Medicine & Health

469 items

Research Square Sep 15, 2026
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.
Generative AI Responses to Patient-Presented Orthodontic Misinformation and Controversial Claims: A Comparative Cross-Sectional Evaluation of Safety, Accuracy, Evidence Concordance, Misinformation Correction, Uncertainty Communication, Transparency, and Actionability
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.
Journal of imaging informatics in medicine Sep 15, 2026
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.
LOCUS-Diff: Location-Controlled Thyroid Ultrasound Synthesis for Advancing Nodule Detection
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.
Health Science Reports Sep 14, 2026
Following PRISMA, this review searched PubMed, Web of Science, and Scopus (January 1, 2019 to March 27, 2025), included 58 of 1923 records, and used the CRISP-DM phases (problem understanding, data understanding, data preparation, modeling, evaluation, deployment) to organize machine learning approaches to noninvasive anemia detection and hemoglobin estimation, covering algorithms, data sources, acquisition sites, light sources, evaluation metrics, and deployment, alongside a PROBAST appraisal of risk of bias and applicability.
Following PRISMA, this review searched PubMed, Web of Science, and Scopus (January 1, 2019 to March 27, 2025), included 58 of 1923 records, and used the CRISP-DM phases (problem understanding, data understanding, data preparation, modeling, evaluation, deployment) to organize machine learning approaches to noninvasive anemia detection and hemoglobin estimation, covering algorithms, data sources, acquisition sites, light sources, evaluation metrics, and deployment, alongside a PROBAST appraisal of risk of bias and applicability.
Machine Learning for Noninvasive Anemia Diagnosis: A Systematic Review Based on CRISP-DM
Following PRISMA, this review searched PubMed, Web of Science, and Scopus (January 1, 2019 to March 27, 2025), included 58 of 1923 records, and used the CRISP-DM phases (problem understanding, data understanding, data preparation, modeling, evaluation, deployment) to organize machine learning approaches to noninvasive anemia detection and hemoglobin estimation, covering algorithms, data sources, acquisition sites, light sources, evaluation metrics, and deployment, alongside a PROBAST appraisal of risk of bias and applicability.
Following PRISMA, this review searched PubMed, Web of Science, and Scopus (January 1, 2019 to March 27, 2025), included 58 of 1923 records, and used the CRISP-DM phases (problem understanding, data understanding, data preparation, modeling, evaluation, deployment) to organize machine learning approaches to noninvasive anemia detection and hemoglobin estimation, covering algorithms, data sources, acquisition sites, light sources, evaluation metrics, and deployment, alongside a PROBAST appraisal of risk of bias and applicability.
medRxiv Sep 14, 2026
This study conducted a systematic mapping and bibliometric analysis of 4,143 publications from 2015 to 2025 on AI-generated synthetic data in biomedicine, combining expert annotation with LLM-assisted classification across data modality, medical domain, paper type, deployment status, and research stance, finding continuous growth in publication volume, 77.8% of papers strongly supportive with critical work below 1%, medical imaging dominating the corpus, highly cited primary research concentrated in molecular and pharmaceutical applications, and only 27 publications reporting operational use, thereby revealing a gap between methodological growth and deployment.
This study conducted a systematic mapping and bibliometric analysis of 4,143 publications from 2015 to 2025 on AI-generated synthetic data in biomedicine, combining expert annotation with LLM-assisted classification across data modality, medical domain, paper type, deployment status, and research stance, finding continuous growth in publication volume, 77.8% of papers strongly supportive with critical work below 1%, medical imaging dominating the corpus, highly cited primary research concentrated in molecular and pharmaceutical applications, and only 27 publications reporting operational use, thereby revealing a gap between methodological growth and deployment.
AI-Based Synthetic Data in Biomedicine: A Decade of Growth and a Persistent Translation Gap
This study conducted a systematic mapping and bibliometric analysis of 4,143 publications from 2015 to 2025 on AI-generated synthetic data in biomedicine, combining expert annotation with LLM-assisted classification across data modality, medical domain, paper type, deployment status, and research stance, finding continuous growth in publication volume, 77.8% of papers strongly supportive with critical work below 1%, medical imaging dominating the corpus, highly cited primary research concentrated in molecular and pharmaceutical applications, and only 27 publications reporting operational use, thereby revealing a gap between methodological growth and deployment.
This study conducted a systematic mapping and bibliometric analysis of 4,143 publications from 2015 to 2025 on AI-generated synthetic data in biomedicine, combining expert annotation with LLM-assisted classification across data modality, medical domain, paper type, deployment status, and research stance, finding continuous growth in publication volume, 77.8% of papers strongly supportive with critical work below 1%, medical imaging dominating the corpus, highly cited primary research concentrated in molecular and pharmaceutical applications, and only 27 publications reporting operational use, thereby revealing a gap between methodological growth and deployment.
Intelligent Computing Sep 14, 2026
This survey systematically reviews prompt engineering research for SAM and its growing ecosystem, proposing a hierarchical taxonomy that organizes methods into geometric prompts, textual semantic prompts, and multimodal fusion prompts, further tracing the transition from manually crafted prompts to automated generation based on detector outputs, prototype learning, reinforcement learning, and vision-language models, while tracing how prompt engineering enables cross-domain generalization in medical imaging, remote sensing, industrial inspection, and anomaly detection, and identifying key challenges such as prompt sensitivity, cross-modal misalignment, and computational inefficiency alongside future directions including causal prompt reasoning, collaborative multi-agent prompting, and diffu
This survey systematically reviews prompt engineering research for SAM and its growing ecosystem, proposing a hierarchical taxonomy that organizes methods into geometric prompts, textual semantic prompts, and multimodal fusion prompts, further tracing the transition from manually crafted prompts to automated generation based on detector outputs, prototype learning, reinforcement learning, and vision-language models, while tracing how prompt engineering enables cross-domain generalization in medical imaging, remote sensing, industrial inspection, and anomaly detection, and identifying key challenges such as prompt sensitivity, cross-modal misalignment, and computational inefficiency alongside future directions including causal prompt reasoning, collaborative multi-agent prompting, and diffu
Prompt Engineering in the Segment Anything Model: Methodologies, Applications, and Emerging Challenges
This survey systematically reviews prompt engineering research for SAM and its growing ecosystem, proposing a hierarchical taxonomy that organizes methods into geometric prompts, textual semantic prompts, and multimodal fusion prompts, further tracing the transition from manually crafted prompts to automated generation based on detector outputs, prototype learning, reinforcement learning, and vision-language models, while tracing how prompt engineering enables cross-domain generalization in medical imaging, remote sensing, industrial inspection, and anomaly detection, and identifying key challenges such as prompt sensitivity, cross-modal misalignment, and computational inefficiency alongside future directions including causal prompt reasoning, collaborative multi-agent prompting, and diffu
This survey systematically reviews prompt engineering research for SAM and its growing ecosystem, proposing a hierarchical taxonomy that organizes methods into geometric prompts, textual semantic prompts, and multimodal fusion prompts, further tracing the transition from manually crafted prompts to automated generation based on detector outputs, prototype learning, reinforcement learning, and vision-language models, while tracing how prompt engineering enables cross-domain generalization in medical imaging, remote sensing, industrial inspection, and anomaly detection, and identifying key challenges such as prompt sensitivity, cross-modal misalignment, and computational inefficiency alongside future directions including causal prompt reasoning, collaborative multi-agent prompting, and diffu
medRxiv Sep 14, 2026
This study investigated AI acceptability among parents (first cohort n = 198; second cohort n = 79) and pediatric healthcare professionals (n = 33) across different disease, diagnosis, or treatment scenarios, finding that more liberal data privacy was associated with reduced willingness to use AI (p < .001), higher perceived disease severity was linked to higher willingness to use AI in the second parent group (beta = .10, p = .013), and when AI and clinician recommendations conflicted, parents were more likely to choose AI over clinician judgment in treatment compared to diagnosis scenarios, with healthcare professionals showing similar patterns but additionally weighting perceived disease severity.
This study investigated AI acceptability among parents (first cohort n = 198; second cohort n = 79) and pediatric healthcare professionals (n = 33) across different disease, diagnosis, or treatment scenarios, finding that more liberal data privacy was associated with reduced willingness to use AI (p < .001), higher perceived disease severity was linked to higher willingness to use AI in the second parent group (beta = .10, p = .013), and when AI and clinician recommendations conflicted, parents were more likely to choose AI over clinician judgment in treatment compared to diagnosis scenarios, with healthcare professionals showing similar patterns but additionally weighting perceived disease severity.
Acceptability of AI-applications in routine clinical care for children and adolescents: perspectives of parents and healthcare professionals
This study investigated AI acceptability among parents (first cohort n = 198; second cohort n = 79) and pediatric healthcare professionals (n = 33) across different disease, diagnosis, or treatment scenarios, finding that more liberal data privacy was associated with reduced willingness to use AI (p < .001), higher perceived disease severity was linked to higher willingness to use AI in the second parent group (beta = .10, p = .013), and when AI and clinician recommendations conflicted, parents were more likely to choose AI over clinician judgment in treatment compared to diagnosis scenarios, with healthcare professionals showing similar patterns but additionally weighting perceived disease severity.
This study investigated AI acceptability among parents (first cohort n = 198; second cohort n = 79) and pediatric healthcare professionals (n = 33) across different disease, diagnosis, or treatment scenarios, finding that more liberal data privacy was associated with reduced willingness to use AI (p < .001), higher perceived disease severity was linked to higher willingness to use AI in the second parent group (beta = .10, p = .013), and when AI and clinician recommendations conflicted, parents were more likely to choose AI over clinician judgment in treatment compared to diagnosis scenarios, with healthcare professionals showing similar patterns but additionally weighting perceived disease severity.
Human gene therapy Sep 14, 2026
This Perspective article presents the InsightRP2 framework, an integrated translational strategy combining clinical data, artificial intelligence-supported imaging analysis, experimental disease modeling, and adeno-associated virus design, with the aim of facilitating development of a targeted gene therapy for RP2-associated retinitis pigmentosa.
This Perspective article presents the InsightRP2 framework, an integrated translational strategy combining clinical data, artificial intelligence-supported imaging analysis, experimental disease modeling, and adeno-associated virus design, with the aim of facilitating development of a targeted gene therapy for RP2-associated retinitis pigmentosa.
InsightRP2: An Interdisciplinary Framework for Therapy Development in RP2-Associated Retinopathy
This Perspective article presents the InsightRP2 framework, an integrated translational strategy combining clinical data, artificial intelligence-supported imaging analysis, experimental disease modeling, and adeno-associated virus design, with the aim of facilitating development of a targeted gene therapy for RP2-associated retinitis pigmentosa.
This Perspective article presents the InsightRP2 framework, an integrated translational strategy combining clinical data, artificial intelligence-supported imaging analysis, experimental disease modeling, and adeno-associated virus design, with the aim of facilitating development of a targeted gene therapy for RP2-associated retinitis pigmentosa.
发表出处待核验 Sep 14, 2026
This work builds a frozen, content-hashed data asset and a uniform scoring harness that maps seven MaveDB saturation genome editing (SGE) score sets to GRCh38, harmonises orientation and freezes them into immutable matrices, then evaluates nineteen variant effect predictors across sixteen strata using per-gene Spearman rho pooled by DerSimonian-Laird random-effects meta-analysis with per-stratum measurement-reliability estimates, attenuation correction, paired dependent-correlation tests and leave-one-gene-out validation, covering 64,178 variants and seven cancer susceptibility genes.
This work builds a frozen, content-hashed data asset and a uniform scoring harness that maps seven MaveDB saturation genome editing (SGE) score sets to GRCh38, harmonises orientation and freezes them into immutable matrices, then evaluates nineteen variant effect predictors across sixteen strata using per-gene Spearman rho pooled by DerSimonian-Laird random-effects meta-analysis with per-stratum measurement-reliability estimates, attenuation correction, paired dependent-correlation tests and leave-one-gene-out validation, covering 64,178 variants and seven cancer susceptibility genes.
functional-standard-atlas: an attenuation-corrected, territory-resolved benchmark of variant effect predictors against saturation genome editing
This work builds a frozen, content-hashed data asset and a uniform scoring harness that maps seven MaveDB saturation genome editing (SGE) score sets to GRCh38, harmonises orientation and freezes them into immutable matrices, then evaluates nineteen variant effect predictors across sixteen strata using per-gene Spearman rho pooled by DerSimonian-Laird random-effects meta-analysis with per-stratum measurement-reliability estimates, attenuation correction, paired dependent-correlation tests and leave-one-gene-out validation, covering 64,178 variants and seven cancer susceptibility genes.
This work builds a frozen, content-hashed data asset and a uniform scoring harness that maps seven MaveDB saturation genome editing (SGE) score sets to GRCh38, harmonises orientation and freezes them into immutable matrices, then evaluates nineteen variant effect predictors across sixteen strata using per-gene Spearman rho pooled by DerSimonian-Laird random-effects meta-analysis with per-stratum measurement-reliability estimates, attenuation correction, paired dependent-correlation tests and leave-one-gene-out validation, covering 64,178 variants and seven cancer susceptibility genes.
Journal of Medical Internet Research Sep 14, 2026
Using 16,447 clinical notes from 6,382 patients with mental health diagnoses in the MIMIC-IV database, this study labeled sentiment from patient, physician, and general perspectives with two large language models (DeepSeek-7B and Mistral-7B) and three lexicon-based tools (ClinSent-lexicon, TextBlob, and VADER), finding substantial directional change in sentiment trajectories among patients with multiple admissions, greater fluctuation in Discharge Instructions than in Brief Hospital Course notes, more balanced patient-perspective sentiment versus predominantly neutral physician and general perspectives, better alignment of LLMs with patient-centered annotations than lexicon-based methods, and significantly more negative discharge-note sentiment trajectories among patients who died within 3
Using 16,447 clinical notes from 6,382 patients with mental health diagnoses in the MIMIC-IV database, this study labeled sentiment from patient, physician, and general perspectives with two large language models (DeepSeek-7B and Mistral-7B) and three lexicon-based tools (ClinSent-lexicon, TextBlob, and VADER), finding substantial directional change in sentiment trajectories among patients with multiple admissions, greater fluctuation in Discharge Instructions than in Brief Hospital Course notes, more balanced patient-perspective sentiment versus predominantly neutral physician and general perspectives, better alignment of LLMs with patient-centered annotations than lexicon-based methods, and significantly more negative discharge-note sentiment trajectories among patients who died within 3
Temporal Analysis of Patient-Centered Sentiment in Clinical Notes for Patients With Mental Health Conditions: Retrospective Cohort Study
Using 16,447 clinical notes from 6,382 patients with mental health diagnoses in the MIMIC-IV database, this study labeled sentiment from patient, physician, and general perspectives with two large language models (DeepSeek-7B and Mistral-7B) and three lexicon-based tools (ClinSent-lexicon, TextBlob, and VADER), finding substantial directional change in sentiment trajectories among patients with multiple admissions, greater fluctuation in Discharge Instructions than in Brief Hospital Course notes, more balanced patient-perspective sentiment versus predominantly neutral physician and general perspectives, better alignment of LLMs with patient-centered annotations than lexicon-based methods, and significantly more negative discharge-note sentiment trajectories among patients who died within 3
Using 16,447 clinical notes from 6,382 patients with mental health diagnoses in the MIMIC-IV database, this study labeled sentiment from patient, physician, and general perspectives with two large language models (DeepSeek-7B and Mistral-7B) and three lexicon-based tools (ClinSent-lexicon, TextBlob, and VADER), finding substantial directional change in sentiment trajectories among patients with multiple admissions, greater fluctuation in Discharge Instructions than in Brief Hospital Course notes, more balanced patient-perspective sentiment versus predominantly neutral physician and general perspectives, better alignment of LLMs with patient-centered annotations than lexicon-based methods, and significantly more negative discharge-note sentiment trajectories among patients who died within 3
International Journal of Behavioral Medicine Sep 14, 2026
This cross-sectional study surveyed 427 adults on antiretroviral treatment (ART) at a large tertiary referral center in Kano, Nigeria, finding that 75.2% were aware of AI chatbots, 72.6% had ever used one, and 66.5% had used chatbots for HIV-related queries (most commonly general HIV/ART information 36.3%, checking ART side effects 23.4%, and preparing questions for clinicians 15.0%), and identified factors independently associated with HIV-related chatbot use, including younger age, post-secondary education, being married, shorter ART duration, presence of comorbidities, smartphone ownership, internet access, and English proficiency.
This cross-sectional study surveyed 427 adults on antiretroviral treatment (ART) at a large tertiary referral center in Kano, Nigeria, finding that 75.2% were aware of AI chatbots, 72.6% had ever used one, and 66.5% had used chatbots for HIV-related queries (most commonly general HIV/ART information 36.3%, checking ART side effects 23.4%, and preparing questions for clinicians 15.0%), and identified factors independently associated with HIV-related chatbot use, including younger age, post-secondary education, being married, shorter ART duration, presence of comorbidities, smartphone ownership, internet access, and English proficiency.
Feasibility of AI-Enabled Chatbots for Pre-consultation in HIV Care in Northern Nigeria
This cross-sectional study surveyed 427 adults on antiretroviral treatment (ART) at a large tertiary referral center in Kano, Nigeria, finding that 75.2% were aware of AI chatbots, 72.6% had ever used one, and 66.5% had used chatbots for HIV-related queries (most commonly general HIV/ART information 36.3%, checking ART side effects 23.4%, and preparing questions for clinicians 15.0%), and identified factors independently associated with HIV-related chatbot use, including younger age, post-secondary education, being married, shorter ART duration, presence of comorbidities, smartphone ownership, internet access, and English proficiency.
This cross-sectional study surveyed 427 adults on antiretroviral treatment (ART) at a large tertiary referral center in Kano, Nigeria, finding that 75.2% were aware of AI chatbots, 72.6% had ever used one, and 66.5% had used chatbots for HIV-related queries (most commonly general HIV/ART information 36.3%, checking ART side effects 23.4%, and preparing questions for clinicians 15.0%), and identified factors independently associated with HIV-related chatbot use, including younger age, post-secondary education, being married, shorter ART duration, presence of comorbidities, smartphone ownership, internet access, and English proficiency.

Page 42 · showing 10