Medicine & Health

466 items

World Journal of Methodology Sep 20, 2026
This letter to the editor responds to a study by Zhou et al published in the World Journal of Gastroenterology on the concept of artificial wisdom (AW) applied to historical medical inquiry, itself a response to an AI-human analysis of Alexander the Great's cause of death; while acknowledging the innovative integration of generative AI with clinical reasoning, the letter highlights epistemic and ethical limitations, arguing that AI systems shaped by transient data and iterative obsolescence cannot access enduring or timeless truths, that the persuasive fluency of large language models risks creating an illusion of certainty and conflating probabilistic synthesis with wisdom, and that transparency, accountability, and human moral stewardship are essential safeguards, ultimately proposing a
This letter to the editor responds to a study by Zhou et al published in the World Journal of Gastroenterology on the concept of artificial wisdom (AW) applied to historical medical inquiry, itself a response to an AI-human analysis of Alexander the Great's cause of death; while acknowledging the innovative integration of generative AI with clinical reasoning, the letter highlights epistemic and ethical limitations, arguing that AI systems shaped by transient data and iterative obsolescence cannot access enduring or timeless truths, that the persuasive fluency of large language models risks creating an illusion of certainty and conflating probabilistic synthesis with wisdom, and that transparency, accountability, and human moral stewardship are essential safeguards, ultimately proposing a
Letter to the Editor: Artificial wisdom and the transience of truth: Ethical and temporal reflections on artificial intelligence-human inquiry into history.
This letter to the editor responds to a study by Zhou et al published in the World Journal of Gastroenterology on the concept of artificial wisdom (AW) applied to historical medical inquiry, itself a response to an AI-human analysis of Alexander the Great's cause of death; while acknowledging the innovative integration of generative AI with clinical reasoning, the letter highlights epistemic and ethical limitations, arguing that AI systems shaped by transient data and iterative obsolescence cannot access enduring or timeless truths, that the persuasive fluency of large language models risks creating an illusion of certainty and conflating probabilistic synthesis with wisdom, and that transparency, accountability, and human moral stewardship are essential safeguards, ultimately proposing a
This letter to the editor responds to a study by Zhou et al published in the World Journal of Gastroenterology on the concept of artificial wisdom (AW) applied to historical medical inquiry, itself a response to an AI-human analysis of Alexander the Great's cause of death; while acknowledging the innovative integration of generative AI with clinical reasoning, the letter highlights epistemic and ethical limitations, arguing that AI systems shaped by transient data and iterative obsolescence cannot access enduring or timeless truths, that the persuasive fluency of large language models risks creating an illusion of certainty and conflating probabilistic synthesis with wisdom, and that transparency, accountability, and human moral stewardship are essential safeguards, ultimately proposing a
World Journal of Methodology Sep 20, 2026
This opinion review argues that the current academic promotion system in surgery disproportionately favors quantifiable metrics such as publications and grant funding over the demonstration of clinical skill, creating a fundamental "credentialing paradox"; that AI tools, by streamlining research tasks, amplify this publication-centric culture and widen the disconnect between a surgeon's academic rank and their proficiency in the operating room, placing less-funded faculty and those who dedicate time to clinical care and education at a disadvantage; and that the profession should redefine academic success through a more holistic framework that formally recognizes and rewards excellence in clinical care, education, and mentorship alongside research output.
This opinion review argues that the current academic promotion system in surgery disproportionately favors quantifiable metrics such as publications and grant funding over the demonstration of clinical skill, creating a fundamental "credentialing paradox"; that AI tools, by streamlining research tasks, amplify this publication-centric culture and widen the disconnect between a surgeon's academic rank and their proficiency in the operating room, placing less-funded faculty and those who dedicate time to clinical care and education at a disadvantage; and that the profession should redefine academic success through a more holistic framework that formally recognizes and rewards excellence in clinical care, education, and mentorship alongside research output.
Surgical paradox: Pen vs scalpel—an opinion review on reforming academic promotion
This opinion review argues that the current academic promotion system in surgery disproportionately favors quantifiable metrics such as publications and grant funding over the demonstration of clinical skill, creating a fundamental "credentialing paradox"; that AI tools, by streamlining research tasks, amplify this publication-centric culture and widen the disconnect between a surgeon's academic rank and their proficiency in the operating room, placing less-funded faculty and those who dedicate time to clinical care and education at a disadvantage; and that the profession should redefine academic success through a more holistic framework that formally recognizes and rewards excellence in clinical care, education, and mentorship alongside research output.
This opinion review argues that the current academic promotion system in surgery disproportionately favors quantifiable metrics such as publications and grant funding over the demonstration of clinical skill, creating a fundamental "credentialing paradox"; that AI tools, by streamlining research tasks, amplify this publication-centric culture and widen the disconnect between a surgeon's academic rank and their proficiency in the operating room, placing less-funded faculty and those who dedicate time to clinical care and education at a disadvantage; and that the profession should redefine academic success through a more holistic framework that formally recognizes and rewards excellence in clinical care, education, and mentorship alongside research output.
medRxiv Sep 20, 2026
Using 2,704 colorectal cancer discharge notes from MIMIC-IV and a 46-symptom inventory derived from the MSAS and EORTC QLQ-CR29, this study benchmarked dictionary-based rule matching, pretrained clinical NER, zero-shot Claude Haiku and Gemini 3.5 Flash, and two hybrid variants (LLM output plus post-hoc rule-based negation filtering) against a 200-note two-rater adjudicated gold standard, finding that Gemini 3.5 Flash performed best (Macro F1=0.70, Micro F1=0.86, Macro Precision=0.74), followed by Claude Haiku (Macro F1=0.63, Macro Recall=0.71), both substantially outperforming rule-based (Macro F1=0.44) and NER (Macro F1=0.38) methods, while post-hoc negation filtering paradoxically degraded LLM performance (Gemini+Hybrid Macro F1=0.58; Claude+Hybrid Macro F1=0.54).
Using 2,704 colorectal cancer discharge notes from MIMIC-IV and a 46-symptom inventory derived from the MSAS and EORTC QLQ-CR29, this study benchmarked dictionary-based rule matching, pretrained clinical NER, zero-shot Claude Haiku and Gemini 3.5 Flash, and two hybrid variants (LLM output plus post-hoc rule-based negation filtering) against a 200-note two-rater adjudicated gold standard, finding that Gemini 3.5 Flash performed best (Macro F1=0.70, Micro F1=0.86, Macro Precision=0.74), followed by Claude Haiku (Macro F1=0.63, Macro Recall=0.71), both substantially outperforming rule-based (Macro F1=0.44) and NER (Macro F1=0.38) methods, while post-hoc negation filtering paradoxically degraded LLM performance (Gemini+Hybrid Macro F1=0.58; Claude+Hybrid Macro F1=0.54).
Leveraging Large Language Models for Colorectal Cancer Symptom Extraction from MIMIC-IV Clinical Notes
Using 2,704 colorectal cancer discharge notes from MIMIC-IV and a 46-symptom inventory derived from the MSAS and EORTC QLQ-CR29, this study benchmarked dictionary-based rule matching, pretrained clinical NER, zero-shot Claude Haiku and Gemini 3.5 Flash, and two hybrid variants (LLM output plus post-hoc rule-based negation filtering) against a 200-note two-rater adjudicated gold standard, finding that Gemini 3.5 Flash performed best (Macro F1=0.70, Micro F1=0.86, Macro Precision=0.74), followed by Claude Haiku (Macro F1=0.63, Macro Recall=0.71), both substantially outperforming rule-based (Macro F1=0.44) and NER (Macro F1=0.38) methods, while post-hoc negation filtering paradoxically degraded LLM performance (Gemini+Hybrid Macro F1=0.58; Claude+Hybrid Macro F1=0.54).
Using 2,704 colorectal cancer discharge notes from MIMIC-IV and a 46-symptom inventory derived from the MSAS and EORTC QLQ-CR29, this study benchmarked dictionary-based rule matching, pretrained clinical NER, zero-shot Claude Haiku and Gemini 3.5 Flash, and two hybrid variants (LLM output plus post-hoc rule-based negation filtering) against a 200-note two-rater adjudicated gold standard, finding that Gemini 3.5 Flash performed best (Macro F1=0.70, Micro F1=0.86, Macro Precision=0.74), followed by Claude Haiku (Macro F1=0.63, Macro Recall=0.71), both substantially outperforming rule-based (Macro F1=0.44) and NER (Macro F1=0.38) methods, while post-hoc negation filtering paradoxically degraded LLM performance (Gemini+Hybrid Macro F1=0.58; Claude+Hybrid Macro F1=0.54).
Medinformatics Sep 20, 2026
This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.
This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.
Generative AI for Drug Discovery: GPT-2 and LSTM Models for Designing EGFR Inhibitors
This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.
This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.
medRxiv Sep 20, 2026
This work builds MyoSTAT.AI, a deterministic and fully reproducible benchmarking framework for cardiac ultrasound segmentation and shear-wave elastography (SWE) velocity-field stabilization evaluated entirely on synthetic data, comparing four U-Net-based architectures (2D, 2.5D, 3D, ConvLSTM) through single-variable ablation and six stabilization methods, and reports that the ConvLSTM variant achieved the highest segmentation accuracy (Dice 0.994, IoU 0.987, an 18.6 percentage-point gain over the 2D baseline Dice 0.808), that UNet2.5D with a 3-frame temporal window reached Dice 0.983 at lower latency (433 ms vs. 1193 ms), that TensorRT FP16 deployment sustained 341 FPS on an RTX 3060 and 90.
This work builds MyoSTAT.AI, a deterministic and fully reproducible benchmarking framework for cardiac ultrasound segmentation and shear-wave elastography (SWE) velocity-field stabilization evaluated entirely on synthetic data, comparing four U-Net-based architectures (2D, 2.5D, 3D, ConvLSTM) through single-variable ablation and six stabilization methods, and reports that the ConvLSTM variant achieved the highest segmentation accuracy (Dice 0.994, IoU 0.987, an 18.6 percentage-point gain over the 2D baseline Dice 0.808), that UNet2.5D with a 3-frame temporal window reached Dice 0.983 at lower latency (433 ms vs. 1193 ms), that TensorRT FP16 deployment sustained 341 FPS on an RTX 3060 and 90.
MyoSTAT.AI: An AI-Driven Toolkit for Reproducible Benchmarking of Temporal Segmentation and Shear-Wave Velocity Stabilization on Synthetic Data
This work builds MyoSTAT.AI, a deterministic and fully reproducible benchmarking framework for cardiac ultrasound segmentation and shear-wave elastography (SWE) velocity-field stabilization evaluated entirely on synthetic data, comparing four U-Net-based architectures (2D, 2.5D, 3D, ConvLSTM) through single-variable ablation and six stabilization methods, and reports that the ConvLSTM variant achieved the highest segmentation accuracy (Dice 0.994, IoU 0.987, an 18.6 percentage-point gain over the 2D baseline Dice 0.808), that UNet2.5D with a 3-frame temporal window reached Dice 0.983 at lower latency (433 ms vs. 1193 ms), that TensorRT FP16 deployment sustained 341 FPS on an RTX 3060 and 90.
This work builds MyoSTAT.AI, a deterministic and fully reproducible benchmarking framework for cardiac ultrasound segmentation and shear-wave elastography (SWE) velocity-field stabilization evaluated entirely on synthetic data, comparing four U-Net-based architectures (2D, 2.5D, 3D, ConvLSTM) through single-variable ablation and six stabilization methods, and reports that the ConvLSTM variant achieved the highest segmentation accuracy (Dice 0.994, IoU 0.987, an 18.6 percentage-point gain over the 2D baseline Dice 0.808), that UNet2.5D with a 3-frame temporal window reached Dice 0.983 at lower latency (433 ms vs. 1193 ms), that TensorRT FP16 deployment sustained 341 FPS on an RTX 3060 and 90.
World Journal of Methodology Sep 20, 2026
This paper assesses why high-performing artificial intelligence systems for ocular image processing seldom translate into improved patient outcomes, locating the central problem in the disparity between pixel-level performance metrics and their clinical significance, naming data bias, domain shift, and label noise alongside the lack of prospective randomized deployment trials as primary obstacles, and outlining a path through stringent external validation, established decision criteria, ongoing surveillance in real clinical practice, transparent reporting standards, and deliberate human-factors engineering, with the goal of converting algorithmic accuracy into meaningful diagnostic precision for glaucoma, diabetic retinopathy, and macular conditions (specifically diabetic macular edema and
This paper assesses why high-performing artificial intelligence systems for ocular image processing seldom translate into improved patient outcomes, locating the central problem in the disparity between pixel-level performance metrics and their clinical significance, naming data bias, domain shift, and label noise alongside the lack of prospective randomized deployment trials as primary obstacles, and outlining a path through stringent external validation, established decision criteria, ongoing surveillance in real clinical practice, transparent reporting standards, and deliberate human-factors engineering, with the goal of converting algorithmic accuracy into meaningful diagnostic precision for glaucoma, diabetic retinopathy, and macular conditions (specifically diabetic macular edema and
Artificial Intelligence in Ophthalmology: From Diagnostic Accuracy to Clinical Application
This paper assesses why high-performing artificial intelligence systems for ocular image processing seldom translate into improved patient outcomes, locating the central problem in the disparity between pixel-level performance metrics and their clinical significance, naming data bias, domain shift, and label noise alongside the lack of prospective randomized deployment trials as primary obstacles, and outlining a path through stringent external validation, established decision criteria, ongoing surveillance in real clinical practice, transparent reporting standards, and deliberate human-factors engineering, with the goal of converting algorithmic accuracy into meaningful diagnostic precision for glaucoma, diabetic retinopathy, and macular conditions (specifically diabetic macular edema and
This paper assesses why high-performing artificial intelligence systems for ocular image processing seldom translate into improved patient outcomes, locating the central problem in the disparity between pixel-level performance metrics and their clinical significance, naming data bias, domain shift, and label noise alongside the lack of prospective randomized deployment trials as primary obstacles, and outlining a path through stringent external validation, established decision criteria, ongoing surveillance in real clinical practice, transparent reporting standards, and deliberate human-factors engineering, with the goal of converting algorithmic accuracy into meaningful diagnostic precision for glaucoma, diabetic retinopathy, and macular conditions (specifically diabetic macular edema and
World Journal of Methodology Sep 20, 2026
This review outlines current applications of artificial intelligence across the perioperative cancer pathway in onco-anaesthesia: preoperatively, machine learning and deep learning models enhance risk stratification through automated frailty assessment, electronic health record phenotyping, and prediction of cancer-specific outcomes; intraoperatively, AI-enabled technologies such as closed-loop anaesthesia delivery systems, predictive haemodynamic monitoring, and automated depth-of-anaesthesia control optimize drug dosing, reduce physiological stress, and may help preserve perioperative immune function; postoperatively, AI-driven integration of multimodal data including genomics, radiomics, wearable biosignals, and high-resolution physiological waveforms facilitates early detection of comp
This review outlines current applications of artificial intelligence across the perioperative cancer pathway in onco-anaesthesia: preoperatively, machine learning and deep learning models enhance risk stratification through automated frailty assessment, electronic health record phenotyping, and prediction of cancer-specific outcomes; intraoperatively, AI-enabled technologies such as closed-loop anaesthesia delivery systems, predictive haemodynamic monitoring, and automated depth-of-anaesthesia control optimize drug dosing, reduce physiological stress, and may help preserve perioperative immune function; postoperatively, AI-driven integration of multimodal data including genomics, radiomics, wearable biosignals, and high-resolution physiological waveforms facilitates early detection of comp
Artificial intelligence in onco-anaesthesia: current applications, challenges, and future directions
This review outlines current applications of artificial intelligence across the perioperative cancer pathway in onco-anaesthesia: preoperatively, machine learning and deep learning models enhance risk stratification through automated frailty assessment, electronic health record phenotyping, and prediction of cancer-specific outcomes; intraoperatively, AI-enabled technologies such as closed-loop anaesthesia delivery systems, predictive haemodynamic monitoring, and automated depth-of-anaesthesia control optimize drug dosing, reduce physiological stress, and may help preserve perioperative immune function; postoperatively, AI-driven integration of multimodal data including genomics, radiomics, wearable biosignals, and high-resolution physiological waveforms facilitates early detection of comp
This review outlines current applications of artificial intelligence across the perioperative cancer pathway in onco-anaesthesia: preoperatively, machine learning and deep learning models enhance risk stratification through automated frailty assessment, electronic health record phenotyping, and prediction of cancer-specific outcomes; intraoperatively, AI-enabled technologies such as closed-loop anaesthesia delivery systems, predictive haemodynamic monitoring, and automated depth-of-anaesthesia control optimize drug dosing, reduce physiological stress, and may help preserve perioperative immune function; postoperatively, AI-driven integration of multimodal data including genomics, radiomics, wearable biosignals, and high-resolution physiological waveforms facilitates early detection of comp
MedScience Sep 19, 2026
This article systematically reviews the clinical progress and prospects of neoantigen cancer vaccines for gastrointestinal tumors, noting that these vaccines, owing to their high specificity and strong immunogenicity, can effectively activate specific T-cell immunity and produce synergistic effects when combined with immune checkpoint inhibitors; various vaccine platforms offer distinct advantages, and clinical trials have shown encouraging potential in inducing immune responses and extending progression-free survival, while key challenges involve the accuracy of neoantigen prediction, tumor heterogeneity, and optimal treatment timing, and future directions include AI-assisted multi-omics screening, development of universal vaccines, optimization of novel delivery systems, and multimodal c
This article systematically reviews the clinical progress and prospects of neoantigen cancer vaccines for gastrointestinal tumors, noting that these vaccines, owing to their high specificity and strong immunogenicity, can effectively activate specific T-cell immunity and produce synergistic effects when combined with immune checkpoint inhibitors; various vaccine platforms offer distinct advantages, and clinical trials have shown encouraging potential in inducing immune responses and extending progression-free survival, while key challenges involve the accuracy of neoantigen prediction, tumor heterogeneity, and optimal treatment timing, and future directions include AI-assisted multi-omics screening, development of universal vaccines, optimization of novel delivery systems, and multimodal c
Neoantigen Cancer Vaccines for Gastrointestinal Tumors: Opportunities and Challenges
This article systematically reviews the clinical progress and prospects of neoantigen cancer vaccines for gastrointestinal tumors, noting that these vaccines, owing to their high specificity and strong immunogenicity, can effectively activate specific T-cell immunity and produce synergistic effects when combined with immune checkpoint inhibitors; various vaccine platforms offer distinct advantages, and clinical trials have shown encouraging potential in inducing immune responses and extending progression-free survival, while key challenges involve the accuracy of neoantigen prediction, tumor heterogeneity, and optimal treatment timing, and future directions include AI-assisted multi-omics screening, development of universal vaccines, optimization of novel delivery systems, and multimodal c
This article systematically reviews the clinical progress and prospects of neoantigen cancer vaccines for gastrointestinal tumors, noting that these vaccines, owing to their high specificity and strong immunogenicity, can effectively activate specific T-cell immunity and produce synergistic effects when combined with immune checkpoint inhibitors; various vaccine platforms offer distinct advantages, and clinical trials have shown encouraging potential in inducing immune responses and extending progression-free survival, while key challenges involve the accuracy of neoantigen prediction, tumor heterogeneity, and optimal treatment timing, and future directions include AI-assisted multi-omics screening, development of universal vaccines, optimization of novel delivery systems, and multimodal c
medRxiv Sep 19, 2026
This study introduces GenEHR, an autoregressive generative model trained on electronic health records from millions of patients that explicitly represents irregular inter-visit time intervals via RAdix Time Encoding and combines parameter-efficient gated low-rank adaptation for supervised fine-tuning, improving prediction of a first cancer diagnosis within a five-year horizon across five large EHR cohorts and supporting risk-based screening for aggressive cancers such as pancreatic and ovarian cancer.
This study introduces GenEHR, an autoregressive generative model trained on electronic health records from millions of patients that explicitly represents irregular inter-visit time intervals via RAdix Time Encoding and combines parameter-efficient gated low-rank adaptation for supervised fine-tuning, improving prediction of a first cancer diagnosis within a five-year horizon across five large EHR cohorts and supporting risk-based screening for aggressive cancers such as pancreatic and ovarian cancer.
Identifying cohorts at elevated risk of cancers using generative modeling of patient health states
This study introduces GenEHR, an autoregressive generative model trained on electronic health records from millions of patients that explicitly represents irregular inter-visit time intervals via RAdix Time Encoding and combines parameter-efficient gated low-rank adaptation for supervised fine-tuning, improving prediction of a first cancer diagnosis within a five-year horizon across five large EHR cohorts and supporting risk-based screening for aggressive cancers such as pancreatic and ovarian cancer.
This study introduces GenEHR, an autoregressive generative model trained on electronic health records from millions of patients that explicitly represents irregular inter-visit time intervals via RAdix Time Encoding and combines parameter-efficient gated low-rank adaptation for supervised fine-tuning, improving prediction of a first cancer diagnosis within a five-year horizon across five large EHR cohorts and supporting risk-based screening for aggressive cancers such as pancreatic and ovarian cancer.
Journal of the American Heart Association Sep 18, 2026
This retrospective, single-center external validation study enrolled 100 consecutive patients undergoing clinically indicated OCT and used the previously developed OCT-AID algorithm to perform automated pixelwise full-vessel labeling of 2560 analyzable frames, comparing it frame by frame against an expert manual reference standard; agreement was excellent for calcified plaque identification (κ=0.88) and quantification (intraclass correlation coefficients 0.79–0.93), close to interobserver variability, reasonable for lipid plaque identification and quantification (κ=0.68; lipid arc intraclass correlation coefficient 0.79; minimum fibrous cap thickness intraclass correlation coefficient 0.
This retrospective, single-center external validation study enrolled 100 consecutive patients undergoing clinically indicated OCT and used the previously developed OCT-AID algorithm to perform automated pixelwise full-vessel labeling of 2560 analyzable frames, comparing it frame by frame against an expert manual reference standard; agreement was excellent for calcified plaque identification (κ=0.88) and quantification (intraclass correlation coefficients 0.79–0.93), close to interobserver variability, reasonable for lipid plaque identification and quantification (κ=0.68; lipid arc intraclass correlation coefficient 0.79; minimum fibrous cap thickness intraclass correlation coefficient 0.
Real-World External Validation of Artificial Intelligence-Based Full-Vessel Segmentation for Intracoronary Optical Coherence Tomography
This retrospective, single-center external validation study enrolled 100 consecutive patients undergoing clinically indicated OCT and used the previously developed OCT-AID algorithm to perform automated pixelwise full-vessel labeling of 2560 analyzable frames, comparing it frame by frame against an expert manual reference standard; agreement was excellent for calcified plaque identification (κ=0.88) and quantification (intraclass correlation coefficients 0.79–0.93), close to interobserver variability, reasonable for lipid plaque identification and quantification (κ=0.68; lipid arc intraclass correlation coefficient 0.79; minimum fibrous cap thickness intraclass correlation coefficient 0.
This retrospective, single-center external validation study enrolled 100 consecutive patients undergoing clinically indicated OCT and used the previously developed OCT-AID algorithm to perform automated pixelwise full-vessel labeling of 2560 analyzable frames, comparing it frame by frame against an expert manual reference standard; agreement was excellent for calcified plaque identification (κ=0.88) and quantification (intraclass correlation coefficients 0.79–0.93), close to interobserver variability, reasonable for lipid plaque identification and quantification (κ=0.68; lipid arc intraclass correlation coefficient 0.79; minimum fibrous cap thickness intraclass correlation coefficient 0.

Page 25 · showing 10