Back to List View Graph View

Large language models

Large language models (LLMs) are artificial-intelligence systems trained on very large collections of text to identify statistical relationships between language units and generate or transform text in response to prompts.

Where the papers sit

49 papers from the last 6 months study large language models directly · updated from PubMed 16 Nov 2026

  • Medical AI Evaluation and Education

    Medical AI work is converging on evaluation, education, and responsible clinical integration rather than autonomous care. Studies test AI feedback, Angoff standard setting, Socratic learning, thematic coding, and patient education, alongside clinical reasoning and code mapping. Privacy-preserving local deployment, open-weight benchmarking, bias review, and human-versus-AI supervision recur as safeguards. Therapy support and prediction of neurological complications extend the scope, but effectiveness, equity, and accountability remain open.

    14 papers · 28.6%

  • Clinical Decision Support

    Clinical decision support is moving from isolated question answering toward specialty-specific triage, diagnosis, treatment recommendation, and risk prediction. Applications span hepatopancreatobiliary oncology, immunosuppression-related infection, stroke, rare-disease referrals, audiology, and postoperative complications. Genetic-trial eligibility extraction and prescription review target workflow automation, while mental-health tools address depression and suicidality. Retrospective benchmarks and protocols dominate, leaving prospective safety, calibration, and clinician oversight unresolved.

    12 papers · 24.5%

  • Healthcare AI Adoption and Evaluation

    Healthcare AI adoption is being assessed through performance testing, user attitudes, and oversight rather than accuracy alone. Dental education and professional surveys examine willingness to use LLMs and preferences for governance, while oncology nursing and cancer survivorship studies test patient-facing or decision-support answers. Clinical data-analysis agents and vibe-coding tools expose failures in statistical reasoning, and radiology adaptation targets more reliable impression generation. Domain adaptation improves fit, but monitoring, validation, and accountability remain necessary.

    8 papers · 16.3%

  • Clinical Record Intelligence

    Clinical record intelligence is moving toward structured extraction, longitudinal diagnosis, anonymization, and automated patient instructions. Time-series EHRs are used for chronic kidney disease detection, while note-based models extract infectious-disease and intestinal symptoms and identify spiritual pain. Other work tests privacy-preserving de-identification, periodontitis prevention planning, discharge communication, and morbidity-and-mortality preparation. F1, sensitivity, specificity, and accuracy dominate evaluation, but generalizability and safe workflow integration remain open.

    8 papers · 16.3%

  • Clinical LLM Reliability

    Clinical LLM evaluation is shifting from raw answer accuracy toward safety, completeness, calibration, usability, and shared decision-making. Patient education and 3D avatars emphasize clinician acceptance and communication, while reproductive counselling, endodontic planning, and strabismus-literature simplification test practical usefulness. Hepatology studies compare prognostic prediction with specialists, and confidence calibration probes whether self-reported certainty tracks correctness. Results support cautious assistance, but domain-specific omissions and overconfidence remain unresolved.

    7 papers · 14.3%

NEW DIRECTION

Large language models are proposed as participants in psychotherapy rather than merely tools for clinical support

Psychological therapy in the age of large language models treats the technology as performing therapy functions within or alongside care, including adaptive interaction and elements of therapeutic support, whereas the other papers use LLMs for assessment, decision support, education, information retrieval, simulation, or data extraction. This changes the proposed role of the model from an adjunct that helps clinicians or patients with bounded tasks to a potential component of the therapeutic process itself, while assigning therapists enduring relational, adaptive, and accountability functions 42748037Sep.

Papers

The 49 papers from the last 6 months that study large language models directly, newest first, by theme and by study type. Study types come from PubMed publication types and MeSH headings.

By theme

Medical AI Evaluation and Education (14)
  1. Artificial intelligence and clinical reasoning - a qualitative study with general practice trainees in Germany. BMC medical education · 14 Nov 2026 PMID 43034204
  2. OpenMedEval: Benchmarking 172 open-source LLMs on 326K medical questions across 93 datasets. PloS one · 13 Nov 2026 PMID 43024673
  3. Comparative Evaluation of AI Chatbots for Medical Research: Cross-Sectional Observational Study. JMIR formative research · 3 Nov 2026 PMID 42976335
  4. Clinical Code Mapping with LLM Tool Use: A Pilot for Automated Data Extraction of Medication and Diagnosis Information from Unstructured Clinical Notes. Studies in health technology and informatics · 17 Sept 2026 PMID 42752481
  5. Psychological Therapy in the Age of Large Language Models: Framework for Therapist-Delivered and AI-Supported Functions. JMIR mental health · 16 Sept 2026 PMID 42748037
  6. Promise, Mimicry, and Surveillance: Responsibly Integrating Artificial Intelligence With Socratic Inquiry in Medical Education. JMIR medical education · 10 Sept 2026 PMID 42721480
  7. Exploring Bias in Medical Applications of Large Language Models: Protocol for a Systematic Review. JMIR research protocols · 10 Sept 2026 PMID 42721473
  8. AI-Assisted Angoff Standard Setting for Multiple-Choice Examinations in Medical Education: Comparative Study. JMIR medical education · 9 Sept 2026 PMID 42715553
  9. Automating the Management of Extraspinal Findings in Magnetic Resonance Imaging Spine Studies Using a Privacy-Preserving Large Language Model: Retrospective Validation Study. Journal of medical Internet research · 26 Aug 2026 PMID 42647045
  10. Large Language Model-Assisted Thematic Coding in Medical Education Research: Comparative Methodological Study. JMIR formative research · 25 Aug 2026 PMID 42641075
  11. Local Deployment of Open-Weight Language Models in Dermatology: Viewpoint on Privacy, Equity, and Practical Implementation. JMIR dermatology · 21 Aug 2026 PMID 42627943
  12. A Multidisciplinary Team-Based Large Language Model Framework for Predicting Postoperative Neurological Complications in Acute Type A Aortic Dissection: Model Development and Validation Study. Journal of medical Internet research · 18 Aug 2026 PMID 42611794
  13. A bimodal large language model reduces misalignment in patient education: A double-blinded randomized trial. Med (New York, N.Y.) · 17 Aug 2026 PMID 42607666
  14. AI-Generated Versus Human Supervisor Feedback on Medical Students' Clinical Clerkship Logs: Cross-Sectional Convergent Mixed Methods Study. JMIR medical education · 16 Jun 2026 PMID 42302283
Clinical Decision Support (12)
  1. A Large Language Model-Based System for Depression Symptom Identification: Iterative Qualitative Co-Design Studies. JMIR formative research · 3 Nov 2026 PMID 42976350
  2. Large language models in the diagnosis and treatment of immunosuppression-related infections in rheumatic diseases: a comparative, vignette-based study. Rheumatology international · 9 Oct 2026 PMID 42853428
  3. Ensemble of Domain-Specific Natural Language Processing and Large Language Models for Detecting Suicidal Ideation and Mental Health Conditions in Social Media Text: Development and Evaluation Study. JMIR mental health · 8 Oct 2026 PMID 42849899
  4. Large Language Models in Multidisciplinary Decision-Making for Hepatopancreatobiliary Oncology: Retrospective Comparative Feasibility Study. Journal of medical Internet research · 17 Sept 2026 PMID 42753242
  5. Automated Extraction of Genetic Eligibility Criteria from Clinical Trial Records Using LLMs - A Technical Case Report. Studies in health technology and informatics · 17 Sept 2026 PMID 42752480
  6. Frameworks, Methodologies, and Tools for Evaluating Large Language Models in Digital Mental Health Interventions: Protocol for a Scoping Review. JMIR research protocols · 14 Sept 2026 PMID 42735424
  7. Locally Deployed Large Language Models for AI-Assisted Outpatient Prescription Review: Crossover Study. JMIR medical informatics · 14 Sept 2026 PMID 42735403
  8. Evaluating Large Language Models in Clinical Audiology (AUDIOLOGYBENCH): Benchmark Development and Validation Study. Journal of medical Internet research · 11 Sept 2026 PMID 42727086
  9. Large Language Models as a New Tool for Therapists in Internet-Based Cognitive Behavioral Therapy: Blinded Clinician Rating Pilot Experiment. JMIR mental health · 26 Aug 2026 PMID 42647055
  10. Nurse-Led Large Language Model Chatbot for Predicting and Preventing Complications After Coronary Artery Bypass Grafting: Protocol for a Randomized Controlled Trial. JMIR research protocols · 4 Aug 2026 PMID 42550966
  11. A Multiagent Large Language Model Framework for Emergency Treatment Recommendation in Acute Ischemic Stroke: Development and Validation Study. Journal of medical Internet research · 30 Jul 2026 PMID 42531250
  12. Initial-Visit Specialty Triage in Rare Diseases Using Large Language Models: Retrospective Benchmarking Study. Journal of medical Internet research · 23 Jul 2026 PMID 42490550
Healthcare AI Adoption and Evaluation (8)
  1. Domain Adaptation of a Large Language Model for Radiology Impression Generation - Multi-Reader Evaluation. Journal of medical systems · 27 Oct 2026 PMID 42944792
  2. Large Language Model Chatbot Responses to Cancer Survivorship Questions in Hong Kong: Bilingual Evaluation and Prompt Optimization Study. Journal of medical Internet research · 8 Oct 2026 PMID 42849027
  3. Benchmarking AI Vibe Coding for Clinical Statistical Analysis: A Structured Evaluation in Pulmonary Hypertension Research. Studies in health technology and informatics · 17 Sept 2026 PMID 42752488
  4. Attitudes Toward Large Language Models in Health Care and Preferences for Their Adoption and Oversight Among Health Care Professionals: Cross-Sectional Survey. Journal of medical Internet research · 15 Sept 2026 PMID 42742517
  5. Performance, Failures, and Oversight of a Large Language Model Agent for Clinical Data Analysis: Evaluation Study. Journal of medical Internet research · 8 Sept 2026 PMID 42709964
  6. Large language model use in dental education: a cross-sectional multi-country study. Medical education online · 6 Aug 2026 PMID 42559854
  7. Performance of Large Language Models for Oncology Nursing Decision Support: Cross-Sectional Study. Journal of medical Internet research · 24 Jul 2026 PMID 42497362
  8. Understanding Public Awareness, Attitudes, Beliefs, and Perceptions About ChatGPT in Saudi Arabia: A Road Map for Digital Health. Medical science monitor : international medical journal of experimental and clinical research · 27 Jun 2026 PMID 42363582
Clinical Record Intelligence (8)
  1. Large Language Model-Assisted Discharge Instructions for Diabetic Kidney Disease: Comparative Evaluation Study. JMIR medical informatics · 13 Nov 2026 PMID 43024853
  2. Detecting spiritual pain in electronic medical records using large language models. Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer · 29 Oct 2026 PMID 42955097
  3. (AI)lephant in the Room: Utility of Generative AI to Develop Discussion Guides for Cardiac Surgery Morbidity and Mortality Conferences. Journal of surgical education · 13 Oct 2026 PMID 42868634
  4. Periodontitis Risk Assessment and Prevention Planning: Comparative Study of Multimodal Large Language Models and Periodontist Evaluations. Journal of medical Internet research · 2 Oct 2026 PMID 42826249
  5. Leveraging time-series electronic health records with large language models for chronic kidney disease diagnosis in primary care. BMJ health & care informatics · 18 Sept 2026 PMID 42759972
  6. Anonymization of Portuguese Clinical Notes Using Large Language Models and Quantum-Enhanced Hybrid Architectures: Comparative Evaluation Study. Journal of medical Internet research · 14 Sept 2026 PMID 42735382
  7. Fine-Tuning Large Language Models for Structured Extraction of Infectious Disease-Related Information From Clinical Notes in Japanese Primary Care: Development and Internal Validation Study. JMIR formative research · 10 Sept 2026 PMID 42721099
  8. The Performance of Large Language Models in Extracting Intestinal Symptoms From Electronic Health Records: Retrospective Observational Study. Journal of medical Internet research · 26 Aug 2026 PMID 42647073
Clinical LLM Reliability (7)
  1. Large Language Model-Powered 3D Avatars to Train Shared Decision-Making in Undergraduate Medical Students: Design and Mixed Methods Acceptance Study. JMIR formative research · 27 Oct 2026 PMID 42944729
  2. A Clinician-Centered Evaluation Framework for Large Language Models in Patient Education: Integrating the Technology Acceptance Model and Medical Condition Regard Scale. JMIR formative research · 21 Sept 2026 PMID 42766478
  3. Multicenter Evaluation of Large Language Models Versus Hepatologists for Prognostic Prediction in Drug-Induced Liver Injury. Liver international : official journal of the International Association for the Study of the Liver · 18 Sept 2026 PMID 42757445
  4. Large language models show high clinical safety but differences in completeness for reproductive counselling in women with inflammatory rheumatic and musculoskeletal diseases: a comparative expert evaluation. Rheumatology international · 10 Sept 2026 PMID 42720754
  5. Large Language Model Simplification of Open Access Pediatric Strabismus Literature: Cross-Sectional Validation of Readability and Clinical Fidelity. JMIR formative research · 14 Aug 2026 PMID 42600075
  6. Large Language Models for Endodontic Symptom Assessment and Treatment Planning Using Image-Free Clinical Records: Comparative Evaluation Study. JMIR medical informatics · 24 Jul 2026 PMID 42497401
  7. Calibration of Self-Reported Confidence and Accuracy of Large Language Models in Medical Question Answering. Journal of medical systems · 26 Jun 2026 PMID 42360536

By study type

Clinical trials (2)
  1. A bimodal large language model reduces misalignment in patient education: A double-blinded randomized trial. Med (New York, N.Y.) · 17 Aug 2026 PMID 42607666
  2. Nurse-Led Large Language Model Chatbot for Predicting and Preventing Complications After Coronary Artery Bypass Grafting: Protocol for a Randomized Controlled Trial. JMIR research protocols · 4 Aug 2026 PMID 42550966
Observational studies and case reports (16)
  1. Comparative Evaluation of AI Chatbots for Medical Research: Cross-Sectional Observational Study. JMIR formative research · 3 Nov 2026 PMID 42976335
  2. Domain Adaptation of a Large Language Model for Radiology Impression Generation - Multi-Reader Evaluation. Journal of medical systems · 27 Oct 2026 PMID 42944792
  3. Large Language Model-Powered 3D Avatars to Train Shared Decision-Making in Undergraduate Medical Students: Design and Mixed Methods Acceptance Study. JMIR formative research · 27 Oct 2026 PMID 42944729
  4. Large language models in the diagnosis and treatment of immunosuppression-related infections in rheumatic diseases: a comparative, vignette-based study. Rheumatology international · 9 Oct 2026 PMID 42853428
  5. Large Language Models in Multidisciplinary Decision-Making for Hepatopancreatobiliary Oncology: Retrospective Comparative Feasibility Study. Journal of medical Internet research · 17 Sept 2026 PMID 42753242
  6. Attitudes Toward Large Language Models in Health Care and Preferences for Their Adoption and Oversight Among Health Care Professionals: Cross-Sectional Survey. Journal of medical Internet research · 15 Sept 2026 PMID 42742517
  7. The Performance of Large Language Models in Extracting Intestinal Symptoms From Electronic Health Records: Retrospective Observational Study. Journal of medical Internet research · 26 Aug 2026 PMID 42647073
  8. Automating the Management of Extraspinal Findings in Magnetic Resonance Imaging Spine Studies Using a Privacy-Preserving Large Language Model: Retrospective Validation Study. Journal of medical Internet research · 26 Aug 2026 PMID 42647045
  9. A Multidisciplinary Team-Based Large Language Model Framework for Predicting Postoperative Neurological Complications in Acute Type A Aortic Dissection: Model Development and Validation Study. Journal of medical Internet research · 18 Aug 2026 PMID 42611794
  10. Large Language Model Simplification of Open Access Pediatric Strabismus Literature: Cross-Sectional Validation of Readability and Clinical Fidelity. JMIR formative research · 14 Aug 2026 PMID 42600075
  11. Large language model use in dental education: a cross-sectional multi-country study. Medical education online · 6 Aug 2026 PMID 42559854
  12. A Multiagent Large Language Model Framework for Emergency Treatment Recommendation in Acute Ischemic Stroke: Development and Validation Study. Journal of medical Internet research · 30 Jul 2026 PMID 42531250
  13. Performance of Large Language Models for Oncology Nursing Decision Support: Cross-Sectional Study. Journal of medical Internet research · 24 Jul 2026 PMID 42497362
  14. Initial-Visit Specialty Triage in Rare Diseases Using Large Language Models: Retrospective Benchmarking Study. Journal of medical Internet research · 23 Jul 2026 PMID 42490550
  15. Understanding Public Awareness, Attitudes, Beliefs, and Perceptions About ChatGPT in Saudi Arabia: A Road Map for Digital Health. Medical science monitor : international medical journal of experimental and clinical research · 27 Jun 2026 PMID 42363582
  16. AI-Generated Versus Human Supervisor Feedback on Medical Students' Clinical Clerkship Logs: Cross-Sectional Convergent Mixed Methods Study. JMIR medical education · 16 Jun 2026 PMID 42302283
Human data, design not indexed (31)
  1. Artificial intelligence and clinical reasoning - a qualitative study with general practice trainees in Germany. BMC medical education · 14 Nov 2026 PMID 43034204
  2. Large Language Model-Assisted Discharge Instructions for Diabetic Kidney Disease: Comparative Evaluation Study. JMIR medical informatics · 13 Nov 2026 PMID 43024853
  3. OpenMedEval: Benchmarking 172 open-source LLMs on 326K medical questions across 93 datasets. PloS one · 13 Nov 2026 PMID 43024673
  4. A Large Language Model-Based System for Depression Symptom Identification: Iterative Qualitative Co-Design Studies. JMIR formative research · 3 Nov 2026 PMID 42976350
  5. Detecting spiritual pain in electronic medical records using large language models. Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer · 29 Oct 2026 PMID 42955097
  6. (AI)lephant in the Room: Utility of Generative AI to Develop Discussion Guides for Cardiac Surgery Morbidity and Mortality Conferences. Journal of surgical education · 13 Oct 2026 PMID 42868634
  7. Ensemble of Domain-Specific Natural Language Processing and Large Language Models for Detecting Suicidal Ideation and Mental Health Conditions in Social Media Text: Development and Evaluation Study. JMIR mental health · 8 Oct 2026 PMID 42849899
  8. Large Language Model Chatbot Responses to Cancer Survivorship Questions in Hong Kong: Bilingual Evaluation and Prompt Optimization Study. Journal of medical Internet research · 8 Oct 2026 PMID 42849027
  9. Periodontitis Risk Assessment and Prevention Planning: Comparative Study of Multimodal Large Language Models and Periodontist Evaluations. Journal of medical Internet research · 2 Oct 2026 PMID 42826249
  10. A Clinician-Centered Evaluation Framework for Large Language Models in Patient Education: Integrating the Technology Acceptance Model and Medical Condition Regard Scale. JMIR formative research · 21 Sept 2026 PMID 42766478
  11. Leveraging time-series electronic health records with large language models for chronic kidney disease diagnosis in primary care. BMJ health & care informatics · 18 Sept 2026 PMID 42759972
  12. Multicenter Evaluation of Large Language Models Versus Hepatologists for Prognostic Prediction in Drug-Induced Liver Injury. Liver international : official journal of the International Association for the Study of the Liver · 18 Sept 2026 PMID 42757445
  13. Benchmarking AI Vibe Coding for Clinical Statistical Analysis: A Structured Evaluation in Pulmonary Hypertension Research. Studies in health technology and informatics · 17 Sept 2026 PMID 42752488
  14. Clinical Code Mapping with LLM Tool Use: A Pilot for Automated Data Extraction of Medication and Diagnosis Information from Unstructured Clinical Notes. Studies in health technology and informatics · 17 Sept 2026 PMID 42752481
  15. Automated Extraction of Genetic Eligibility Criteria from Clinical Trial Records Using LLMs - A Technical Case Report. Studies in health technology and informatics · 17 Sept 2026 PMID 42752480
  16. Psychological Therapy in the Age of Large Language Models: Framework for Therapist-Delivered and AI-Supported Functions. JMIR mental health · 16 Sept 2026 PMID 42748037
  17. Frameworks, Methodologies, and Tools for Evaluating Large Language Models in Digital Mental Health Interventions: Protocol for a Scoping Review. JMIR research protocols · 14 Sept 2026 PMID 42735424
  18. Locally Deployed Large Language Models for AI-Assisted Outpatient Prescription Review: Crossover Study. JMIR medical informatics · 14 Sept 2026 PMID 42735403
  19. Anonymization of Portuguese Clinical Notes Using Large Language Models and Quantum-Enhanced Hybrid Architectures: Comparative Evaluation Study. Journal of medical Internet research · 14 Sept 2026 PMID 42735382
  20. Evaluating Large Language Models in Clinical Audiology (AUDIOLOGYBENCH): Benchmark Development and Validation Study. Journal of medical Internet research · 11 Sept 2026 PMID 42727086
  21. Promise, Mimicry, and Surveillance: Responsibly Integrating Artificial Intelligence With Socratic Inquiry in Medical Education. JMIR medical education · 10 Sept 2026 PMID 42721480
  22. Exploring Bias in Medical Applications of Large Language Models: Protocol for a Systematic Review. JMIR research protocols · 10 Sept 2026 PMID 42721473
  23. Fine-Tuning Large Language Models for Structured Extraction of Infectious Disease-Related Information From Clinical Notes in Japanese Primary Care: Development and Internal Validation Study. JMIR formative research · 10 Sept 2026 PMID 42721099
  24. Large language models show high clinical safety but differences in completeness for reproductive counselling in women with inflammatory rheumatic and musculoskeletal diseases: a comparative expert evaluation. Rheumatology international · 10 Sept 2026 PMID 42720754
  25. AI-Assisted Angoff Standard Setting for Multiple-Choice Examinations in Medical Education: Comparative Study. JMIR medical education · 9 Sept 2026 PMID 42715553
  26. Performance, Failures, and Oversight of a Large Language Model Agent for Clinical Data Analysis: Evaluation Study. Journal of medical Internet research · 8 Sept 2026 PMID 42709964
  27. Large Language Models as a New Tool for Therapists in Internet-Based Cognitive Behavioral Therapy: Blinded Clinician Rating Pilot Experiment. JMIR mental health · 26 Aug 2026 PMID 42647055
  28. Large Language Model-Assisted Thematic Coding in Medical Education Research: Comparative Methodological Study. JMIR formative research · 25 Aug 2026 PMID 42641075
  29. Local Deployment of Open-Weight Language Models in Dermatology: Viewpoint on Privacy, Equity, and Practical Implementation. JMIR dermatology · 21 Aug 2026 PMID 42627943
  30. Large Language Models for Endodontic Symptom Assessment and Treatment Planning Using Image-Free Clinical Records: Comparative Evaluation Study. JMIR medical informatics · 24 Jul 2026 PMID 42497401
  31. Calibration of Self-Reported Confidence and Accuracy of Large Language Models in Medical Question Answering. Journal of medical systems · 26 Jun 2026 PMID 42360536