while current evidence comes mostly from single-center retrospective studies and prospective evidence for treatment response prediction remains limited.
Chinese medical journal This review systematically evaluates established and emerging non-invasive tests for detecting early-stage liver fibrosis (F1–F2), spanning serum biomarkers, molecular imaging probes, AI-based analysis of conventional imaging, alternative biofluids such as urine, exhaled breath and saliva, gut microbiota-derived biomarkers, and multiomics-integrated models, concluding that these approaches show diagnostic promise but remain constrained by limited validation, absent standardization, and unclear integration into clinical pathways, and proposing a tiered diagnostic framework as a near-term implementation route.
This review systematically evaluates established and emerging non-invasive tests for detecting early-stage liver fibrosis (F1–F2), spanning serum biomarkers, molecular imaging probes, AI-based analysis of conventional imaging, alternative biofluids such as urine, exhaled breath and saliva, gut microbiota-derived biomarkers, and multiomics-integrated models, concluding that these approaches show diagnostic promise but remain constrained by limited validation, absent standardization, and unclear integration into clinical pathways, and proposing a tiered diagnostic framework as a near-term implementation route.
This review systematically evaluates established and emerging non-invasive tests for detecting early-stage liver fibrosis (F1–F2), spanning serum biomarkers, molecular imaging probes, AI-based analysis of conventional imaging, alternative biofluids such as urine, exhaled breath and saliva, gut microbiota-derived biomarkers, and multiomics-integrated models, concluding that these approaches show diagnostic promise but remain constrained by limited validation, absent standardization, and unclear integration into clinical pathways, and proposing a tiered diagnostic framework as a near-term implementation route.
This review systematically evaluates established and emerging non-invasive tests for detecting early-stage liver fibrosis (F1–F2), spanning serum biomarkers, molecular imaging probes, AI-based analysis of conventional imaging, alternative biofluids such as urine, exhaled breath and saliva, gut microbiota-derived biomarkers, and multiomics-integrated models, concluding that these approaches show diagnostic promise but remain constrained by limited validation, absent standardization, and unclear integration into clinical pathways, and proposing a tiered diagnostic framework as a near-term implementation route.
Journal of imaging informatics in medicine In this single-center retrospective study of 1,034 women aged 45-65 undergoing health checkups, 4,185 serial noncontrast chest CT examinations were used to derive AI-quantified T11 and T12 bone mineral density and build individual longitudinal trajectories, showing that women with low baseline bone status defined as mean T11-T12 AI-derived CT-BMD <= 128 mg/cm3 had smaller absolute BMD loss (10.82 vs 12.52 mg/cm3; P = 0.022) and a less negative T12 slope (-3.08 vs -3.91 mg/cm3/year; P = 0.011), while the greater relative decline seen in unadjusted analysis was not sustained after covariate adjustment or T11-only sensitivity analysis, and adding T11 BMD to clinical variables gave no clear incremental discrimination for rapid loss (AUC 0.708 vs 0.716; P = 0.128).
In this single-center retrospective study of 1,034 women aged 45-65 undergoing health checkups, 4,185 serial noncontrast chest CT examinations were used to derive AI-quantified T11 and T12 bone mineral density and build individual longitudinal trajectories, showing that women with low baseline bone status defined as mean T11-T12 AI-derived CT-BMD <= 128 mg/cm3 had smaller absolute BMD loss (10.82 vs 12.52 mg/cm3; P = 0.022) and a less negative T12 slope (-3.08 vs -3.91 mg/cm3/year; P = 0.011), while the greater relative decline seen in unadjusted analysis was not sustained after covariate adjustment or T11-only sensitivity analysis, and adding T11 BMD to clinical variables gave no clear incremental discrimination for rapid loss (AUC 0.708 vs 0.716; P = 0.128).
In this single-center retrospective study of 1,034 women aged 45-65 undergoing health checkups, 4,185 serial noncontrast chest CT examinations were used to derive AI-quantified T11 and T12 bone mineral density and build individual longitudinal trajectories, showing that women with low baseline bone status defined as mean T11-T12 AI-derived CT-BMD <= 128 mg/cm3 had smaller absolute BMD loss (10.82 vs 12.52 mg/cm3; P = 0.022) and a less negative T12 slope (-3.08 vs -3.91 mg/cm3/year; P = 0.011), while the greater relative decline seen in unadjusted analysis was not sustained after covariate adjustment or T11-only sensitivity analysis, and adding T11 BMD to clinical variables gave no clear incremental discrimination for rapid loss (AUC 0.708 vs 0.716; P = 0.128).
In this single-center retrospective study of 1,034 women aged 45-65 undergoing health checkups, 4,185 serial noncontrast chest CT examinations were used to derive AI-quantified T11 and T12 bone mineral density and build individual longitudinal trajectories, showing that women with low baseline bone status defined as mean T11-T12 AI-derived CT-BMD <= 128 mg/cm3 had smaller absolute BMD loss (10.82 vs 12.52 mg/cm3; P = 0.022) and a less negative T12 slope (-3.08 vs -3.91 mg/cm3/year; P = 0.011), while the greater relative decline seen in unadjusted analysis was not sustained after covariate adjustment or T11-only sensitivity analysis, and adding T11 BMD to clinical variables gave no clear incremental discrimination for rapid loss (AUC 0.708 vs 0.716; P = 0.128).
Physiological Measurement This work proposes a novel architecture that integrates a local feature extraction module with a global context model, in which the Mel_Grouper module serves as a front-end to enhance local pathological representations and its output is fed into the Transformer-based Mel_Encoder to fuse global context, achieving improvements of 3.37%, 3.06%, 6.83% and 5.36% over the previous best results on the four subtasks of the SJTU Paediatric Respiratory Sound (SPRSound) dataset, with further experiments on a real-world paediatric respiratory sound dataset.
This work proposes a novel architecture that integrates a local feature extraction module with a global context model, in which the Mel_Grouper module serves as a front-end to enhance local pathological representations and its output is fed into the Transformer-based Mel_Encoder to fuse global context, achieving improvements of 3.37%, 3.06%, 6.83% and 5.36% over the previous best results on the four subtasks of the SJTU Paediatric Respiratory Sound (SPRSound) dataset, with further experiments on a real-world paediatric respiratory sound dataset.
This work proposes a novel architecture that integrates a local feature extraction module with a global context model, in which the Mel_Grouper module serves as a front-end to enhance local pathological representations and its output is fed into the Transformer-based Mel_Encoder to fuse global context, achieving improvements of 3.37%, 3.06%, 6.83% and 5.36% over the previous best results on the four subtasks of the SJTU Paediatric Respiratory Sound (SPRSound) dataset, with further experiments on a real-world paediatric respiratory sound dataset.
This work proposes a novel architecture that integrates a local feature extraction module with a global context model, in which the Mel_Grouper module serves as a front-end to enhance local pathological representations and its output is fed into the Transformer-based Mel_Encoder to fuse global context, achieving improvements of 3.37%, 3.06%, 6.83% and 5.36% over the previous best results on the four subtasks of the SJTU Paediatric Respiratory Sound (SPRSound) dataset, with further experiments on a real-world paediatric respiratory sound dataset.
Journal of general internal medicine In this retrospective cohort study at a single tertiary academic medical center, large language models predicted same-day discharge from clinical documentation in the 30 hours preceding a 06:00 index time for adult inpatients admitted in 2024 with a length of stay between 2 and 14 days, using a randomly generated validation set (n = 860) and test set (n = 886); the baseline GPT-5 prompt achieved an F1 score of 0.48 and sensitivity of 0.
In this retrospective cohort study at a single tertiary academic medical center, large language models predicted same-day discharge from clinical documentation in the 30 hours preceding a 06:00 index time for adult inpatients admitted in 2024 with a length of stay between 2 and 14 days, using a randomly generated validation set (n = 860) and test set (n = 886); the baseline GPT-5 prompt achieved an F1 score of 0.48 and sensitivity of 0.
In this retrospective cohort study at a single tertiary academic medical center, large language models predicted same-day discharge from clinical documentation in the 30 hours preceding a 06:00 index time for adult inpatients admitted in 2024 with a length of stay between 2 and 14 days, using a randomly generated validation set (n = 860) and test set (n = 886); the baseline GPT-5 prompt achieved an F1 score of 0.48 and sensitivity of 0.
In this retrospective cohort study at a single tertiary academic medical center, large language models predicted same-day discharge from clinical documentation in the 30 hours preceding a 06:00 index time for adult inpatients admitted in 2024 with a length of stay between 2 and 14 days, using a randomly generated validation set (n = 860) and test set (n = 886); the baseline GPT-5 prompt achieved an F1 score of 0.48 and sensitivity of 0.
Annals of biomedical engineering This article argues that prompt injection is a failure mode distinct from accuracy, bias, and hallucination—a model performing exactly as instructed by an instruction the clinician neither wrote nor can see—arising from a fundamental property of current language-model architectures that receive an undifferentiated stream of tokens and possess no mechanism for distinguishing content that carries authority from content that does not, with medicine particularly exposed because the clinical record is assembled from material originating outside the institution, including referral correspondence, patient-entered messages, external reports, scanned documents, and imaging acquired elsewhere; the authors argue that prompt injection warrants classification as a patient safety hazard with an articula
This article argues that prompt injection is a failure mode distinct from accuracy, bias, and hallucination—a model performing exactly as instructed by an instruction the clinician neither wrote nor can see—arising from a fundamental property of current language-model architectures that receive an undifferentiated stream of tokens and possess no mechanism for distinguishing content that carries authority from content that does not, with medicine particularly exposed because the clinical record is assembled from material originating outside the institution, including referral correspondence, patient-entered messages, external reports, scanned documents, and imaging acquired elsewhere; the authors argue that prompt injection warrants classification as a patient safety hazard with an articula
This article argues that prompt injection is a failure mode distinct from accuracy, bias, and hallucination—a model performing exactly as instructed by an instruction the clinician neither wrote nor can see—arising from a fundamental property of current language-model architectures that receive an undifferentiated stream of tokens and possess no mechanism for distinguishing content that carries authority from content that does not, with medicine particularly exposed because the clinical record is assembled from material originating outside the institution, including referral correspondence, patient-entered messages, external reports, scanned documents, and imaging acquired elsewhere; the authors argue that prompt injection warrants classification as a patient safety hazard with an articula
This article argues that prompt injection is a failure mode distinct from accuracy, bias, and hallucination—a model performing exactly as instructed by an instruction the clinician neither wrote nor can see—arising from a fundamental property of current language-model architectures that receive an undifferentiated stream of tokens and possess no mechanism for distinguishing content that carries authority from content that does not, with medicine particularly exposed because the clinical record is assembled from material originating outside the institution, including referral correspondence, patient-entered messages, external reports, scanned documents, and imaging acquired elsewhere; the authors argue that prompt injection warrants classification as a patient safety hazard with an articula
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery In this retrospective two-center study of 2 365 patients (1 562 from the First Affiliated Hospital of Sun Yat-sen University and 803 from Ruijin Hospital, Shanghai Jiao Tong University School of Medicine), the authors developed ENDOVISTA-ENT, an integrated AI system with Model 1 for inside/outside-body image determination, Model 2 for recognition of 11 standard anatomical sites, and Model 3 for lesion localization and benign/malignant classification, reporting internal/external accuracies of 99.44%/99.84% and 96.09%/94.73%, malignant-lesion AUCs of 0.986/0.968, early nasopharyngeal, laryngeal, and hypopharyngeal cancer AUCs of 0.878-0.932, an increase in six physicians' overall interpretation accuracy on 200 pathologically confirmed cases from 78.50% to 88.20% with AI assistance (χ²=40.
In this retrospective two-center study of 2 365 patients (1 562 from the First Affiliated Hospital of Sun Yat-sen University and 803 from Ruijin Hospital, Shanghai Jiao Tong University School of Medicine), the authors developed ENDOVISTA-ENT, an integrated AI system with Model 1 for inside/outside-body image determination, Model 2 for recognition of 11 standard anatomical sites, and Model 3 for lesion localization and benign/malignant classification, reporting internal/external accuracies of 99.44%/99.84% and 96.09%/94.73%, malignant-lesion AUCs of 0.986/0.968, early nasopharyngeal, laryngeal, and hypopharyngeal cancer AUCs of 0.878-0.932, an increase in six physicians' overall interpretation accuracy on 200 pathologically confirmed cases from 78.50% to 88.20% with AI assistance (χ²=40.
In this retrospective two-center study of 2 365 patients (1 562 from the First Affiliated Hospital of Sun Yat-sen University and 803 from Ruijin Hospital, Shanghai Jiao Tong University School of Medicine), the authors developed ENDOVISTA-ENT, an integrated AI system with Model 1 for inside/outside-body image determination, Model 2 for recognition of 11 standard anatomical sites, and Model 3 for lesion localization and benign/malignant classification, reporting internal/external accuracies of 99.44%/99.84% and 96.09%/94.73%, malignant-lesion AUCs of 0.986/0.968, early nasopharyngeal, laryngeal, and hypopharyngeal cancer AUCs of 0.878-0.932, an increase in six physicians' overall interpretation accuracy on 200 pathologically confirmed cases from 78.50% to 88.20% with AI assistance (χ²=40.
In this retrospective two-center study of 2 365 patients (1 562 from the First Affiliated Hospital of Sun Yat-sen University and 803 from Ruijin Hospital, Shanghai Jiao Tong University School of Medicine), the authors developed ENDOVISTA-ENT, an integrated AI system with Model 1 for inside/outside-body image determination, Model 2 for recognition of 11 standard anatomical sites, and Model 3 for lesion localization and benign/malignant classification, reporting internal/external accuracies of 99.44%/99.84% and 96.09%/94.73%, malignant-lesion AUCs of 0.986/0.968, early nasopharyngeal, laryngeal, and hypopharyngeal cancer AUCs of 0.878-0.932, an increase in six physicians' overall interpretation accuracy on 200 pathologically confirmed cases from 78.50% to 88.20% with AI assistance (χ²=40.
bioRxiv The work first characterized fully human heavy-chain-only antibodies (HCAbs) independently of any HCAb-trained model, finding a reproducible distributional shift relative to conventional human VH domains localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather than widespread framework remodeling; on this basis the authors developed HCAbLM, described as the first foundation model pretrained specifically on a large-scale fully human HCAb repertoire using 31.
The work first characterized fully human heavy-chain-only antibodies (HCAbs) independently of any HCAb-trained model, finding a reproducible distributional shift relative to conventional human VH domains localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather than widespread framework remodeling; on this basis the authors developed HCAbLM, described as the first foundation model pretrained specifically on a large-scale fully human HCAb repertoire using 31.
The work first characterized fully human heavy-chain-only antibodies (HCAbs) independently of any HCAb-trained model, finding a reproducible distributional shift relative to conventional human VH domains localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather than widespread framework remodeling; on this basis the authors developed HCAbLM, described as the first foundation model pretrained specifically on a large-scale fully human HCAb repertoire using 31.
The work first characterized fully human heavy-chain-only antibodies (HCAbs) independently of any HCAb-trained model, finding a reproducible distributional shift relative to conventional human VH domains localized predominantly to CDR1/2, CDR3 architecture and, where supported, a restricted framework region rather than widespread framework remodeling; on this basis the authors developed HCAbLM, described as the first foundation model pretrained specifically on a large-scale fully human HCAb repertoire using 31.
Ear, nose, & throat journal This study prompted ChatGPT to generate zero-shot appeal letters for cochlear implant insurance denials in asymmetric hearing loss or single-sided deafness across 30 prompt variations, had three cochlear implant providers score them against American Cochlear Implant Alliance guidelines, and checked citation accuracy; 96.6% of responses listed multiple benefits of cochlear implants and 79.3% partially aligned with the guidelines, but 51.7% contained hallucinated benefits and only six of 96 citations (6.3%) accurately referenced peer-reviewed sources, with the rest hallucinated (57.3%), erroneous (24%), or irrelevant (10%), indicating that human verification is needed before clinical or advocacy use.
This study prompted ChatGPT to generate zero-shot appeal letters for cochlear implant insurance denials in asymmetric hearing loss or single-sided deafness across 30 prompt variations, had three cochlear implant providers score them against American Cochlear Implant Alliance guidelines, and checked citation accuracy; 96.6% of responses listed multiple benefits of cochlear implants and 79.3% partially aligned with the guidelines, but 51.7% contained hallucinated benefits and only six of 96 citations (6.3%) accurately referenced peer-reviewed sources, with the rest hallucinated (57.3%), erroneous (24%), or irrelevant (10%), indicating that human verification is needed before clinical or advocacy use.
This study prompted ChatGPT to generate zero-shot appeal letters for cochlear implant insurance denials in asymmetric hearing loss or single-sided deafness across 30 prompt variations, had three cochlear implant providers score them against American Cochlear Implant Alliance guidelines, and checked citation accuracy; 96.6% of responses listed multiple benefits of cochlear implants and 79.3% partially aligned with the guidelines, but 51.7% contained hallucinated benefits and only six of 96 citations (6.3%) accurately referenced peer-reviewed sources, with the rest hallucinated (57.3%), erroneous (24%), or irrelevant (10%), indicating that human verification is needed before clinical or advocacy use.
This study prompted ChatGPT to generate zero-shot appeal letters for cochlear implant insurance denials in asymmetric hearing loss or single-sided deafness across 30 prompt variations, had three cochlear implant providers score them against American Cochlear Implant Alliance guidelines, and checked citation accuracy; 96.6% of responses listed multiple benefits of cochlear implants and 79.3% partially aligned with the guidelines, but 51.7% contained hallucinated benefits and only six of 96 citations (6.3%) accurately referenced peer-reviewed sources, with the rest hallucinated (57.3%), erroneous (24%), or irrelevant (10%), indicating that human verification is needed before clinical or advocacy use.
Nature nanotechnology This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
Chinese medical journal Using retrospective deidentified clinical data from 1370 inpatients with chronic pancreatitis who underwent extracorporeal shock wave lithotripsy (ESWL) at Changhai Hospital between May 31, 2016 and June 26, 2019, this study retained 55 of 109 variables and compared ten machine-learning and deep-learning algorithms (XGBoost, LightGBM, CatBoost, random forest, support vector machine, artificial neural network, multilayer perceptron, TabNet, Transformer, and Wide&Deep) across three modeling schemes (all preprocessed variables, 21 variables selected by univariate screening, and ADASYN-oversampled training data) using the F1-score as the primary selection metric; TabNet achieved the best held-out test performance in the first two schemes (F1 of 0.
Using retrospective deidentified clinical data from 1370 inpatients with chronic pancreatitis who underwent extracorporeal shock wave lithotripsy (ESWL) at Changhai Hospital between May 31, 2016 and June 26, 2019, this study retained 55 of 109 variables and compared ten machine-learning and deep-learning algorithms (XGBoost, LightGBM, CatBoost, random forest, support vector machine, artificial neural network, multilayer perceptron, TabNet, Transformer, and Wide&Deep) across three modeling schemes (all preprocessed variables, 21 variables selected by univariate screening, and ADASYN-oversampled training data) using the F1-score as the primary selection metric; TabNet achieved the best held-out test performance in the first two schemes (F1 of 0.
Using retrospective deidentified clinical data from 1370 inpatients with chronic pancreatitis who underwent extracorporeal shock wave lithotripsy (ESWL) at Changhai Hospital between May 31, 2016 and June 26, 2019, this study retained 55 of 109 variables and compared ten machine-learning and deep-learning algorithms (XGBoost, LightGBM, CatBoost, random forest, support vector machine, artificial neural network, multilayer perceptron, TabNet, Transformer, and Wide&Deep) across three modeling schemes (all preprocessed variables, 21 variables selected by univariate screening, and ADASYN-oversampled training data) using the F1-score as the primary selection metric; TabNet achieved the best held-out test performance in the first two schemes (F1 of 0.
Using retrospective deidentified clinical data from 1370 inpatients with chronic pancreatitis who underwent extracorporeal shock wave lithotripsy (ESWL) at Changhai Hospital between May 31, 2016 and June 26, 2019, this study retained 55 of 109 variables and compared ten machine-learning and deep-learning algorithms (XGBoost, LightGBM, CatBoost, random forest, support vector machine, artificial neural network, multilayer perceptron, TabNet, Transformer, and Wide&Deep) across three modeling schemes (all preprocessed variables, 21 variables selected by univariate screening, and ADASYN-oversampled training data) using the F1-score as the primary selection metric; TabNet achieved the best held-out test performance in the first two schemes (F1 of 0.
Sleep This Commentary reviews recently published sleep foundation models by comparing their training cohorts, assessment frameworks, and reported performance, and applies an existing sleep foundation model without fine-tuning to an independent cohort of patients with Narcolepsy Type 1 (n = 51) and healthy controls (n = 28), finding modest zero-shot sleep-staging performance below supervised methods on the same cohort and minimal improvement in disorder classification from PSG-derived embeddings beyond demographic baselines, concluding that sleep foundation models are not yet suitable for clinical deployment.
This Commentary reviews recently published sleep foundation models by comparing their training cohorts, assessment frameworks, and reported performance, and applies an existing sleep foundation model without fine-tuning to an independent cohort of patients with Narcolepsy Type 1 (n = 51) and healthy controls (n = 28), finding modest zero-shot sleep-staging performance below supervised methods on the same cohort and minimal improvement in disorder classification from PSG-derived embeddings beyond demographic baselines, concluding that sleep foundation models are not yet suitable for clinical deployment.
This Commentary reviews recently published sleep foundation models by comparing their training cohorts, assessment frameworks, and reported performance, and applies an existing sleep foundation model without fine-tuning to an independent cohort of patients with Narcolepsy Type 1 (n = 51) and healthy controls (n = 28), finding modest zero-shot sleep-staging performance below supervised methods on the same cohort and minimal improvement in disorder classification from PSG-derived embeddings beyond demographic baselines, concluding that sleep foundation models are not yet suitable for clinical deployment.
This Commentary reviews recently published sleep foundation models by comparing their training cohorts, assessment frameworks, and reported performance, and applies an existing sleep foundation model without fine-tuning to an independent cohort of patients with Narcolepsy Type 1 (n = 51) and healthy controls (n = 28), finding modest zero-shot sleep-staging performance below supervised methods on the same cohort and minimal improvement in disorder classification from PSG-derived embeddings beyond demographic baselines, concluding that sleep foundation models are not yet suitable for clinical deployment.
Clinical Cancer Research In 203 patients with pancreatic ductal adenocarcinoma who received neoadjuvant therapy and curative-intent resection and were restricted to minor pathologic response, an AI-enabled pipeline segmented cancer and stroma from routine H&E whole-slide images and quantified spatial composition and configuration, finding that a fragmented, interface-rich tumor-stroma ecology was independently associated with shorter disease-free survival; two spatial risk models (cancer mean shape index plus stromal shape index variability, adjusted HR 1.71, P = 0.003; mean stromal patch area plus edge density, adjusted HR 2.19, P = 0.
In 203 patients with pancreatic ductal adenocarcinoma who received neoadjuvant therapy and curative-intent resection and were restricted to minor pathologic response, an AI-enabled pipeline segmented cancer and stroma from routine H&E whole-slide images and quantified spatial composition and configuration, finding that a fragmented, interface-rich tumor-stroma ecology was independently associated with shorter disease-free survival; two spatial risk models (cancer mean shape index plus stromal shape index variability, adjusted HR 1.71, P = 0.003; mean stromal patch area plus edge density, adjusted HR 2.19, P = 0.
In 203 patients with pancreatic ductal adenocarcinoma who received neoadjuvant therapy and curative-intent resection and were restricted to minor pathologic response, an AI-enabled pipeline segmented cancer and stroma from routine H&E whole-slide images and quantified spatial composition and configuration, finding that a fragmented, interface-rich tumor-stroma ecology was independently associated with shorter disease-free survival; two spatial risk models (cancer mean shape index plus stromal shape index variability, adjusted HR 1.71, P = 0.003; mean stromal patch area plus edge density, adjusted HR 2.19, P = 0.
In 203 patients with pancreatic ductal adenocarcinoma who received neoadjuvant therapy and curative-intent resection and were restricted to minor pathologic response, an AI-enabled pipeline segmented cancer and stroma from routine H&E whole-slide images and quantified spatial composition and configuration, finding that a fragmented, interface-rich tumor-stroma ecology was independently associated with shorter disease-free survival; two spatial risk models (cancer mean shape index plus stromal shape index variability, adjusted HR 1.71, P = 0.003; mean stromal patch area plus edge density, adjusted HR 2.19, P = 0.
Journal of imaging informatics in medicine This work prospectively collected 8,181 frames from 455 patients during routine colonoscopy at Farhikhtegan Hospital, Tehran, Iran, between February and December 2025 (432 polyp-positive frames with expert pixel-level segmentation masks and 7,749 normal-mucosa frames), linked patient-level metadata (age, sex, colonoscopy indication, BBPS score, and procedure duration) to every case, and trained and evaluated six segmentation architectures under one standardized protocol with patient-grouped five-fold cross-validation, finding that PraNet reached the highest internal Dice (0.755) and nnU-Net the highest internal IoU (0.665) and pixel accuracy, yet gated false-positive rates on normal mucosa ranged from 24.9% (YOLOv11m-seg) to 59.
This work prospectively collected 8,181 frames from 455 patients during routine colonoscopy at Farhikhtegan Hospital, Tehran, Iran, between February and December 2025 (432 polyp-positive frames with expert pixel-level segmentation masks and 7,749 normal-mucosa frames), linked patient-level metadata (age, sex, colonoscopy indication, BBPS score, and procedure duration) to every case, and trained and evaluated six segmentation architectures under one standardized protocol with patient-grouped five-fold cross-validation, finding that PraNet reached the highest internal Dice (0.755) and nnU-Net the highest internal IoU (0.665) and pixel accuracy, yet gated false-positive rates on normal mucosa ranged from 24.9% (YOLOv11m-seg) to 59.
This work prospectively collected 8,181 frames from 455 patients during routine colonoscopy at Farhikhtegan Hospital, Tehran, Iran, between February and December 2025 (432 polyp-positive frames with expert pixel-level segmentation masks and 7,749 normal-mucosa frames), linked patient-level metadata (age, sex, colonoscopy indication, BBPS score, and procedure duration) to every case, and trained and evaluated six segmentation architectures under one standardized protocol with patient-grouped five-fold cross-validation, finding that PraNet reached the highest internal Dice (0.755) and nnU-Net the highest internal IoU (0.665) and pixel accuracy, yet gated false-positive rates on normal mucosa ranged from 24.9% (YOLOv11m-seg) to 59.
This work prospectively collected 8,181 frames from 455 patients during routine colonoscopy at Farhikhtegan Hospital, Tehran, Iran, between February and December 2025 (432 polyp-positive frames with expert pixel-level segmentation masks and 7,749 normal-mucosa frames), linked patient-level metadata (age, sex, colonoscopy indication, BBPS score, and procedure duration) to every case, and trained and evaluated six segmentation architectures under one standardized protocol with patient-grouped five-fold cross-validation, finding that PraNet reached the highest internal Dice (0.755) and nnU-Net the highest internal IoU (0.665) and pixel accuracy, yet gated false-positive rates on normal mucosa ranged from 24.9% (YOLOv11m-seg) to 59.
Journal of the American College of Radiology : JACR This prospective shadow-mode study evaluated an FDA-cleared AI algorithm (Aidoc) for intracranial aneurysm detection on 3,856 consecutive brain CT angiographies (November 7 to December 19, 2023) with radiologists blinded to AI, finding that AI alone achieved higher sensitivity (0.846) than radiologists alone (0.718) with similar specificity (0.987 vs 0.985), radiologist-AI concordance was 96.3%, AI surfaced additional aneurysms missed by radiologists with a relative enhanced detection rate (rEDR) of 39% (55 AI-only true-positives per 140 radiologist true-positives), an AI:radiologist incremental detection ratio of 1.83 (55 of 30), a favorable gain-to-pain ratio (GPR) of 1.20 (55 of 46), and a number-needed-to-examine (NNE) of 70.
This prospective shadow-mode study evaluated an FDA-cleared AI algorithm (Aidoc) for intracranial aneurysm detection on 3,856 consecutive brain CT angiographies (November 7 to December 19, 2023) with radiologists blinded to AI, finding that AI alone achieved higher sensitivity (0.846) than radiologists alone (0.718) with similar specificity (0.987 vs 0.985), radiologist-AI concordance was 96.3%, AI surfaced additional aneurysms missed by radiologists with a relative enhanced detection rate (rEDR) of 39% (55 AI-only true-positives per 140 radiologist true-positives), an AI:radiologist incremental detection ratio of 1.83 (55 of 30), a favorable gain-to-pain ratio (GPR) of 1.20 (55 of 46), and a number-needed-to-examine (NNE) of 70.
This prospective shadow-mode study evaluated an FDA-cleared AI algorithm (Aidoc) for intracranial aneurysm detection on 3,856 consecutive brain CT angiographies (November 7 to December 19, 2023) with radiologists blinded to AI, finding that AI alone achieved higher sensitivity (0.846) than radiologists alone (0.718) with similar specificity (0.987 vs 0.985), radiologist-AI concordance was 96.3%, AI surfaced additional aneurysms missed by radiologists with a relative enhanced detection rate (rEDR) of 39% (55 AI-only true-positives per 140 radiologist true-positives), an AI:radiologist incremental detection ratio of 1.83 (55 of 30), a favorable gain-to-pain ratio (GPR) of 1.20 (55 of 46), and a number-needed-to-examine (NNE) of 70.
This prospective shadow-mode study evaluated an FDA-cleared AI algorithm (Aidoc) for intracranial aneurysm detection on 3,856 consecutive brain CT angiographies (November 7 to December 19, 2023) with radiologists blinded to AI, finding that AI alone achieved higher sensitivity (0.846) than radiologists alone (0.718) with similar specificity (0.987 vs 0.985), radiologist-AI concordance was 96.3%, AI surfaced additional aneurysms missed by radiologists with a relative enhanced detection rate (rEDR) of 39% (55 AI-only true-positives per 140 radiologist true-positives), an AI:radiologist incremental detection ratio of 1.83 (55 of 30), a favorable gain-to-pain ratio (GPR) of 1.20 (55 of 46), and a number-needed-to-examine (NNE) of 70.
Updates in surgery In routine use of a surgical AI platform, the study automatically assigned Parkland Grading Scale scores across 249 consecutive laparoscopic cholecystectomies, grouped them into Low (PGS 1-2, n=78) and High (PGS 3-5, n=171) severity, compared surgical outcomes, and evaluated model F1, discrimination (AUC 0.932 and 0.896) and calibration against two surgeons' independent double reviews of a 75-video sample, finding that the High group had older age, higher ASA scores, more cholecystitis and urgent surgery, longer operative duration, more intraoperative events and bailouts, longer hospital stay, and more 90-day major complications and readmissions, with operative duration and hemorrhage-related events remaining significant after case-control matching (n=84).
In routine use of a surgical AI platform, the study automatically assigned Parkland Grading Scale scores across 249 consecutive laparoscopic cholecystectomies, grouped them into Low (PGS 1-2, n=78) and High (PGS 3-5, n=171) severity, compared surgical outcomes, and evaluated model F1, discrimination (AUC 0.932 and 0.896) and calibration against two surgeons' independent double reviews of a 75-video sample, finding that the High group had older age, higher ASA scores, more cholecystitis and urgent surgery, longer operative duration, more intraoperative events and bailouts, longer hospital stay, and more 90-day major complications and readmissions, with operative duration and hemorrhage-related events remaining significant after case-control matching (n=84).
In routine use of a surgical AI platform, the study automatically assigned Parkland Grading Scale scores across 249 consecutive laparoscopic cholecystectomies, grouped them into Low (PGS 1-2, n=78) and High (PGS 3-5, n=171) severity, compared surgical outcomes, and evaluated model F1, discrimination (AUC 0.932 and 0.896) and calibration against two surgeons' independent double reviews of a 75-video sample, finding that the High group had older age, higher ASA scores, more cholecystitis and urgent surgery, longer operative duration, more intraoperative events and bailouts, longer hospital stay, and more 90-day major complications and readmissions, with operative duration and hemorrhage-related events remaining significant after case-control matching (n=84).
In routine use of a surgical AI platform, the study automatically assigned Parkland Grading Scale scores across 249 consecutive laparoscopic cholecystectomies, grouped them into Low (PGS 1-2, n=78) and High (PGS 3-5, n=171) severity, compared surgical outcomes, and evaluated model F1, discrimination (AUC 0.932 and 0.896) and calibration against two surgeons' independent double reviews of a 75-video sample, finding that the High group had older age, higher ASA scores, more cholecystitis and urgent surgery, longer operative duration, more intraoperative events and bailouts, longer hospital stay, and more 90-day major complications and readmissions, with operative duration and hemorrhage-related events remaining significant after case-control matching (n=84).
Zhonghua yi xue za zhi From a clinical-expert perspective, this article reviews the progress and value of artificial intelligence, especially deep learning, in core links of spinal deformity surgery such as imaging parameter measurement, surgical risk prediction, and individualized plan formulation, analyzes bottlenecks in technology promotion, and looks ahead to a "human-machine co-intelligence" direction, arguing that integrating AI with clinical experience can move the discipline from "standardized treatment" toward "individualized precision treatment" and build an intelligent diagnosis and treatment system.
From a clinical-expert perspective, this article reviews the progress and value of artificial intelligence, especially deep learning, in core links of spinal deformity surgery such as imaging parameter measurement, surgical risk prediction, and individualized plan formulation, analyzes bottlenecks in technology promotion, and looks ahead to a "human-machine co-intelligence" direction, arguing that integrating AI with clinical experience can move the discipline from "standardized treatment" toward "individualized precision treatment" and build an intelligent diagnosis and treatment system.
From a clinical-expert perspective, this article reviews the progress and value of artificial intelligence, especially deep learning, in core links of spinal deformity surgery such as imaging parameter measurement, surgical risk prediction, and individualized plan formulation, analyzes bottlenecks in technology promotion, and looks ahead to a "human-machine co-intelligence" direction, arguing that integrating AI with clinical experience can move the discipline from "standardized treatment" toward "individualized precision treatment" and build an intelligent diagnosis and treatment system.
From a clinical-expert perspective, this article reviews the progress and value of artificial intelligence, especially deep learning, in core links of spinal deformity surgery such as imaging parameter measurement, surgical risk prediction, and individualized plan formulation, analyzes bottlenecks in technology promotion, and looks ahead to a "human-machine co-intelligence" direction, arguing that integrating AI with clinical experience can move the discipline from "standardized treatment" toward "individualized precision treatment" and build an intelligent diagnosis and treatment system.
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
This study retrospectively collected 23 434 electronic nasopharyngolaryngoscopic images from 3 255 subjects across five medical centers (15 465 laryngoscopic and 7 969 nasopharyngoscopic images), developed the WSC-T intelligent diagnostic model for head and neck tumors, reported internal and external test accuracies of 94.89% and 91.04% with AUCs of 0.98 and 0.97 for laryngeal-hypopharyngeal cancer and 96.27% and 92.31% with AUCs of 0.98 and 0.97 for nasopharyngeal cancer, compared it with a supervised learning model without contrastive learning, and built a cloud-based platform enabling image uploading, automated analysis, and diagnostic result output.
Journal of Medical Internet Research This cross-sectional survey, distributed online through a health care news platform mailing list, gathered responses from 335 health care professionals (including 230 attending physicians, 68.7%) and found that 62.7% reported current or contemplated large language model use, users reported significantly higher self-reported knowledge than nonusers (P < .001), the most valued applications were literature review (73.4%), decision support (57%), and patient communication (54.9%), leading concerns were decision errors (75.5%) and algorithmic bias (73.1%), 96.4% expressed concern about bias with those who had observed bias reporting higher concern (P < .001), and respondents favored regulation by professional associations (65.4%) over technology companies (29%), with 87.
This cross-sectional survey, distributed online through a health care news platform mailing list, gathered responses from 335 health care professionals (including 230 attending physicians, 68.7%) and found that 62.7% reported current or contemplated large language model use, users reported significantly higher self-reported knowledge than nonusers (P < .001), the most valued applications were literature review (73.4%), decision support (57%), and patient communication (54.9%), leading concerns were decision errors (75.5%) and algorithmic bias (73.1%), 96.4% expressed concern about bias with those who had observed bias reporting higher concern (P < .001), and respondents favored regulation by professional associations (65.4%) over technology companies (29%), with 87.
This cross-sectional survey, distributed online through a health care news platform mailing list, gathered responses from 335 health care professionals (including 230 attending physicians, 68.7%) and found that 62.7% reported current or contemplated large language model use, users reported significantly higher self-reported knowledge than nonusers (P < .001), the most valued applications were literature review (73.4%), decision support (57%), and patient communication (54.9%), leading concerns were decision errors (75.5%) and algorithmic bias (73.1%), 96.4% expressed concern about bias with those who had observed bias reporting higher concern (P < .001), and respondents favored regulation by professional associations (65.4%) over technology companies (29%), with 87.
This cross-sectional survey, distributed online through a health care news platform mailing list, gathered responses from 335 health care professionals (including 230 attending physicians, 68.7%) and found that 62.7% reported current or contemplated large language model use, users reported significantly higher self-reported knowledge than nonusers (P < .001), the most valued applications were literature review (73.4%), decision support (57%), and patient communication (54.9%), leading concerns were decision errors (75.5%) and algorithmic bias (73.1%), 96.4% expressed concern about bias with those who had observed bias reporting higher concern (P < .001), and respondents favored regulation by professional associations (65.4%) over technology companies (29%), with 87.
bioRxiv The work introduces semantic vaccinology and implements it as SemVac: publications linked to each protein are retrieved through PaperBLAST, condensed into a structured semantic profile, and an LLM is prompted to return an antigenicity probability; on a curated 246-protein bacterial benchmark the best of 14 general-purpose LLMs matched or exceeded the precision of the specialized predictor PLGDL, with open-weight Kimi K2 0905 offering the strongest performance-cost balance, predictions were robust to masking of vaccine keywords, reproducible across repeated inference, and generalized to a 1,200-protein cross-pathogen dataset; explicit chain-of-thought reasoning increased recall but lowered precision in every model tested; applied to the mpox virus proteome, SemVac recovered the established
The work introduces semantic vaccinology and implements it as SemVac: publications linked to each protein are retrieved through PaperBLAST, condensed into a structured semantic profile, and an LLM is prompted to return an antigenicity probability; on a curated 246-protein bacterial benchmark the best of 14 general-purpose LLMs matched or exceeded the precision of the specialized predictor PLGDL, with open-weight Kimi K2 0905 offering the strongest performance-cost balance, predictions were robust to masking of vaccine keywords, reproducible across repeated inference, and generalized to a 1,200-protein cross-pathogen dataset; explicit chain-of-thought reasoning increased recall but lowered precision in every model tested; applied to the mpox virus proteome, SemVac recovered the established
The work introduces semantic vaccinology and implements it as SemVac: publications linked to each protein are retrieved through PaperBLAST, condensed into a structured semantic profile, and an LLM is prompted to return an antigenicity probability; on a curated 246-protein bacterial benchmark the best of 14 general-purpose LLMs matched or exceeded the precision of the specialized predictor PLGDL, with open-weight Kimi K2 0905 offering the strongest performance-cost balance, predictions were robust to masking of vaccine keywords, reproducible across repeated inference, and generalized to a 1,200-protein cross-pathogen dataset; explicit chain-of-thought reasoning increased recall but lowered precision in every model tested; applied to the mpox virus proteome, SemVac recovered the established
The work introduces semantic vaccinology and implements it as SemVac: publications linked to each protein are retrieved through PaperBLAST, condensed into a structured semantic profile, and an LLM is prompted to return an antigenicity probability; on a curated 246-protein bacterial benchmark the best of 14 general-purpose LLMs matched or exceeded the precision of the specialized predictor PLGDL, with open-weight Kimi K2 0905 offering the strongest performance-cost balance, predictions were robust to masking of vaccine keywords, reproducible across repeated inference, and generalized to a 1,200-protein cross-pathogen dataset; explicit chain-of-thought reasoning increased recall but lowered precision in every model tested; applied to the mpox virus proteome, SemVac recovered the established
bioRxiv Using repeated intratracheal inoculation of mice with recombinant Staphylococcus aureus serine protease-like protein B (SplB) or an inactive mutant, this study found that SplB sensitized mice and caused eosinophilic airway inflammation and hyperresponsiveness, that asthma development required both the proteolytic activity of SplB and a functional adaptive immune system, and that the soluble protease sensor IL-33 was necessary for eosinophil tissue invasion whereas the membrane-bound protease sensor PAR2 was not, leading the authors to propose a third mechanism in which S. aureus releases allergens such as SplB that sensitize individuals and lead to asthma.
Using repeated intratracheal inoculation of mice with recombinant Staphylococcus aureus serine protease-like protein B (SplB) or an inactive mutant, this study found that SplB sensitized mice and caused eosinophilic airway inflammation and hyperresponsiveness, that asthma development required both the proteolytic activity of SplB and a functional adaptive immune system, and that the soluble protease sensor IL-33 was necessary for eosinophil tissue invasion whereas the membrane-bound protease sensor PAR2 was not, leading the authors to propose a third mechanism in which S. aureus releases allergens such as SplB that sensitize individuals and lead to asthma.
Using repeated intratracheal inoculation of mice with recombinant Staphylococcus aureus serine protease-like protein B (SplB) or an inactive mutant, this study found that SplB sensitized mice and caused eosinophilic airway inflammation and hyperresponsiveness, that asthma development required both the proteolytic activity of SplB and a functional adaptive immune system, and that the soluble protease sensor IL-33 was necessary for eosinophil tissue invasion whereas the membrane-bound protease sensor PAR2 was not, leading the authors to propose a third mechanism in which S. aureus releases allergens such as SplB that sensitize individuals and lead to asthma.
Using repeated intratracheal inoculation of mice with recombinant Staphylococcus aureus serine protease-like protein B (SplB) or an inactive mutant, this study found that SplB sensitized mice and caused eosinophilic airway inflammation and hyperresponsiveness, that asthma development required both the proteolytic activity of SplB and a functional adaptive immune system, and that the soluble protease sensor IL-33 was necessary for eosinophil tissue invasion whereas the membrane-bound protease sensor PAR2 was not, leading the authors to propose a third mechanism in which S. aureus releases allergens such as SplB that sensitize individuals and lead to asthma.
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery In a single-center retrospective study, an attention-based multi-task deep learning model combining a ResNet+CBAM imaging branch with a DNN+Transformer clinical-feature branch used contrast-enhanced neck CT to jointly predict lymph node malignancy and primary site, achieving in the test set (n=457) an AUC of 0.851 for benign/malignant prediction, a Micro-AUC of 0.819 for primary-site prediction, and Top-1/Top-3 accuracy of 79%/93%, and in a real-world CMSCCUP cohort (172 cases) a Micro-AUC of 0.809 and Top-3 accuracy of 88%, significantly improving junior physicians' predictive accuracy (all P<0.001).
In a single-center retrospective study, an attention-based multi-task deep learning model combining a ResNet+CBAM imaging branch with a DNN+Transformer clinical-feature branch used contrast-enhanced neck CT to jointly predict lymph node malignancy and primary site, achieving in the test set (n=457) an AUC of 0.851 for benign/malignant prediction, a Micro-AUC of 0.819 for primary-site prediction, and Top-1/Top-3 accuracy of 79%/93%, and in a real-world CMSCCUP cohort (172 cases) a Micro-AUC of 0.809 and Top-3 accuracy of 88%, significantly improving junior physicians' predictive accuracy (all P<0.001).
In a single-center retrospective study, an attention-based multi-task deep learning model combining a ResNet+CBAM imaging branch with a DNN+Transformer clinical-feature branch used contrast-enhanced neck CT to jointly predict lymph node malignancy and primary site, achieving in the test set (n=457) an AUC of 0.851 for benign/malignant prediction, a Micro-AUC of 0.819 for primary-site prediction, and Top-1/Top-3 accuracy of 79%/93%, and in a real-world CMSCCUP cohort (172 cases) a Micro-AUC of 0.809 and Top-3 accuracy of 88%, significantly improving junior physicians' predictive accuracy (all P<0.001).
In a single-center retrospective study, an attention-based multi-task deep learning model combining a ResNet+CBAM imaging branch with a DNN+Transformer clinical-feature branch used contrast-enhanced neck CT to jointly predict lymph node malignancy and primary site, achieving in the test set (n=457) an AUC of 0.851 for benign/malignant prediction, a Micro-AUC of 0.819 for primary-site prediction, and Top-1/Top-3 accuracy of 79%/93%, and in a real-world CMSCCUP cohort (172 cases) a Micro-AUC of 0.809 and Top-3 accuracy of 88%, significantly improving junior physicians' predictive accuracy (all P<0.001).
Research Square This work introduces Text2Cypher-Hub, a community platform for disseminating, discovering, and reusing Text2Cypher resources, and as its initial contribution releases three curated benchmarks---bio2C, twt2C, and fin2C---covering biomedical, social-media, and financial property graphs, together comprising 6,500 technically and semantically validated natural-language-to-Cypher pairs spanning five complexity categories, while describing the curation workflow and demonstrating suitability for supervised fine-tuning and retrieval-augmented generation pipelines.
This work introduces Text2Cypher-Hub, a community platform for disseminating, discovering, and reusing Text2Cypher resources, and as its initial contribution releases three curated benchmarks---bio2C, twt2C, and fin2C---covering biomedical, social-media, and financial property graphs, together comprising 6,500 technically and semantically validated natural-language-to-Cypher pairs spanning five complexity categories, while describing the curation workflow and demonstrating suitability for supervised fine-tuning and retrieval-augmented generation pipelines.
This work introduces Text2Cypher-Hub, a community platform for disseminating, discovering, and reusing Text2Cypher resources, and as its initial contribution releases three curated benchmarks---bio2C, twt2C, and fin2C---covering biomedical, social-media, and financial property graphs, together comprising 6,500 technically and semantically validated natural-language-to-Cypher pairs spanning five complexity categories, while describing the curation workflow and demonstrating suitability for supervised fine-tuning and retrieval-augmented generation pipelines.
This work introduces Text2Cypher-Hub, a community platform for disseminating, discovering, and reusing Text2Cypher resources, and as its initial contribution releases three curated benchmarks---bio2C, twt2C, and fin2C---covering biomedical, social-media, and financial property graphs, together comprising 6,500 technically and semantically validated natural-language-to-Cypher pairs spanning five complexity categories, while describing the curation workflow and demonstrating suitability for supervised fine-tuning and retrieval-augmented generation pipelines.
Journal of minimally invasive surgery This single-center, repeated cross-sectional descriptive survey administered anonymous online questionnaires before and one month after installation of an AI-based computer-aided detection (AI-CADe) system, with 29 and 25 endoscopy unit staff completing the pre- and post-installation surveys respectively, and found that staff held generally favorable perceptions of AI-CADe, recognizing its potential value for adenoma detection rate improvement, lesion removal, patient and procedural satisfaction, and workflow, while also reporting concerns about false-positive detection, overdetection, unnecessary biopsies, and dependence on AI, with accuracy and sensitivity most frequently selected as adoption factors.
This single-center, repeated cross-sectional descriptive survey administered anonymous online questionnaires before and one month after installation of an AI-based computer-aided detection (AI-CADe) system, with 29 and 25 endoscopy unit staff completing the pre- and post-installation surveys respectively, and found that staff held generally favorable perceptions of AI-CADe, recognizing its potential value for adenoma detection rate improvement, lesion removal, patient and procedural satisfaction, and workflow, while also reporting concerns about false-positive detection, overdetection, unnecessary biopsies, and dependence on AI, with accuracy and sensitivity most frequently selected as adoption factors.
This single-center, repeated cross-sectional descriptive survey administered anonymous online questionnaires before and one month after installation of an AI-based computer-aided detection (AI-CADe) system, with 29 and 25 endoscopy unit staff completing the pre- and post-installation surveys respectively, and found that staff held generally favorable perceptions of AI-CADe, recognizing its potential value for adenoma detection rate improvement, lesion removal, patient and procedural satisfaction, and workflow, while also reporting concerns about false-positive detection, overdetection, unnecessary biopsies, and dependence on AI, with accuracy and sensitivity most frequently selected as adoption factors.
This single-center, repeated cross-sectional descriptive survey administered anonymous online questionnaires before and one month after installation of an AI-based computer-aided detection (AI-CADe) system, with 29 and 25 endoscopy unit staff completing the pre- and post-installation surveys respectively, and found that staff held generally favorable perceptions of AI-CADe, recognizing its potential value for adenoma detection rate improvement, lesion removal, patient and procedural satisfaction, and workflow, while also reporting concerns about false-positive detection, overdetection, unnecessary biopsies, and dependence on AI, with accuracy and sensitivity most frequently selected as adoption factors.
bioRxiv This work presents the Hierarchical Temporal Transformer (HTT), a two-level architecture in which level 1 encodes each report with BiomedBERT adapted by LoRA and level 2 is a temporal transformer that reads a patient's full report sequence using a continuous-time positional encoding built from the measured number of days between visits plus learnable cancer-type embeddings; on a controlled synthetic corpus of sequential radiology reports it reaches validation AUROC 0.942 versus 0.881 for a single-report baseline and transfers to held-out pancreatic cancer at 0.995 versus 0.949, and on 4,786 real pathology reports from TCGA-Reports spanning 14 cancer types it predicts tumor grade for three types withheld entirely from training with AUROC 1.000 on thyroid carcinoma, 0.960 on sarcoma and 0.
This work presents the Hierarchical Temporal Transformer (HTT), a two-level architecture in which level 1 encodes each report with BiomedBERT adapted by LoRA and level 2 is a temporal transformer that reads a patient's full report sequence using a continuous-time positional encoding built from the measured number of days between visits plus learnable cancer-type embeddings; on a controlled synthetic corpus of sequential radiology reports it reaches validation AUROC 0.942 versus 0.881 for a single-report baseline and transfers to held-out pancreatic cancer at 0.995 versus 0.949, and on 4,786 real pathology reports from TCGA-Reports spanning 14 cancer types it predicts tumor grade for three types withheld entirely from training with AUROC 1.000 on thyroid carcinoma, 0.960 on sarcoma and 0.
This work presents the Hierarchical Temporal Transformer (HTT), a two-level architecture in which level 1 encodes each report with BiomedBERT adapted by LoRA and level 2 is a temporal transformer that reads a patient's full report sequence using a continuous-time positional encoding built from the measured number of days between visits plus learnable cancer-type embeddings; on a controlled synthetic corpus of sequential radiology reports it reaches validation AUROC 0.942 versus 0.881 for a single-report baseline and transfers to held-out pancreatic cancer at 0.995 versus 0.949, and on 4,786 real pathology reports from TCGA-Reports spanning 14 cancer types it predicts tumor grade for three types withheld entirely from training with AUROC 1.000 on thyroid carcinoma, 0.960 on sarcoma and 0.
This work presents the Hierarchical Temporal Transformer (HTT), a two-level architecture in which level 1 encodes each report with BiomedBERT adapted by LoRA and level 2 is a temporal transformer that reads a patient's full report sequence using a continuous-time positional encoding built from the measured number of days between visits plus learnable cancer-type embeddings; on a controlled synthetic corpus of sequential radiology reports it reaches validation AUROC 0.942 versus 0.881 for a single-report baseline and transfers to held-out pancreatic cancer at 0.995 versus 0.949, and on 4,786 real pathology reports from TCGA-Reports spanning 14 cancer types it predicts tumor grade for three types withheld entirely from training with AUROC 1.000 on thyroid carcinoma, 0.960 on sarcoma and 0.
bioRxiv The work proposes that cortico-thalamic circuits are well suited to implement multi-head self- and cross-attention: layer 2/3 pyramidal cells maintain a recurrent key-value memory while layer 5 pyramidal cells decode the memory retrieved by an incoming query, the computation of keys, values and queries maps onto core and matrix thalamo-cortical projections distributed across the micro- and macro-columns of a cortical area, one cortical area forms an attention head and cortex a multi-head self-attention network, the same thalamo-cortical microcircuit also calculates sensory prediction errors guiding gradient-based synaptic plasticity, and a reward-prediction error gates via basal ganglia the cortical output and the re-activation of hippocampal memories, with the trained network aligning wit
The work proposes that cortico-thalamic circuits are well suited to implement multi-head self- and cross-attention: layer 2/3 pyramidal cells maintain a recurrent key-value memory while layer 5 pyramidal cells decode the memory retrieved by an incoming query, the computation of keys, values and queries maps onto core and matrix thalamo-cortical projections distributed across the micro- and macro-columns of a cortical area, one cortical area forms an attention head and cortex a multi-head self-attention network, the same thalamo-cortical microcircuit also calculates sensory prediction errors guiding gradient-based synaptic plasticity, and a reward-prediction error gates via basal ganglia the cortical output and the re-activation of hippocampal memories, with the trained network aligning wit
The work proposes that cortico-thalamic circuits are well suited to implement multi-head self- and cross-attention: layer 2/3 pyramidal cells maintain a recurrent key-value memory while layer 5 pyramidal cells decode the memory retrieved by an incoming query, the computation of keys, values and queries maps onto core and matrix thalamo-cortical projections distributed across the micro- and macro-columns of a cortical area, one cortical area forms an attention head and cortex a multi-head self-attention network, the same thalamo-cortical microcircuit also calculates sensory prediction errors guiding gradient-based synaptic plasticity, and a reward-prediction error gates via basal ganglia the cortical output and the re-activation of hippocampal memories, with the trained network aligning wit
The work proposes that cortico-thalamic circuits are well suited to implement multi-head self- and cross-attention: layer 2/3 pyramidal cells maintain a recurrent key-value memory while layer 5 pyramidal cells decode the memory retrieved by an incoming query, the computation of keys, values and queries maps onto core and matrix thalamo-cortical projections distributed across the micro- and macro-columns of a cortical area, one cortical area forms an attention head and cortex a multi-head self-attention network, the same thalamo-cortical microcircuit also calculates sensory prediction errors guiding gradient-based synaptic plasticity, and a reward-prediction error gates via basal ganglia the cortical output and the re-activation of hippocampal memories, with the trained network aligning wit
Research Square In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
Preprints.org This review systematically surveys state-of-the-art emergency rescue technologies for building fires and industrial thermal disasters, covering early fire detection integrating the Internet of Things (IoT), artificial intelligence (AI), and machine learning; advanced suppression technologies such as water mist, gaseous agents, and high-expansion foam; autonomous and semi-autonomous rescue robotics; UAVs equipped with thermal imaging; Building Information Modeling (BIM) and digital twins for emergency planning and evacuation simulation; PPE advancements including biometric wearables; and communication and situational-awareness systems, with special attention to industrial thermal hazards including petrochemical fires, hazardous material incidents, BLEVE events, and dust explosions, and conc
This review systematically surveys state-of-the-art emergency rescue technologies for building fires and industrial thermal disasters, covering early fire detection integrating the Internet of Things (IoT), artificial intelligence (AI), and machine learning; advanced suppression technologies such as water mist, gaseous agents, and high-expansion foam; autonomous and semi-autonomous rescue robotics; UAVs equipped with thermal imaging; Building Information Modeling (BIM) and digital twins for emergency planning and evacuation simulation; PPE advancements including biometric wearables; and communication and situational-awareness systems, with special attention to industrial thermal hazards including petrochemical fires, hazardous material incidents, BLEVE events, and dust explosions, and conc
This review systematically surveys state-of-the-art emergency rescue technologies for building fires and industrial thermal disasters, covering early fire detection integrating the Internet of Things (IoT), artificial intelligence (AI), and machine learning; advanced suppression technologies such as water mist, gaseous agents, and high-expansion foam; autonomous and semi-autonomous rescue robotics; UAVs equipped with thermal imaging; Building Information Modeling (BIM) and digital twins for emergency planning and evacuation simulation; PPE advancements including biometric wearables; and communication and situational-awareness systems, with special attention to industrial thermal hazards including petrochemical fires, hazardous material incidents, BLEVE events, and dust explosions, and conc
This review systematically surveys state-of-the-art emergency rescue technologies for building fires and industrial thermal disasters, covering early fire detection integrating the Internet of Things (IoT), artificial intelligence (AI), and machine learning; advanced suppression technologies such as water mist, gaseous agents, and high-expansion foam; autonomous and semi-autonomous rescue robotics; UAVs equipped with thermal imaging; Building Information Modeling (BIM) and digital twins for emergency planning and evacuation simulation; PPE advancements including biometric wearables; and communication and situational-awareness systems, with special attention to industrial thermal hazards including petrochemical fires, hazardous material incidents, BLEVE events, and dust explosions, and conc
Experimental hematology & oncology This study integrated six public single-cell RNA sequencing datasets, used inferCNV to infer copy number variations at the single-cell level and identify a high-CNV (HCNV) malignant subpopulation, built a multimodal deep-learning AI prognostic model on routine H&E-stained sections with HCNV activity as the biological anchor for pathology feature selection, and through multiomics screening plus in vitro and in vivo experiments identified RTN3 as the core driver gene, showing that RTN3 activates JAK2/STAT3 to transcriptionally upregulate glycolytic enzymes PKM2, GLUT1 and LDHA, driving glycolytic metabolic reprogramming and conferring gemcitabine resistance in bladder cancer.
This study integrated six public single-cell RNA sequencing datasets, used inferCNV to infer copy number variations at the single-cell level and identify a high-CNV (HCNV) malignant subpopulation, built a multimodal deep-learning AI prognostic model on routine H&E-stained sections with HCNV activity as the biological anchor for pathology feature selection, and through multiomics screening plus in vitro and in vivo experiments identified RTN3 as the core driver gene, showing that RTN3 activates JAK2/STAT3 to transcriptionally upregulate glycolytic enzymes PKM2, GLUT1 and LDHA, driving glycolytic metabolic reprogramming and conferring gemcitabine resistance in bladder cancer.
This study integrated six public single-cell RNA sequencing datasets, used inferCNV to infer copy number variations at the single-cell level and identify a high-CNV (HCNV) malignant subpopulation, built a multimodal deep-learning AI prognostic model on routine H&E-stained sections with HCNV activity as the biological anchor for pathology feature selection, and through multiomics screening plus in vitro and in vivo experiments identified RTN3 as the core driver gene, showing that RTN3 activates JAK2/STAT3 to transcriptionally upregulate glycolytic enzymes PKM2, GLUT1 and LDHA, driving glycolytic metabolic reprogramming and conferring gemcitabine resistance in bladder cancer.
This study integrated six public single-cell RNA sequencing datasets, used inferCNV to infer copy number variations at the single-cell level and identify a high-CNV (HCNV) malignant subpopulation, built a multimodal deep-learning AI prognostic model on routine H&E-stained sections with HCNV activity as the biological anchor for pathology feature selection, and through multiomics screening plus in vitro and in vivo experiments identified RTN3 as the core driver gene, showing that RTN3 activates JAK2/STAT3 to transcriptionally upregulate glycolytic enzymes PKM2, GLUT1 and LDHA, driving glycolytic metabolic reprogramming and conferring gemcitabine resistance in bladder cancer.
Circulation This American Heart Association scientific statement summarizes the current epidemiology of cardiovascular disease and stroke among Hispanic/Latino adults in the United States, noting that cardiovascular disease became the leading cause of death in this population in 2022, that Hispanic adults carry a disproportionate burden of cardiometabolic risk factors including obesity, diabetes, and dyslipidemia, and that substantial differences exist across Hispanic heritage groups, sexes, and disease types, such that the "Hispanic paradox" is increasingly seen as an oversimplification; it further sets priorities including expanding disaggregated data collection, increasing research representation, and ensuring equitable implementation of precision medicine approaches including genomics, multi-omics
This American Heart Association scientific statement summarizes the current epidemiology of cardiovascular disease and stroke among Hispanic/Latino adults in the United States, noting that cardiovascular disease became the leading cause of death in this population in 2022, that Hispanic adults carry a disproportionate burden of cardiometabolic risk factors including obesity, diabetes, and dyslipidemia, and that substantial differences exist across Hispanic heritage groups, sexes, and disease types, such that the "Hispanic paradox" is increasingly seen as an oversimplification; it further sets priorities including expanding disaggregated data collection, increasing research representation, and ensuring equitable implementation of precision medicine approaches including genomics, multi-omics
This American Heart Association scientific statement summarizes the current epidemiology of cardiovascular disease and stroke among Hispanic/Latino adults in the United States, noting that cardiovascular disease became the leading cause of death in this population in 2022, that Hispanic adults carry a disproportionate burden of cardiometabolic risk factors including obesity, diabetes, and dyslipidemia, and that substantial differences exist across Hispanic heritage groups, sexes, and disease types, such that the "Hispanic paradox" is increasingly seen as an oversimplification; it further sets priorities including expanding disaggregated data collection, increasing research representation, and ensuring equitable implementation of precision medicine approaches including genomics, multi-omics
This American Heart Association scientific statement summarizes the current epidemiology of cardiovascular disease and stroke among Hispanic/Latino adults in the United States, noting that cardiovascular disease became the leading cause of death in this population in 2022, that Hispanic adults carry a disproportionate burden of cardiometabolic risk factors including obesity, diabetes, and dyslipidemia, and that substantial differences exist across Hispanic heritage groups, sexes, and disease types, such that the "Hispanic paradox" is increasingly seen as an oversimplification; it further sets priorities including expanding disaggregated data collection, increasing research representation, and ensuring equitable implementation of precision medicine approaches including genomics, multi-omics
Journal of minimally invasive surgery This review reorganizes the surgical AI literature around decision points rather than algorithmic type or predicted outcomes, examining PubMed-indexed studies from 2015 to 2025 and finding that preoperative AI predominantly supports patient selection and treatment planning under diagnostic uncertainty while postoperative AI mainly supports time-sensitive management and prognostic assessment, thereby reframing surgical AI as an integral component of phase-specific clinical decision pathways across the surgical care continuum rather than a standalone predictive instrument.
This review reorganizes the surgical AI literature around decision points rather than algorithmic type or predicted outcomes, examining PubMed-indexed studies from 2015 to 2025 and finding that preoperative AI predominantly supports patient selection and treatment planning under diagnostic uncertainty while postoperative AI mainly supports time-sensitive management and prognostic assessment, thereby reframing surgical AI as an integral component of phase-specific clinical decision pathways across the surgical care continuum rather than a standalone predictive instrument.
This review reorganizes the surgical AI literature around decision points rather than algorithmic type or predicted outcomes, examining PubMed-indexed studies from 2015 to 2025 and finding that preoperative AI predominantly supports patient selection and treatment planning under diagnostic uncertainty while postoperative AI mainly supports time-sensitive management and prognostic assessment, thereby reframing surgical AI as an integral component of phase-specific clinical decision pathways across the surgical care continuum rather than a standalone predictive instrument.
This review reorganizes the surgical AI literature around decision points rather than algorithmic type or predicted outcomes, examining PubMed-indexed studies from 2015 to 2025 and finding that preoperative AI predominantly supports patient selection and treatment planning under diagnostic uncertainty while postoperative AI mainly supports time-sensitive management and prognostic assessment, thereby reframing surgical AI as an integral component of phase-specific clinical decision pathways across the surgical care continuum rather than a standalone predictive instrument.
Academic medicine : journal of the Association of American Medical Colleges This paper identifies and names the phenomenon of "inference impersonation"—ambient AI scribes generate rather than transcribe clinical reasoning in the Assessment and Plan, producing text indistinguishable from transcription in the final note, so trainees may edit AI drafts instead of reasoning independently and risk never developing the judgment training exists to build; it proposes vendor-side learner-specific configurations and section-level transparency plus training-program responses such as reasoning-before-note, competency gating, and oral assessment.
This paper identifies and names the phenomenon of "inference impersonation"—ambient AI scribes generate rather than transcribe clinical reasoning in the Assessment and Plan, producing text indistinguishable from transcription in the final note, so trainees may edit AI drafts instead of reasoning independently and risk never developing the judgment training exists to build; it proposes vendor-side learner-specific configurations and section-level transparency plus training-program responses such as reasoning-before-note, competency gating, and oral assessment.
This paper identifies and names the phenomenon of "inference impersonation"—ambient AI scribes generate rather than transcribe clinical reasoning in the Assessment and Plan, producing text indistinguishable from transcription in the final note, so trainees may edit AI drafts instead of reasoning independently and risk never developing the judgment training exists to build; it proposes vendor-side learner-specific configurations and section-level transparency plus training-program responses such as reasoning-before-note, competency gating, and oral assessment.
This paper identifies and names the phenomenon of "inference impersonation"—ambient AI scribes generate rather than transcribe clinical reasoning in the Assessment and Plan, producing text indistinguishable from transcription in the final note, so trainees may edit AI drafts instead of reasoning independently and risk never developing the judgment training exists to build; it proposes vendor-side learner-specific configurations and section-level transparency plus training-program responses such as reasoning-before-note, competency gating, and oral assessment.
Expert Review of Hematology This review argues that immune reconstitution assessment after allogeneic hematopoietic cell transplantation is highly heterogeneous, which hampers the production of solid evidence and limits its potential use as a clinical endpoint, and that cross-center standardization is therefore needed, covering pre-analytical variables such as sample collection and handling as well as analytical procedures, drawing on the experience of international flow cytometry standardization consortia and achievable through existing working groups.
This review argues that immune reconstitution assessment after allogeneic hematopoietic cell transplantation is highly heterogeneous, which hampers the production of solid evidence and limits its potential use as a clinical endpoint, and that cross-center standardization is therefore needed, covering pre-analytical variables such as sample collection and handling as well as analytical procedures, drawing on the experience of international flow cytometry standardization consortia and achievable through existing working groups.
This review argues that immune reconstitution assessment after allogeneic hematopoietic cell transplantation is highly heterogeneous, which hampers the production of solid evidence and limits its potential use as a clinical endpoint, and that cross-center standardization is therefore needed, covering pre-analytical variables such as sample collection and handling as well as analytical procedures, drawing on the experience of international flow cytometry standardization consortia and achievable through existing working groups.
This review argues that immune reconstitution assessment after allogeneic hematopoietic cell transplantation is highly heterogeneous, which hampers the production of solid evidence and limits its potential use as a clinical endpoint, and that cross-center standardization is therefore needed, covering pre-analytical variables such as sample collection and handling as well as analytical procedures, drawing on the experience of international flow cytometry standardization consortia and achievable through existing working groups.
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery Drawing on the diagnostic and therapeutic characteristics of otology, rhinology, laryngology, and head and neck oncology, this article summarizes representative applications of multimodal artificial intelligence in otolaryngology–head and neck surgery, analyzes translational issues including data standards and cross-modal alignment, missing modalities and model generalization, privacy protection and multicenter collaboration, interpretability, clinical evidence, and workflow integration, and proposes establishing specialty data standards suited to clinical practice in China, building a staged multicenter validation system, forming a human–machine collaboration model supervised by specialty physicians, and cautiously advancing general and specialty large models toward multimodal clinical ap
Drawing on the diagnostic and therapeutic characteristics of otology, rhinology, laryngology, and head and neck oncology, this article summarizes representative applications of multimodal artificial intelligence in otolaryngology–head and neck surgery, analyzes translational issues including data standards and cross-modal alignment, missing modalities and model generalization, privacy protection and multicenter collaboration, interpretability, clinical evidence, and workflow integration, and proposes establishing specialty data standards suited to clinical practice in China, building a staged multicenter validation system, forming a human–machine collaboration model supervised by specialty physicians, and cautiously advancing general and specialty large models toward multimodal clinical ap
Drawing on the diagnostic and therapeutic characteristics of otology, rhinology, laryngology, and head and neck oncology, this article summarizes representative applications of multimodal artificial intelligence in otolaryngology–head and neck surgery, analyzes translational issues including data standards and cross-modal alignment, missing modalities and model generalization, privacy protection and multicenter collaboration, interpretability, clinical evidence, and workflow integration, and proposes establishing specialty data standards suited to clinical practice in China, building a staged multicenter validation system, forming a human–machine collaboration model supervised by specialty physicians, and cautiously advancing general and specialty large models toward multimodal clinical ap
Drawing on the diagnostic and therapeutic characteristics of otology, rhinology, laryngology, and head and neck oncology, this article summarizes representative applications of multimodal artificial intelligence in otolaryngology–head and neck surgery, analyzes translational issues including data standards and cross-modal alignment, missing modalities and model generalization, privacy protection and multicenter collaboration, interpretability, clinical evidence, and workflow integration, and proposes establishing specialty data standards suited to clinical practice in China, building a staged multicenter validation system, forming a human–machine collaboration model supervised by specialty physicians, and cautiously advancing general and specialty large models toward multimodal clinical ap
Journal of Zhejiang University(Science Edition) Using ADNI data, this study builds a patient-level multimodal fusion framework based on ResNet50 transfer learning that concatenates MRI and PET imaging features with clinical variables (ADAS11, ADAS13, APOE4, age, sex, education, MMSE total) in a fully connected network to produce three-way AD/MCI/CN predictions, with Grad-CAM heatmaps for explanation; the ablation shows accuracy rising as modalities are added, from 39.61% for MRI alone and 51.72% for PET alone to 66.67% for clinical-only, 54.17% for MRI+PET, and 79.17% for the full three-modality model on a 24-patient test cohort (95% Wilson interval roughly 59.5%-90.8%), with the addition of clinical data producing the single largest gain.
Using ADNI data, this study builds a patient-level multimodal fusion framework based on ResNet50 transfer learning that concatenates MRI and PET imaging features with clinical variables (ADAS11, ADAS13, APOE4, age, sex, education, MMSE total) in a fully connected network to produce three-way AD/MCI/CN predictions, with Grad-CAM heatmaps for explanation; the ablation shows accuracy rising as modalities are added, from 39.61% for MRI alone and 51.72% for PET alone to 66.67% for clinical-only, 54.17% for MRI+PET, and 79.17% for the full three-modality model on a 24-patient test cohort (95% Wilson interval roughly 59.5%-90.8%), with the addition of clinical data producing the single largest gain.
Using ADNI data, this study builds a patient-level multimodal fusion framework based on ResNet50 transfer learning that concatenates MRI and PET imaging features with clinical variables (ADAS11, ADAS13, APOE4, age, sex, education, MMSE total) in a fully connected network to produce three-way AD/MCI/CN predictions, with Grad-CAM heatmaps for explanation; the ablation shows accuracy rising as modalities are added, from 39.61% for MRI alone and 51.72% for PET alone to 66.67% for clinical-only, 54.17% for MRI+PET, and 79.17% for the full three-modality model on a 24-patient test cohort (95% Wilson interval roughly 59.5%-90.8%), with the addition of clinical data producing the single largest gain.
Using ADNI data, this study builds a patient-level multimodal fusion framework based on ResNet50 transfer learning that concatenates MRI and PET imaging features with clinical variables (ADAS11, ADAS13, APOE4, age, sex, education, MMSE total) in a fully connected network to produce three-way AD/MCI/CN predictions, with Grad-CAM heatmaps for explanation; the ablation shows accuracy rising as modalities are added, from 39.61% for MRI alone and 51.72% for PET alone to 66.67% for clinical-only, 54.17% for MRI+PET, and 79.17% for the full three-modality model on a 24-patient test cohort (95% Wilson interval roughly 59.5%-90.8%), with the addition of clinical data producing the single largest gain.
Pain management In this prospective cohort study, 96 patients with spinal pain completed an extensive questionnaire covering pain, mood, sleep, lifestyle, and treatment expectations at baseline and at 1 and 3 months, with binary recovery outcomes defined at 3 months for pain intensity, disability, quality of life, and Patient Global Impression of Change; a three-step machine learning framework combining SHAP-based candidate feature selection, Leave-One-Out Cross-Validation with permutation testing, and generalization testing yielded AUC values of 0.93-0.99 in LOOCV and 0.62-0.
In this prospective cohort study, 96 patients with spinal pain completed an extensive questionnaire covering pain, mood, sleep, lifestyle, and treatment expectations at baseline and at 1 and 3 months, with binary recovery outcomes defined at 3 months for pain intensity, disability, quality of life, and Patient Global Impression of Change; a three-step machine learning framework combining SHAP-based candidate feature selection, Leave-One-Out Cross-Validation with permutation testing, and generalization testing yielded AUC values of 0.93-0.99 in LOOCV and 0.62-0.
In this prospective cohort study, 96 patients with spinal pain completed an extensive questionnaire covering pain, mood, sleep, lifestyle, and treatment expectations at baseline and at 1 and 3 months, with binary recovery outcomes defined at 3 months for pain intensity, disability, quality of life, and Patient Global Impression of Change; a three-step machine learning framework combining SHAP-based candidate feature selection, Leave-One-Out Cross-Validation with permutation testing, and generalization testing yielded AUC values of 0.93-0.99 in LOOCV and 0.62-0.
In this prospective cohort study, 96 patients with spinal pain completed an extensive questionnaire covering pain, mood, sleep, lifestyle, and treatment expectations at baseline and at 1 and 3 months, with binary recovery outcomes defined at 3 months for pain intensity, disability, quality of life, and Patient Global Impression of Change; a three-step machine learning framework combining SHAP-based candidate feature selection, Leave-One-Out Cross-Validation with permutation testing, and generalization testing yielded AUC values of 0.93-0.99 in LOOCV and 0.62-0.
Lirias The book offers a body of concepts to encapsulate a threatened yet resistant urbanism, arguing that popular practices and knowledges within urban communities and neighbourhoods contain potentially reparative and curative elements, exemplified in the streets of Kinshasa, Lagos, Mexico City and Naples, and outlines an infrastructural and aesthetic politics to bring out that potential.
The book offers a body of concepts to encapsulate a threatened yet resistant urbanism, arguing that popular practices and knowledges within urban communities and neighbourhoods contain potentially reparative and curative elements, exemplified in the streets of Kinshasa, Lagos, Mexico City and Naples, and outlines an infrastructural and aesthetic politics to bring out that potential.
The book offers a body of concepts to encapsulate a threatened yet resistant urbanism, arguing that popular practices and knowledges within urban communities and neighbourhoods contain potentially reparative and curative elements, exemplified in the streets of Kinshasa, Lagos, Mexico City and Naples, and outlines an infrastructural and aesthetic politics to bring out that potential.
The book offers a body of concepts to encapsulate a threatened yet resistant urbanism, arguing that popular practices and knowledges within urban communities and neighbourhoods contain potentially reparative and curative elements, exemplified in the streets of Kinshasa, Lagos, Mexico City and Naples, and outlines an infrastructural and aesthetic politics to bring out that potential.
Nature medicine This work developed and evaluated a fully on-premise clinical AI agent that couples local operational control with a multi-perspective reliability framework to support selective autonomy, achieving 90.04% accuracy on a seven-disease task and 83.8% on a four-disease task across two MIMIC-IV-derived benchmarks, and finding that diagnostic behavioral consistency best discriminated correctness (AUC = 0.860, and AUC = 0.875 under stress testing), with a consistency threshold of 0.90 retaining 49.4% of cases at 98.9% diagnostic accuracy.
This work developed and evaluated a fully on-premise clinical AI agent that couples local operational control with a multi-perspective reliability framework to support selective autonomy, achieving 90.04% accuracy on a seven-disease task and 83.8% on a four-disease task across two MIMIC-IV-derived benchmarks, and finding that diagnostic behavioral consistency best discriminated correctness (AUC = 0.860, and AUC = 0.875 under stress testing), with a consistency threshold of 0.90 retaining 49.4% of cases at 98.9% diagnostic accuracy.
This work developed and evaluated a fully on-premise clinical AI agent that couples local operational control with a multi-perspective reliability framework to support selective autonomy, achieving 90.04% accuracy on a seven-disease task and 83.8% on a four-disease task across two MIMIC-IV-derived benchmarks, and finding that diagnostic behavioral consistency best discriminated correctness (AUC = 0.860, and AUC = 0.875 under stress testing), with a consistency threshold of 0.90 retaining 49.4% of cases at 98.9% diagnostic accuracy.
This work developed and evaluated a fully on-premise clinical AI agent that couples local operational control with a multi-perspective reliability framework to support selective autonomy, achieving 90.04% accuracy on a seven-disease task and 83.8% on a four-disease task across two MIMIC-IV-derived benchmarks, and finding that diagnostic behavioral consistency best discriminated correctness (AUC = 0.860, and AUC = 0.875 under stress testing), with a consistency threshold of 0.90 retaining 49.4% of cases at 98.9% diagnostic accuracy.
Journal of imaging informatics in medicine This work proposes LOCUS-Diff, a generative framework that combines a thyroid ultrasound synthesis foundation model, a nodule spatial control branch, and a COMB label-correction mechanism to produce synthetic samples judged by senior clinical experts in visual Turing tests as anatomically plausible and rivaling real scans, consistently outperforming the state of the art in downstream nodule detection on TN5000 and TN3k, and achieving higher mAP when augmenting a training subset with only 60% of real data with synthetic samples than training on the full real dataset.
This work proposes LOCUS-Diff, a generative framework that combines a thyroid ultrasound synthesis foundation model, a nodule spatial control branch, and a COMB label-correction mechanism to produce synthetic samples judged by senior clinical experts in visual Turing tests as anatomically plausible and rivaling real scans, consistently outperforming the state of the art in downstream nodule detection on TN5000 and TN3k, and achieving higher mAP when augmenting a training subset with only 60% of real data with synthetic samples than training on the full real dataset.
This work proposes LOCUS-Diff, a generative framework that combines a thyroid ultrasound synthesis foundation model, a nodule spatial control branch, and a COMB label-correction mechanism to produce synthetic samples judged by senior clinical experts in visual Turing tests as anatomically plausible and rivaling real scans, consistently outperforming the state of the art in downstream nodule detection on TN5000 and TN3k, and achieving higher mAP when augmenting a training subset with only 60% of real data with synthetic samples than training on the full real dataset.
This work proposes LOCUS-Diff, a generative framework that combines a thyroid ultrasound synthesis foundation model, a nodule spatial control branch, and a COMB label-correction mechanism to produce synthetic samples judged by senior clinical experts in visual Turing tests as anatomically plausible and rivaling real scans, consistently outperforming the state of the art in downstream nodule detection on TN5000 and TN3k, and achieving higher mAP when augmenting a training subset with only 60% of real data with synthetic samples than training on the full real dataset.
Expert Review of Clinical Immunology This review summarizes the established clinical framework for atopic dermatitis (AD) diagnosis alongside emerging tools intended to complement it—circulating and skin-derived biomarkers, minimally invasive tape stripping, the skin microbiome, instrumental barrier assessment, noninvasive biofluids, advanced optical imaging (reflectance confocal microscopy, optical coherence tomography and line-field confocal OCT), and artificial-intelligence and digital tools, with attention to special populations—concluding that clinical diagnosis remains the reference standard, that the experienced clinician still outperforms any single test, and that these tools are promising adjuncts though few are standardized or prospectively validated.
This review summarizes the established clinical framework for atopic dermatitis (AD) diagnosis alongside emerging tools intended to complement it—circulating and skin-derived biomarkers, minimally invasive tape stripping, the skin microbiome, instrumental barrier assessment, noninvasive biofluids, advanced optical imaging (reflectance confocal microscopy, optical coherence tomography and line-field confocal OCT), and artificial-intelligence and digital tools, with attention to special populations—concluding that clinical diagnosis remains the reference standard, that the experienced clinician still outperforms any single test, and that these tools are promising adjuncts though few are standardized or prospectively validated.
This review summarizes the established clinical framework for atopic dermatitis (AD) diagnosis alongside emerging tools intended to complement it—circulating and skin-derived biomarkers, minimally invasive tape stripping, the skin microbiome, instrumental barrier assessment, noninvasive biofluids, advanced optical imaging (reflectance confocal microscopy, optical coherence tomography and line-field confocal OCT), and artificial-intelligence and digital tools, with attention to special populations—concluding that clinical diagnosis remains the reference standard, that the experienced clinician still outperforms any single test, and that these tools are promising adjuncts though few are standardized or prospectively validated.
This review summarizes the established clinical framework for atopic dermatitis (AD) diagnosis alongside emerging tools intended to complement it—circulating and skin-derived biomarkers, minimally invasive tape stripping, the skin microbiome, instrumental barrier assessment, noninvasive biofluids, advanced optical imaging (reflectance confocal microscopy, optical coherence tomography and line-field confocal OCT), and artificial-intelligence and digital tools, with attention to special populations—concluding that clinical diagnosis remains the reference standard, that the experienced clinician still outperforms any single test, and that these tools are promising adjuncts though few are standardized or prospectively validated.
Journal of Zhejiang University(Science Edition) This paper presents Universal Doc AI, a multimodal intelligent document management system that unifies Optical Character Recognition (OCR), Retrieval-Augmented Generation (RAG), vector-based semantic search, and Large Language Models (LLMs) into a single platform that extracts text from user-uploaded PDFs, scans, images, and handwritten notes, chunks and embeds it for vector indexing, and answers natural-language questions grounded in the uploaded documents, reporting improvements in retrieval accuracy, response relevance, and interaction efficiency over traditional keyword-based search.
This paper presents Universal Doc AI, a multimodal intelligent document management system that unifies Optical Character Recognition (OCR), Retrieval-Augmented Generation (RAG), vector-based semantic search, and Large Language Models (LLMs) into a single platform that extracts text from user-uploaded PDFs, scans, images, and handwritten notes, chunks and embeds it for vector indexing, and answers natural-language questions grounded in the uploaded documents, reporting improvements in retrieval accuracy, response relevance, and interaction efficiency over traditional keyword-based search.
This paper presents Universal Doc AI, a multimodal intelligent document management system that unifies Optical Character Recognition (OCR), Retrieval-Augmented Generation (RAG), vector-based semantic search, and Large Language Models (LLMs) into a single platform that extracts text from user-uploaded PDFs, scans, images, and handwritten notes, chunks and embeds it for vector indexing, and answers natural-language questions grounded in the uploaded documents, reporting improvements in retrieval accuracy, response relevance, and interaction efficiency over traditional keyword-based search.
This paper presents Universal Doc AI, a multimodal intelligent document management system that unifies Optical Character Recognition (OCR), Retrieval-Augmented Generation (RAG), vector-based semantic search, and Large Language Models (LLMs) into a single platform that extracts text from user-uploaded PDFs, scans, images, and handwritten notes, chunks and embeds it for vector indexing, and answers natural-language questions grounded in the uploaded documents, reporting improvements in retrieval accuracy, response relevance, and interaction efficiency over traditional keyword-based search.
Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery This article systematically reviews the current applications, main problems, and future directions of medical AI image technology in the precision diagnosis and treatment of head and neck tumors, noting that the technology enables precise quantification of imaging features and opens new paths for early identification, efficacy evaluation, and prognosis prediction, while still facing challenges such as insufficient data standardization, limited model generalization, poor interpretability, and insufficient clinical translation.
This article systematically reviews the current applications, main problems, and future directions of medical AI image technology in the precision diagnosis and treatment of head and neck tumors, noting that the technology enables precise quantification of imaging features and opens new paths for early identification, efficacy evaluation, and prognosis prediction, while still facing challenges such as insufficient data standardization, limited model generalization, poor interpretability, and insufficient clinical translation.
This article systematically reviews the current applications, main problems, and future directions of medical AI image technology in the precision diagnosis and treatment of head and neck tumors, noting that the technology enables precise quantification of imaging features and opens new paths for early identification, efficacy evaluation, and prognosis prediction, while still facing challenges such as insufficient data standardization, limited model generalization, poor interpretability, and insufficient clinical translation.
This article systematically reviews the current applications, main problems, and future directions of medical AI image technology in the precision diagnosis and treatment of head and neck tumors, noting that the technology enables precise quantification of imaging features and opens new paths for early identification, efficacy evaluation, and prognosis prediction, while still facing challenges such as insufficient data standardization, limited model generalization, poor interpretability, and insufficient clinical translation.
The Journal of asthma : official journal of the Association for the Care of Asthma Using the Japanese JAMDAS electronic medical records database, this retrospective observational study analyzed 32,258 patients with asthma who initiated fluticasone furoate/umeclidinium/vilanterol single-inhaler triple therapy between August 18, 2020 and December 31, 2024, extracting Asthma Control Test scores via structured query language and hospitalization and emergency transport data via a large language model, and assessed the proportion meeting the Japanese Practical Guidelines for Asthma Management 2024 clinical remission definition (oral corticosteroid-free, no exacerbations, ACT >= 23), treatment patterns, adherence and persistence at 3-month intervals up to 18 months; only 1.8-3.0%, 0.5-1.5% and 4.5-10.
Using the Japanese JAMDAS electronic medical records database, this retrospective observational study analyzed 32,258 patients with asthma who initiated fluticasone furoate/umeclidinium/vilanterol single-inhaler triple therapy between August 18, 2020 and December 31, 2024, extracting Asthma Control Test scores via structured query language and hospitalization and emergency transport data via a large language model, and assessed the proportion meeting the Japanese Practical Guidelines for Asthma Management 2024 clinical remission definition (oral corticosteroid-free, no exacerbations, ACT >= 23), treatment patterns, adherence and persistence at 3-month intervals up to 18 months; only 1.8-3.0%, 0.5-1.5% and 4.5-10.
Using the Japanese JAMDAS electronic medical records database, this retrospective observational study analyzed 32,258 patients with asthma who initiated fluticasone furoate/umeclidinium/vilanterol single-inhaler triple therapy between August 18, 2020 and December 31, 2024, extracting Asthma Control Test scores via structured query language and hospitalization and emergency transport data via a large language model, and assessed the proportion meeting the Japanese Practical Guidelines for Asthma Management 2024 clinical remission definition (oral corticosteroid-free, no exacerbations, ACT >= 23), treatment patterns, adherence and persistence at 3-month intervals up to 18 months; only 1.8-3.0%, 0.5-1.5% and 4.5-10.
Using the Japanese JAMDAS electronic medical records database, this retrospective observational study analyzed 32,258 patients with asthma who initiated fluticasone furoate/umeclidinium/vilanterol single-inhaler triple therapy between August 18, 2020 and December 31, 2024, extracting Asthma Control Test scores via structured query language and hospitalization and emergency transport data via a large language model, and assessed the proportion meeting the Japanese Practical Guidelines for Asthma Management 2024 clinical remission definition (oral corticosteroid-free, no exacerbations, ACT >= 23), treatment patterns, adherence and persistence at 3-month intervals up to 18 months; only 1.8-3.0%, 0.5-1.5% and 4.5-10.
Research Square This preprint trained five backbones under duplicate-controlled image-level partitioning (387 thyroid ultrasound images and 1,332 fine-needle aspiration cytology blocks from 385 public cases, labelled by postoperative diagnosis) and applied the frozen models to TN3K (n = 1,228, dataset-provided benign/malignant labels) and to a DDTI endpoint derived from radiologist TI-RADS categories (n = 637), finding ultrasound ensemble AUROC 0.825 and ResNet-50 0.888 on TN3K versus 0.477 and 0.437 against the TI-RADS-derived endpoint, with a cytology benchmark AUROC of 0.986 (0.970–0.998) against 0.733 for the ultrasound ensemble, while noting that cohort, acquisition and endpoint changed together so the contrast cannot be attributed to label definition alone.
This preprint trained five backbones under duplicate-controlled image-level partitioning (387 thyroid ultrasound images and 1,332 fine-needle aspiration cytology blocks from 385 public cases, labelled by postoperative diagnosis) and applied the frozen models to TN3K (n = 1,228, dataset-provided benign/malignant labels) and to a DDTI endpoint derived from radiologist TI-RADS categories (n = 637), finding ultrasound ensemble AUROC 0.825 and ResNet-50 0.888 on TN3K versus 0.477 and 0.437 against the TI-RADS-derived endpoint, with a cytology benchmark AUROC of 0.986 (0.970–0.998) against 0.733 for the ultrasound ensemble, while noting that cohort, acquisition and endpoint changed together so the contrast cannot be attributed to label definition alone.
This preprint trained five backbones under duplicate-controlled image-level partitioning (387 thyroid ultrasound images and 1,332 fine-needle aspiration cytology blocks from 385 public cases, labelled by postoperative diagnosis) and applied the frozen models to TN3K (n = 1,228, dataset-provided benign/malignant labels) and to a DDTI endpoint derived from radiologist TI-RADS categories (n = 637), finding ultrasound ensemble AUROC 0.825 and ResNet-50 0.888 on TN3K versus 0.477 and 0.437 against the TI-RADS-derived endpoint, with a cytology benchmark AUROC of 0.986 (0.970–0.998) against 0.733 for the ultrasound ensemble, while noting that cohort, acquisition and endpoint changed together so the contrast cannot be attributed to label definition alone.
This preprint trained five backbones under duplicate-controlled image-level partitioning (387 thyroid ultrasound images and 1,332 fine-needle aspiration cytology blocks from 385 public cases, labelled by postoperative diagnosis) and applied the frozen models to TN3K (n = 1,228, dataset-provided benign/malignant labels) and to a DDTI endpoint derived from radiologist TI-RADS categories (n = 637), finding ultrasound ensemble AUROC 0.825 and ResNet-50 0.888 on TN3K versus 0.477 and 0.437 against the TI-RADS-derived endpoint, with a cytology benchmark AUROC of 0.986 (0.970–0.998) against 0.733 for the ultrasound ensemble, while noting that cohort, acquisition and endpoint changed together so the contrast cannot be attributed to label definition alone.
Research Square In this exploratory cross-sectional study, 68 investigator-developed, evidence-mapped English prompts, each containing a false, absolute, unsafe, or contested premise, were submitted once in independent single-turn conversations to ChatGPT (GPT-5), Gemini 2.5 Pro, Microsoft Copilot, DeepSeek-V3.2-Exp, and Doubao-Seed-1.6, yielding 340 complete responses that five clinicians independently scored, showing that 307 responses (90.3%) were classified safe and 33 (9.7%) unsafe, with safe-response rates from 85.3% to 94.1% and a non-significant omnibus safety comparison (P = 0.203) that was not interpreted as equivalence, while all six graded outcomes differed across models (all P < 0.
In this exploratory cross-sectional study, 68 investigator-developed, evidence-mapped English prompts, each containing a false, absolute, unsafe, or contested premise, were submitted once in independent single-turn conversations to ChatGPT (GPT-5), Gemini 2.5 Pro, Microsoft Copilot, DeepSeek-V3.2-Exp, and Doubao-Seed-1.6, yielding 340 complete responses that five clinicians independently scored, showing that 307 responses (90.3%) were classified safe and 33 (9.7%) unsafe, with safe-response rates from 85.3% to 94.1% and a non-significant omnibus safety comparison (P = 0.203) that was not interpreted as equivalence, while all six graded outcomes differed across models (all P < 0.
In this exploratory cross-sectional study, 68 investigator-developed, evidence-mapped English prompts, each containing a false, absolute, unsafe, or contested premise, were submitted once in independent single-turn conversations to ChatGPT (GPT-5), Gemini 2.5 Pro, Microsoft Copilot, DeepSeek-V3.2-Exp, and Doubao-Seed-1.6, yielding 340 complete responses that five clinicians independently scored, showing that 307 responses (90.3%) were classified safe and 33 (9.7%) unsafe, with safe-response rates from 85.3% to 94.1% and a non-significant omnibus safety comparison (P = 0.203) that was not interpreted as equivalence, while all six graded outcomes differed across models (all P < 0.
In this exploratory cross-sectional study, 68 investigator-developed, evidence-mapped English prompts, each containing a false, absolute, unsafe, or contested premise, were submitted once in independent single-turn conversations to ChatGPT (GPT-5), Gemini 2.5 Pro, Microsoft Copilot, DeepSeek-V3.2-Exp, and Doubao-Seed-1.6, yielding 340 complete responses that five clinicians independently scored, showing that 307 responses (90.3%) were classified safe and 33 (9.7%) unsafe, with safe-response rates from 85.3% to 94.1% and a non-significant omnibus safety comparison (P = 0.203) that was not interpreted as equivalence, while all six graded outcomes differed across models (all P < 0.
Movement disorders clinical practice Using data from the TRANQUIL multicenter randomized controlled trial, this study estimated minimal clinically important differences (MCIDs) for the modified activities of daily living (mADL) and mADL11 scales of TETRAS in essential tremor via anchor-based approaches (CGI-I and PGI-I) and ROC analyses, recommending patient-report-based MCIDs of -6.2 for mADL and -4.1 for mADL11.
Using data from the TRANQUIL multicenter randomized controlled trial, this study estimated minimal clinically important differences (MCIDs) for the modified activities of daily living (mADL) and mADL11 scales of TETRAS in essential tremor via anchor-based approaches (CGI-I and PGI-I) and ROC analyses, recommending patient-report-based MCIDs of -6.2 for mADL and -4.1 for mADL11.
Using data from the TRANQUIL multicenter randomized controlled trial, this study estimated minimal clinically important differences (MCIDs) for the modified activities of daily living (mADL) and mADL11 scales of TETRAS in essential tremor via anchor-based approaches (CGI-I and PGI-I) and ROC analyses, recommending patient-report-based MCIDs of -6.2 for mADL and -4.1 for mADL11.
Using data from the TRANQUIL multicenter randomized controlled trial, this study estimated minimal clinically important differences (MCIDs) for the modified activities of daily living (mADL) and mADL11 scales of TETRAS in essential tremor via anchor-based approaches (CGI-I and PGI-I) and ROC analyses, recommending patient-report-based MCIDs of -6.2 for mADL and -4.1 for mADL11.
Research Explorer (The University of Manchester) Drawing on Karen Barad's (2007) concepts of intra-action and the agential cut, this chapter employs a poetic inquiry approach situated in three multi-academy trusts in England, and through two agential cuts embodied in distinct poetic forms materialises how place entangles with governance policy, architecture, and actors to configure parental engagement, thereby repositioning place as a co-agentic participant in governance.
Drawing on Karen Barad's (2007) concepts of intra-action and the agential cut, this chapter employs a poetic inquiry approach situated in three multi-academy trusts in England, and through two agential cuts embodied in distinct poetic forms materialises how place entangles with governance policy, architecture, and actors to configure parental engagement, thereby repositioning place as a co-agentic participant in governance.
Drawing on Karen Barad's (2007) concepts of intra-action and the agential cut, this chapter employs a poetic inquiry approach situated in three multi-academy trusts in England, and through two agential cuts embodied in distinct poetic forms materialises how place entangles with governance policy, architecture, and actors to configure parental engagement, thereby repositioning place as a co-agentic participant in governance.
Drawing on Karen Barad's (2007) concepts of intra-action and the agential cut, this chapter employs a poetic inquiry approach situated in three multi-academy trusts in England, and through two agential cuts embodied in distinct poetic forms materialises how place entangles with governance policy, architecture, and actors to configure parental engagement, thereby repositioning place as a co-agentic participant in governance.
Journal of imaging informatics in medicine This study developed and dual-center validated an interpretable U-Net-based AI framework for automated quality control (QC) of knee anteroposterior (AP) and lateral (LAT) radiographs, generating QC indices through anatomical segmentation and landmark localization, with mean Dice similarity coefficients of 0.964 and 0.936 in internal and external validation, most intraclass correlation coefficients exceeding 0.90, QC sensitivity of 91.67% to 98.36% and specificity of 89.13% to 99.10%; separately, six radiographers who received 4 weeks of AI-based feedback on 948 radiographs from 474 patients showed exploratory numerical gains in sensitivity, with effect sizes of 0.30 to 0.73.
This study developed and dual-center validated an interpretable U-Net-based AI framework for automated quality control (QC) of knee anteroposterior (AP) and lateral (LAT) radiographs, generating QC indices through anatomical segmentation and landmark localization, with mean Dice similarity coefficients of 0.964 and 0.936 in internal and external validation, most intraclass correlation coefficients exceeding 0.90, QC sensitivity of 91.67% to 98.36% and specificity of 89.13% to 99.10%; separately, six radiographers who received 4 weeks of AI-based feedback on 948 radiographs from 474 patients showed exploratory numerical gains in sensitivity, with effect sizes of 0.30 to 0.73.
This study developed and dual-center validated an interpretable U-Net-based AI framework for automated quality control (QC) of knee anteroposterior (AP) and lateral (LAT) radiographs, generating QC indices through anatomical segmentation and landmark localization, with mean Dice similarity coefficients of 0.964 and 0.936 in internal and external validation, most intraclass correlation coefficients exceeding 0.90, QC sensitivity of 91.67% to 98.36% and specificity of 89.13% to 99.10%; separately, six radiographers who received 4 weeks of AI-based feedback on 948 radiographs from 474 patients showed exploratory numerical gains in sensitivity, with effect sizes of 0.30 to 0.73.
This study developed and dual-center validated an interpretable U-Net-based AI framework for automated quality control (QC) of knee anteroposterior (AP) and lateral (LAT) radiographs, generating QC indices through anatomical segmentation and landmark localization, with mean Dice similarity coefficients of 0.964 and 0.936 in internal and external validation, most intraclass correlation coefficients exceeding 0.90, QC sensitivity of 91.67% to 98.36% and specificity of 89.13% to 99.10%; separately, six radiographers who received 4 weeks of AI-based feedback on 948 radiographs from 474 patients showed exploratory numerical gains in sensitivity, with effect sizes of 0.30 to 0.73.
Cancer This review synthesizes the clinical evidence and resistance mechanisms for immunotherapy in ovarian cancer, noting that single-agent immune checkpoint inhibitors achieve objective response rates generally below 15% in recurrent disease, that the clearest added benefit appears in chemotherapy-based combinations for PD-L1-positive platinum-resistant disease (e.g., in ENGOT-ov65/KEYNOTE-B96, median overall survival 18.2 vs 14.0 months in the CPS >=1 population, HR 0.
This review synthesizes the clinical evidence and resistance mechanisms for immunotherapy in ovarian cancer, noting that single-agent immune checkpoint inhibitors achieve objective response rates generally below 15% in recurrent disease, that the clearest added benefit appears in chemotherapy-based combinations for PD-L1-positive platinum-resistant disease (e.g., in ENGOT-ov65/KEYNOTE-B96, median overall survival 18.2 vs 14.0 months in the CPS >=1 population, HR 0.
This review synthesizes the clinical evidence and resistance mechanisms for immunotherapy in ovarian cancer, noting that single-agent immune checkpoint inhibitors achieve objective response rates generally below 15% in recurrent disease, that the clearest added benefit appears in chemotherapy-based combinations for PD-L1-positive platinum-resistant disease (e.g., in ENGOT-ov65/KEYNOTE-B96, median overall survival 18.2 vs 14.0 months in the CPS >=1 population, HR 0.
This review synthesizes the clinical evidence and resistance mechanisms for immunotherapy in ovarian cancer, noting that single-agent immune checkpoint inhibitors achieve objective response rates generally below 15% in recurrent disease, that the clearest added benefit appears in chemotherapy-based combinations for PD-L1-positive platinum-resistant disease (e.g., in ENGOT-ov65/KEYNOTE-B96, median overall survival 18.2 vs 14.0 months in the CPS >=1 population, HR 0.
bioRxiv Using cerastecin Cpd 4 as a template, this study applied two AI tools, Link-INVENT and AutoMolDesigner, for molecular design and chemical derivatization, leading to the discovery of the MsbA-targeted small molecule Y-11 with an MIC of 0.5 g/mL against A. baumannii, equivalent potency to Cpd4 against carbapenem-resistant A. baumannii, lower cytotoxicity, hemolysis, and spontaneous resistance frequency, effective reduction of bacterial loads in infected mice, and a proposed mechanism in which Y-11 inhibits lipooligosaccharide transport and impairs outer membrane formation, probably by competitively binding the substrate binding site of MsbA and modulating ATPase activity.
Using cerastecin Cpd 4 as a template, this study applied two AI tools, Link-INVENT and AutoMolDesigner, for molecular design and chemical derivatization, leading to the discovery of the MsbA-targeted small molecule Y-11 with an MIC of 0.5 g/mL against A. baumannii, equivalent potency to Cpd4 against carbapenem-resistant A. baumannii, lower cytotoxicity, hemolysis, and spontaneous resistance frequency, effective reduction of bacterial loads in infected mice, and a proposed mechanism in which Y-11 inhibits lipooligosaccharide transport and impairs outer membrane formation, probably by competitively binding the substrate binding site of MsbA and modulating ATPase activity.
Using cerastecin Cpd 4 as a template, this study applied two AI tools, Link-INVENT and AutoMolDesigner, for molecular design and chemical derivatization, leading to the discovery of the MsbA-targeted small molecule Y-11 with an MIC of 0.5 g/mL against A. baumannii, equivalent potency to Cpd4 against carbapenem-resistant A. baumannii, lower cytotoxicity, hemolysis, and spontaneous resistance frequency, effective reduction of bacterial loads in infected mice, and a proposed mechanism in which Y-11 inhibits lipooligosaccharide transport and impairs outer membrane formation, probably by competitively binding the substrate binding site of MsbA and modulating ATPase activity.
Using cerastecin Cpd 4 as a template, this study applied two AI tools, Link-INVENT and AutoMolDesigner, for molecular design and chemical derivatization, leading to the discovery of the MsbA-targeted small molecule Y-11 with an MIC of 0.5 g/mL against A. baumannii, equivalent potency to Cpd4 against carbapenem-resistant A. baumannii, lower cytotoxicity, hemolysis, and spontaneous resistance frequency, effective reduction of bacterial loads in infected mice, and a proposed mechanism in which Y-11 inhibits lipooligosaccharide transport and impairs outer membrane formation, probably by competitively binding the substrate binding site of MsbA and modulating ATPase activity.
Primary health care research & development This study proposes a hybrid deep learning framework that fuses a static periocular ResNet18 classifier with a facial-image ensemble of ResNet50, EfficientNet-B0 and DenseNet121 under an OR-based parallel rule for early autism spectrum disorder risk indication and referral support; the periocular model reached 90% sensitivity, the facial ensemble reached 87.1% sensitivity with an AUC of 0.948, and under a conditional-independence assumption the analytically estimated system-level sensitivity was 0.9871, corresponding to a joint false-negative probability of about 1.29%, while system specificity fell to roughly 0.807.
This study proposes a hybrid deep learning framework that fuses a static periocular ResNet18 classifier with a facial-image ensemble of ResNet50, EfficientNet-B0 and DenseNet121 under an OR-based parallel rule for early autism spectrum disorder risk indication and referral support; the periocular model reached 90% sensitivity, the facial ensemble reached 87.1% sensitivity with an AUC of 0.948, and under a conditional-independence assumption the analytically estimated system-level sensitivity was 0.9871, corresponding to a joint false-negative probability of about 1.29%, while system specificity fell to roughly 0.807.
This study proposes a hybrid deep learning framework that fuses a static periocular ResNet18 classifier with a facial-image ensemble of ResNet50, EfficientNet-B0 and DenseNet121 under an OR-based parallel rule for early autism spectrum disorder risk indication and referral support; the periocular model reached 90% sensitivity, the facial ensemble reached 87.1% sensitivity with an AUC of 0.948, and under a conditional-independence assumption the analytically estimated system-level sensitivity was 0.9871, corresponding to a joint false-negative probability of about 1.29%, while system specificity fell to roughly 0.807.
This study proposes a hybrid deep learning framework that fuses a static periocular ResNet18 classifier with a facial-image ensemble of ResNet50, EfficientNet-B0 and DenseNet121 under an OR-based parallel rule for early autism spectrum disorder risk indication and referral support; the periocular model reached 90% sensitivity, the facial ensemble reached 87.1% sensitivity with an AUC of 0.948, and under a conditional-independence assumption the analytically estimated system-level sensitivity was 0.9871, corresponding to a joint false-negative probability of about 1.29%, while system specificity fell to roughly 0.807.
Nature News This Nature news report surveys the global hunt for natural geological hydrogen now underway in almost 30 countries: venture capitalists have invested nearly US$500 million since 2023, a 2024 analysis suggests Earth's subsurface probably holds tens of trillions of tonnes of the gas, and if even a small fraction can be recovered at a profit it could meet projected clean-energy needs for 200 years, yet nobody knows whether deposits large enough to match the hype exist, with results from several wells expected within months.
This Nature news report surveys the global hunt for natural geological hydrogen now underway in almost 30 countries: venture capitalists have invested nearly US$500 million since 2023, a 2024 analysis suggests Earth's subsurface probably holds tens of trillions of tonnes of the gas, and if even a small fraction can be recovered at a profit it could meet projected clean-energy needs for 200 years, yet nobody knows whether deposits large enough to match the hype exist, with results from several wells expected within months.
This Nature news report surveys the global hunt for natural geological hydrogen now underway in almost 30 countries: venture capitalists have invested nearly US$500 million since 2023, a 2024 analysis suggests Earth's subsurface probably holds tens of trillions of tonnes of the gas, and if even a small fraction can be recovered at a profit it could meet projected clean-energy needs for 200 years, yet nobody knows whether deposits large enough to match the hype exist, with results from several wells expected within months.
This Nature news report surveys the global hunt for natural geological hydrogen now underway in almost 30 countries: venture capitalists have invested nearly US$500 million since 2023, a 2024 analysis suggests Earth's subsurface probably holds tens of trillions of tonnes of the gas, and if even a small fraction can be recovered at a profit it could meet projected clean-energy needs for 200 years, yet nobody knows whether deposits large enough to match the hype exist, with results from several wells expected within months.
Nature News A study in mice shows that after infection with gut-illness-causing bacteria (Citrobacter rodentium) or parasites (Schistosoma mansoni), CD4+ T cells from the gut migrate through the bloodstream to the meninges surrounding the central nervous system and take up residence there, still responding to a second round of infection more than a month later, suggesting they keep a record of past illness.
A study in mice shows that after infection with gut-illness-causing bacteria (Citrobacter rodentium) or parasites (Schistosoma mansoni), CD4+ T cells from the gut migrate through the bloodstream to the meninges surrounding the central nervous system and take up residence there, still responding to a second round of infection more than a month later, suggesting they keep a record of past illness.
A study in mice shows that after infection with gut-illness-causing bacteria (Citrobacter rodentium) or parasites (Schistosoma mansoni), CD4+ T cells from the gut migrate through the bloodstream to the meninges surrounding the central nervous system and take up residence there, still responding to a second round of infection more than a month later, suggesting they keep a record of past illness.
A study in mice shows that after infection with gut-illness-causing bacteria (Citrobacter rodentium) or parasites (Schistosoma mansoni), CD4+ T cells from the gut migrate through the bloodstream to the meninges surrounding the central nervous system and take up residence there, still responding to a second round of infection more than a month later, suggesting they keep a record of past illness.