Medical LLMs

LLM: Large Language Model

Follow this topic Ask about this topic

Medical large language models are studied for tasks such as diagnosis, clinical coding, note summarization, triage, and patient communication. Common approaches include clinical pretraining and fine-tuning, retrieval-augmented generation with guidelines or knowledge graphs, tool-using agents, and multimodal models that combine text with images or structured records. Evaluation ranges from question-answering benchmarks to realistic consultations, EHR workflows, and clinician studies, with growing attention to calibration, privacy, bias, and evidence grounding. A central challenge is that strong scores on fixed tests do not ensure reliable behavior with incomplete or changing information, misleading patient input, or high-stakes decisions, so human oversight and real-world validation remain important.

Latest papers

402 papers40 papers in the last four weeks, up 29% on the four weeks before. 0.2% of all new papers.

Mar 23, 2026

Multi-Method Validation of Large Language Model Medical Translation Across High- and Low-Resource Languages

Language barriers affect 27.3 million U.S. residents with non-English language preference, yet professional medical translation remains costly and often unavailable. We evaluated four frontier large language models (GPT-5.1, Claude Opus 4.5, Gemini 3 Pro, Kimi K2) translating 22 medical documents into 8 languages spanning high-resource (Spanish, Chinese, Russian, Vietnamese), medium-resource (Korean, Arabic), and low-resource (Tagalog, Haitian Creole) categories using a five-layer validation framework. Across 704 translation pairs, all models achieved high semantic preservation (LaBSE greater than 0.92), with no significant difference between high- and low-resource languages (p = 0.066). Cross-model back-translation confirmed results were not driven by same-model circularity (delta = -0.0009). Inter-model concordance across four independently trained models was high (LaBSE: 0.946), and lexical borrowing analysis showed no correlation between English term retention and fidelity scores in low-resource languages (rho = +0.018, p = 0.82). These converging results suggest frontier LLMs preserve medical meaning across resource levels, with implications for language access in healthcare.

Chukwuebuka Anyaegbuna, Eduardo Juan Perez Guerrero, Jerry Liu +6

Machine Translation Multilingual Language Model Evaluation Medical LLMs Low-Resource MT MT Evaluation

Mar 23, 2026

Multimodal Survival Analysis with Locally Deployable Large Language Models

We study multimodal survival analysis integrating clinical text, tabular covariates, and genomic profiles using locally deployable large language models (LLMs). As many institutions face tight computational and privacy constraints, this setting motivates the use of lightweight, on-premises models. Our approach jointly estimates calibrated survival probabilities and generates concise, evidence-grounded prognosis text via teacher-student distillation and principled multimodal fusion. On a TCGA cohort, it outperforms standard baselines, avoids reliance on cloud services and associated privacy concerns, and reduces the risk of hallucinated or miscalibrated estimates that can be observed in base LLMs.

Moritz Gögl, Christopher Yau

University of Oxford

Multimodal Survival Analysis Cancer Survival Prediction Medical LLMs

Mar 21, 2026

Can Large Language Models Reliably Extract Physiology Index Values from Coronary Angiography Reports?

Coronary angiography (CAG) reports contain clinically relevant physiological measurements, yet this information is typically in the form of unstructured natural language, limiting its use in research. We investigate the use of Large Language Models (LLMs) to automatically extract these values, along with their anatomical locations, from Portuguese CAG reports. To our knowledge, this study is the first addressing physiology indexes extraction from a large (1342 reports) corpus of CAG reports, and one of the few focusing on CAG or Portuguese clinical text. We explore local privacy-preserving general-purpose and medical LLMs under different settings. Prompting strategies included zero-shot, few-shot, and few-shot prompting with implausible examples. In addition, we apply constrained generation and introduce a post-processing step based on RegEx. Given the sparsity of measurements, we propose a multi-stage evaluation framework separating format validity, value detection, and value correctness, while accounting for asymmetric clinical error costs. This study demonstrates the potential of LLMs in for extracting physiological indices from Portuguese CAG reports. Non-medical models performed similarly, the best results were obtained with Llama with a zero-shot prompting, while GPT-OSS demonstrated the highest robustness to changes in the prompts. While MedGemma demonstrated similar results to non-medical models, MedLlama's results were out-of-format in the unconstrained setting, and had a significant lower performance in the constrained one. Changes in the prompt techinique and adding a RegEx layer showed no significant improvement across models, while using constrained generation decreased performance, although having the benefit of allowing the usage of specific models that are not able to conform with the templates.

Sofia Morgado, Filipa Valdeira, Niklas Sander +4

Sofia Morgado is with the Computer Science Department at Nova School of Science and Technology, Universidade NOVA de Lisboa, Caparica, Portugal (FCT-UNL) · Filipa Valdeira is with Center for Computational and Stochastic Mathematics - Department of Mathematics at Instituto Superior Técnico · Niklas Sander is with the Department of Computer Science at FCT-UNL +4

Clinical Information Extraction LLM Information Extraction Medical LLMs Coronary Angiography

Mar 20, 2026

Evaluating Large Language Models on Historical Health Crisis Knowledge in Resource-Limited Settings: A Hybrid Multi-Metric Study

Large Language Models (LLMs) offer significant potential for delivering health information. However, their reliability in low-resource contexts remains uncertain. This study evaluates GPT-4, Gemini Pro, Llama~3, and Mistral-7B on health crisis-related enquiries concerning COVID-19, dengue, the Nipah virus, and Chikungunya in the low-resource context of Bangladesh. We constructed a question--answer dataset from authoritative sources and assessed model outputs through semantic similarity, expert-model cross-evaluation, and Natural Language Inference (NLI). Findings highlight both the strengths and limitations of LLMs in representing epidemiological history and health crisis knowledge, underscoring their promise and risks for informing policy in resource-constrained environments.

Mohammed Rakibul Hasan

Department of Electrical & Computer Engineering, North South University, Dhaka, Bangladesh

LLM Reliability LLM Evaluation Medical LLMs Factual Knowledge in Language Models

Mar 18, 2026

The Validity Gap in Health AI Evaluation: A Cross-Sectional Analysis of Benchmark Composition

Background: Clinical trials rely on transparent inclusion criteria to ensure generalizability. In contrast, benchmarks validating health-related large language models (LLMs) rarely characterize the "patient" or "query" populations they contain. Without defined composition, aggregate performance metrics may misrepresent model readiness for clinical use. Methods: We analyzed 18,707 consumer health queries across six public benchmarks using LLMs as automated coding instruments to apply a standardized 16-field taxonomy profiling context, topic, and intent. Results: We identified a structural "validity gap." While benchmarks have evolved from static retrieval to interactive dialogue, clinical composition remains misaligned with real-world needs. Although 42% of the corpus referenced objective data, this was polarized toward wellness-focused wearable signals (17.7%); complex diagnostic inputs remained rare, including laboratory values (5.2%), imaging (3.8%), and raw medical records (0.6%). Safety-critical scenarios were effectively absent: suicide/self-harm queries comprised <0.7% of the corpus and chronic disease management only 5.5%. Benchmarks also neglected vulnerable populations (pediatrics/older adults <11%) and global health needs. Conclusions: Evaluation benchmarks remain misaligned with real-world clinical needs, lacking raw clinical artifacts, adequate representation of vulnerable populations, and longitudinal chronic care scenarios. The field must adopt standardized query profiling--analogous to clinical trial reporting--to align evaluation with the full complexity of clinical practice.

Alvin Rajkomar, Pavan Sudarshan, Angela Lai +1

Apple

Benchmark Validity Clinical Language Model Evaluation Medical LLMs

Mar 18, 2026

Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients

Surgical co-management (SCM) is an evidence-based model in which hospitalists jointly manage medically complex perioperative patients alongside surgical teams. Despite its clinical and financial value, SCM is limited by the need to manually identify eligible patients. To determine whether SCM triage can be automated, we conducted a prospective, unblinded study at Stanford Health Care in which an LLM-based, electronic health record (EHR)-integrated triage tool (SCM Navigator) provided SCM recommendations followed by physician review. Using pre-operative documentation, structured data, and clinical criteria for perioperative morbidity, SCM Navigator categorized patients as appropriate, not appropriate, or possibly appropriate for SCM. Faculty indicated their clinical judgment and provided free-text feedback when they disagreed. Sensitivity, specificity, positive predictive value, and negative predictive value were measured using physician determinations as a reference. Free-text reasons were thematically categorized, and manual chart review was conducted on all false-negative cases and 30 randomly selected cases from the largest false-positive category. Since deployment, 6,193 cases have been triaged, of which 1,582 (23%) were recommended for hospitalist consultation. SCM Navigator displayed high sensitivity (0.94, 95% CI 0.91-0.96) and moderate specificity (0.74, 95% CI 0.71-0.77). Post-hoc chart review suggested most discrepancies reflect modifiable gaps in clinical criteria, institutional workflow, or physician practice variability rather than LLM misclassification, which accounted for 2 of 19 (11%) false-negative cases. These findings demonstrate that an LLM-powered, EHR-integrated, human-in-the-loop AI system can accurately and safely triage surgical patients for SCM, and that AI-enabled screening tools can augment and potentially automate time-intensive clinical workflows.

Jane Wang, Timothy Keyes, April S Liang +10

Division of Hospital Medicine, Department of Medicine, Stanford University, Palo Alto, CA · Stanford University School of Medicine, Palo Alto, CA · Stanford Health Care, Technology and Digital Solutions, Palo Alto, CA +2

Clinical Triage Clinical Decision Support Medical LLMs Human-in-the-Loop AI

Mar 16, 2026

SynDocDis: A Metadata-Driven Framework for Generating Synthetic Physician Discussions Using Large Language Models

Physician-physician discussions of patient cases represent a rich source of clinical knowledge and reasoning that could feed AI agents to enrich and even participate in subsequent interactions. However, privacy regulations and ethical considerations severely restrict access to such data. While synthetic data generation using Large Language Models offers a promising alternative, existing approaches primarily focus on patient-physician interactions or structured medical records, leaving a significant gap in physician-to-physician communication synthesis. We present SynDocDis, a novel framework that combines structured prompting techniques with privacy-preserving de-identified case metadata to generate clinically accurate physician-to-physician dialogues. Evaluation by five practicing physicians in nine oncology and hepatology scenarios demonstrated exceptional communication effectiveness (mean 4.4/5) and strong medical content quality (mean 4.1/5), with substantial interrater reliability (kappa = 0.70, 95% CI: 0.67-0.73). The framework achieved 91% clinical relevance ratings while maintaining doctors' and patients' privacy. These results place SynDocDis as a promising framework for advancing medical AI research ethically and responsibly through privacy-compliant synthetic physician dialogue generation with direct applications in medical education and clinical decision support.

Beny Rubinstein, Sergio Matos

University of Aveiro, Portugal · IEETA, DETI, LASI, University of Aveiro, Portugal

Synthetic Data Generation Synthetic Data Generation for Language Models Medical LLMs

Mar 16, 2026

From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding

Medical coding, which assigns standardized ICD codes to clinical documents, is a fundamental yet challenging task in modern healthcare. It requires extensive knowledge of a large code space and the ability to identify and interpret sparse supporting evidence in long, noisy clinical documents. Most existing methods rely on document-level supervision, which provides limited guidance on supporting evidence and insufficient training signals for rare codes. To address these limitations, we propose Span-Centric Learning (SCL), which separates coding knowledge acquisition from its application in full documents. SCL first learns coding knowledge from short spans, then learns to use this knowledge in full documents from a small set of annotated data. Experiments show that, our approach enables an 8B LLM to surpass state-of-the-art methods using only 248 complete documents for training. It also provides explicit supporting evidence for each predicted code, with strong alignment to human annotations. Further analysis shows that the model can learn knowledge of codes absent from documents through spans and apply that knowledge to full documents.

Xu Zhang, Wenxin Ma, Chenxu Wu +5

School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC · MIRACLE Center, Suzhou Institute for Advance Research, USTC · iFlyHealth +2

Automated Medical Coding Medical LLMs Clinical Information Extraction

Mar 15, 2026

MedPriv-Bench: Benchmarking the Privacy-Utility Trade-off of Large Language Models in Medical Open-Ended Question Answering

Recent advances in Retrieval-Augmented Generation enable LLMs to ground outputs in clinical evidence, but connections to external databases create the risk of contextual leakage, where unique combinations of medical details enable patient re-identification without explicit identifiers. Existing healthcare benchmarks emphasize accuracy while overlooking this risk. To fill this gap, we present MedPriv-Bench, the first benchmark for jointly evaluating privacy preservation and clinical utility in medical open-ended question answering. Our framework utilizes a multi-agent, human-in-the-loop pipeline to synthesize sensitive medical contexts and clinically relevant queries that create realistic privacy pressure. We also establish an automated evaluation protocol using a fine-tuned RoBERTa-NLI model, which achieved an instance-level F1 score of 75.3%, sensitivity of 90.7%, and an average inference time of 0.056 s per sample against human annotations. Across nine LLMs and three privacy-preserving methods, we observed a pervasive privacy-utility trade-off. Relative to unprotected Med42-v2-8B (utility 3.87/5; leakage 72.8%), supervised fine-tuning improved utility to 4.25 and reduced leakage to 38.9%, whereas local differential privacy reduced leakage to 20.5% but lowered utility to 3.03. These results demonstrate the need for domain-specific benchmarks to validate medical AI systems in privacy-sensitive settings.

Shaowei Guan, Yu Zhai, Hin Chi Kwok +5

Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University · Department of Language Science and Technology, The Hong Kong Polytechnic University · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore +2

Privacy-Utility Tradeoff Privacy Leakage in Language Models Medical LLMs Medical QA Clinical QA

Mar 14, 2026

Clinician input steers AI toward accurate and harmful recommendations

Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior during clinical interactions. Using 61 curated NEJM Case Records, we tested how expert or misleading clinician reasoning influenced AI-generated differential diagnoses and next step recommendations across 21 reasoning variants from 8 proprietary and open-source models. After clinician exposure, LLM-clinician concordance increased: simulations with >=3 overlapping differential diagnoses rose from 65.8% to 93.5%, and those with >=3 overlapping next step recommendations from 20.3% to 53.8%. Expert context significantly improved correct final-diagnosis inclusion in all 21 models (mean +20.4 pp), reflecting both improved reasoning and passive content echoing, while adversarial context significantly degraded performance in 14 models (mean -5.4 pp). Expert context also significantly increased leading-diagnosis accuracy in all 21 models, whereas adversarial context significantly reduced it in 13. Multi-turn disagreement challenges revealed distinct model phenotypes, from highly conformist to dogmatic, with adversarial arguments remaining a vulnerability even in otherwise resilient models. Inference-time scaling reduced harmful echoing of clinician-introduced recommendations across WHO harm-severity tiers by 62.7% for mild, 57.9% for moderate, 76.3% for severe, and 83.5% for death-tier recommendations. Inference-time prompting recovered diagnostic accuracy lost to adversarial context while preserving expert-context benefits across GPT-5, Claude Sonnet 4.5, and Gemini 3 Flash, and sharply reduced highly consistent harmful echoing across severity tiers. These findings provide a foundation for evaluating clinician-AI collaboration and introduce interactive metrics and mitigation strategies essential to safety and robustness.

Ivan Lopez, Selin S. Everett, Bryan J. Bunning +10

Department of Biomedical Data Science, Stanford University, Stanford, CA, USA · Stanford University School of Medicine, Stanford, CA, USA · Quantitative Sciences Unit, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA +14

Medical LLMs Clinical Language Model Evaluation LLM Sycophancy Adversarial Robustness of Language Models LLM Inference Clinical Reasoning

Mar 14, 2026

Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning

Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap poses serious risks as patients and clinicians may trust coherent but misleading explanations. We conduct a systematic black-box evaluation of faithfulness in medical reasoning among three widely used closed-source LLMs. Our study consists of three perturbation-based probes: (1) causal ablation, testing whether stated chain-of-thought (CoT) reasoning causally influences predictions; (2) positional bias, examining whether models create post-hoc justifications for answers driven by input positioning; and (3) hint injection, testing susceptibility to external suggestions. We complement these quantitative probes with a small-scale human evaluation of model responses to patient-style medical queries to examine concordance between physician assessments of explanation faithfulness and layperson perceptions of trustworthiness. We find that CoT reasoning steps often do not causally drive predictions, and models readily incorporate external hints without acknowledgment. In contrast, positional biases showed minimal impact in this setting. These results underscore that faithfulness, not just accuracy, must be central in evaluating LLMs for medicine, to ensure both public protection and safe clinical deployment.

Halimat Afolabi, Zainab Afolabi, Elizabeth Friel +13

Stratified Precision, United Kingdom · Harvard Medical School, United States · Imperial College London, United Kingdom +3

Faithfulness of Language Model Explanations Medical LLMs CoT Faithfulness Clinical Language Model Evaluation

Mar 14, 2026

QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models

While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evaluations rely heavily on multiple-choice questions, failing to capture the unstructured, ambiguous, and long-tail complexities inherent in genuine user inquiries. To bridge this gap, we introduce QuarkMedBench, an ecologically valid benchmark tailored for real-world medical LLM assessment. We compiled a massive dataset spanning Clinical Care, Wellness Health, and Professional Inquiry, comprising 20,821 single-turn queries and 3,853 multi-turn sessions. To objectively evaluate open-ended answers, we propose an automated scoring framework that integrates multi-model consensus with evidence-based retrieval to dynamically generate 220,617 fine-grained scoring rubrics (~9.8 per query). During evaluation, hierarchical weighting and safety constraints structurally quantify medical accuracy, key-point coverage, and risk interception, effectively mitigating the high costs and subjectivity of human grading. Experimental results demonstrate that the generated rubrics achieve a 91.8% concordance rate with clinical expert blind audits, establishing highly dependable medical reliability. Crucially, baseline evaluations on this benchmark reveal significant performance disparities among state-of-the-art models when navigating real-world clinical nuances, highlighting the limitations of conventional exam-based metrics. Ultimately, QuarkMedBench establishes a rigorous, reproducible yardstick for measuring LLM performance on complex health issues, while its framework inherently supports dynamic knowledge updates to prevent benchmark obsolescence.

Yao Wu, Kangping Yin, Liang Dong +13

Quark Medical Team, Alibaba Group

LLM Evaluation Clinical Language Model Evaluation Medical LLMs Medical QA LLM Safety Evaluation LLM-as-a-Judge

Mar 13, 2026

MedArena: Comparing LLMs for Medicine-in-the-Wild Clinician Preferences

Large language models (LLMs) are increasingly central to clinician workflows, spanning clinical decision support, medical education, and patient communication. However, current evaluation methods for medical LLMs rely heavily on static, templated benchmarks that fail to capture the complexity and dynamics of real-world clinical practice, creating a dissonance between benchmark performance and clinical utility. To address these limitations, we present MedArena, an interactive evaluation platform that enables clinicians to directly test and compare leading LLMs using their own medical queries. Given a clinician-provided query, MedArena presents responses from two randomly selected models and asks the user to select the preferred response. Out of 1571 preferences collected across 12 LLMs up to November 1, 2025, Gemini 2.0 Flash Thinking, Gemini 2.5 Pro, and GPT-4o were the top three models by Bradley-Terry rating. Only one-third of clinician-submitted questions resembled factual recall tasks (e.g., MedQA), whereas the majority addressed topics such as treatment selection, clinical documentation, or patient communication, with ~20% involving multi-turn conversations. Additionally, clinicians cited depth and detail and clarity of presentation more often than raw factual accuracy when explaining their preferences, highlighting the importance of readability and clinical nuance. We also confirm that the model rankings remain stable even after controlling for style-related factors like response length and formatting. By grounding evaluation in real-world clinical questions and preferences, MedArena offers a scalable platform for measuring and improving the utility and efficacy of medical LLMs.

Eric Wu, Kevin Wu, Jason Hom +11

Department of Electrical Engineering, Stanford University, Stanford, CA, USA · Department of Biomedical Data Science, Stanford University, Stanford, CA, USA · Division of Hospital Medicine, Department of Medicine, Stanford School of Medicine, Stanford, CA, USA +8

Clinical Language Model Evaluation Medical LLMs Human Preference Evaluation Pairwise Comparison

Mar 13, 2026

Developing and evaluating a chatbot to support maternal health care

The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource settings where users have low health literacy and limited access to care. However, deploying such systems is technically challenging: user queries are short, underspecified, and code-mixed across languages, answers require regional context-specific grounding, and partial or missing symptom context makes safe routing decisions difficult. We present a chatbot for maternal health in India developed through a partnership between academic researchers, a health tech company, a public health nonprofit, and a hospital. The system combines (1) stage-aware triage, routing high-risk queries to expert templates, (2) hybrid retrieval over curated maternal/newborn guidelines, and (3) evidence-conditioned generation from an LLM. Our core contribution is an evaluation workflow for high-stakes deployment under limited expert supervision. Targeting both component-level and end-to-end testing, we introduce: (i) a labeled triage benchmark (N=150) achieving 86.7% emergency recall, explicitly reporting the missed-emergency vs. over-escalation trade-off; (ii) a synthetic multi-evidence retrieval benchmark (N=100) with chunk-level evidence labels; (iii) LLM-as-judge comparison on real queries (N=781) using clinician-codesigned criteria; and (iv) expert validation. Our findings show that trustworthy medical assistants in multilingual, noisy settings require defense-in-depth design paired with multi-method evaluation, rather than any single model and evaluation method choice.

Smriti Jha, Vidhi Jain, Jianyu Xu +8

Carnegie Mellon University · Population Council Institute · Sitaram Bhartia Institute of Science and Research +1

Healthcare Medical LLMs Clinical Triage Clinical Language Model Evaluation RAG Evaluation

Mar 12, 2026

Performance Evaluation of Open-Source Large Language Models for Assisting Pathology Report Writing in Japanese

The performance of large language models (LLMs) for supporting pathology report writing in Japanese remains unexplored. We evaluated seven open-source LLMs from three perspectives: (A) generation and information extraction of pathology diagnosis text following predefined formats, (B) correction of typographical errors in Japanese pathology reports, and (C) subjective evaluation of model-generated explanatory text by pathologists and clinicians. Thinking models and medical-specialized models showed advantages in structured reporting tasks that required reasoning and in typo correction. In contrast, preferences for explanatory outputs varied substantially across raters. Although the utility of LLMs differed by task, our findings suggest that open-source LLMs can be useful for assisting Japanese pathology report writing in limited but clinically relevant scenarios.

Masataka Kawai, Singo Sakashita, Shumpei Ishikawa +8

Department of Pathology and Clinical Laboratories, National Cancer Center Hospital East, Kashiwa, Japan · Department of Pathology, University of Yamanashi, Chuo, Japan · Division of Pathology, Exploratory Oncology Research & Clinical Trial Center, National Cancer Center, Kashiwa, Japan +3

Medical Report Generation Medical LLMs Clinical Language Model Evaluation LLM Information Extraction Grammatical Error Correction

Mar 11, 2026

Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning

Machine unlearning is increasingly important for clinical language models, where privacy regulations and institutional policies may require removing sensitive information from deployed systems without retraining from scratch. In practice, deletion requests must balance effective forgetting of targeted information with preservation of model utility and minimal parameter modification. We introduce Sparse Token Embedding Unlearning (STEU), a parameter-efficient method for behavioral class-level unlearning that updates only PMI-selected token embeddings together with a small classifier head while keeping all encoder layers frozen. Across experiments on MIMIC-IV, MIMIC-III, and eICU using BioClinicalBERT, BERT-base, and DistilBERT, STEU consistently suppresses the target class while largely preserving retained task performance. In the primary MIMIC-IV setting, STEU achieves near-complete forgetting (forget F1 = 0.0004) while maintaining competitive retained utility (retain avg F1 = 0.4766) after modifying only 0.19% of model parameters. These results suggest that targeted behavioral unlearning can be achieved through sparse embedding edits without modifying deeper encoder representations.

Iyad Ait Hou, Shrenik Borad, Harsh Sharma +3

Department of Computer Science, The George Washington University, Washington, DC · Center for Speech and Language Processing, Johns Hopkins University, Baltimore, MD

Machine Unlearning Language Model Editing Medical LLMs Parameter-Efficient Fine-Tuning

Mar 11, 2026

PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation

PET/CT imaging is pivotal in oncology and nuclear medicine, yet summarizing complex findings into precise diagnostic impressions is labor-intensive. While LLMs have shown promise in medical text generation, their capability in the highly specialized domain of PET/CT remains underexplored. We introduce PET-F2I-41K (PET Findings-to-Impression Benchmark), a large-scale benchmark for PET/CT impression generation using LLMs, constructed from over 41k real-world reports. Using PET-F2I-41K, we conduct a comprehensive evaluation of 27 models across proprietary frontier LLMs, open-source generalist models, and medical-domain LLMs, and we develop a domain-adapted 7B model (PET-F2I-7B) fine-tuned from Qwen2.5-7B-Instruct via LoRA. Beyond standard NLG metrics (e.g., BLEU-4, ROUGE-L, BERTScore), we propose three clinically grounded metrics - Entity Coverage Rate (ECR), Uncovered Entity Rate (UER), and Factual Consistency Rate (FCR) - to assess diagnostic completeness and factual reliability. Experiments reveal that neither frontier nor medical-domain LLMs perform adequately in zero-shot settings. In contrast, PET-F2I-7B achieves substantial gains (e.g., 0.708 BLEU-4) and a 3.0x improvement in entity coverage over the strongest baseline, while offering advantages in cost, latency, and privacy. Beyond this modeling contribution, PET-F2I-41K establishes a standardized evaluation framework to accelerate the development of reliable and clinically deployable reporting systems for PET/CT.

Yuchen Liu, Wenbo Zhang, Liling Peng +6

Fudan University · Shanghai Academy of Artificial Intelligence for Science · Shanghai Universal Medical Imaging Diagnostic Center +1

Radiology Report Generation Medical LLMs Radiology Report Evaluation PET/CT Imaging

Mar 11, 2026

Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent

We present PULSE, a medical reasoning agent that combines a domain-tuned large language model with scientific literature retrieval to support diagnostic decision-making in complex real-world cases. To evaluate its capabilities, we curated a benchmark of 82 authentic endocrinology case reports encompassing a broad spectrum of disease types and incidence levels. In controlled experiments, we compared PULSE's performance against physicians with varying levels of expertise-from residents to senior specialists-and examined how AI assistance influenced human diagnostic reasoning. PULSE attained expert-competitive accuracy, outperforming residents and junior specialists while matching senior specialist performance at both Top@1 and Top@4 thresholds. Unlike physicians, whose accuracy declined with disease rarity, PULSE maintained stable performance across incidence tiers. The agent also exhibited adaptive reasoning, increasing output length with case difficulty in a manner analogous to the longer deliberation observed among expert clinicians. When used collaboratively, PULSE enabled physicians to correct initial errors and broaden diagnostic hypotheses, but also introduced risks of automation bias. The study explores both serial and concurrent collaboration workflows, revealing that PULSE offers robust support across common and rare presentations. These findings underscore both the promise and the limitations of language model-based agents in clinical diagnosis, and offer a framework for evaluating their role in real-world decision-making.

Zhongzhen Huang, Yan Ling, Hong Chen +7

Shanghai Jiao Tong University, Shanghai, China · Department of Endocrinology, Zhongshan Hospital, Fudan University, Shanghai, China · Department of Endocrinology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China +3

Medical Diagnosis Clinical Decision Support Human-AI Decision Making Medical LLMs Clinical Language Model Evaluation

Mar 10, 2026

Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language Models

Radiology reports capture crucial longitudinal information on tumor burden, treatment response, and disease progression, yet their unstructured narrative format complicates automated analysis. While large language models (LLMs) have advanced clinical text processing, most state-of-the-art systems remain proprietary, limiting their applicability in privacy-sensitive healthcare environments. We present a fully open-source, locally deployable pipeline for longitudinal information extraction from radiology reports, implemented using the llm_extractinator framework. The system applies the qwen2.5-72b model to extract and link target, non-target, and new lesion data across time points in accordance with RECIST criteria. Evaluation on 50 Dutch CT Thorax/Abdomen report pairs yielded high extraction performance, with attribute-level accuracies of 93.7% for target lesions, 94.9% for non-target lesions, and 94.0% for new lesions. The approach demonstrates that open-source LLMs can achieve clinically meaningful performance in multi-timepoint oncology tasks while ensuring data privacy and reproducibility. These results highlight the potential of locally deployable LLMs for scalable extraction of structured longitudinal data from routine clinical text.

Luc Builtjes, Alessa Hering

Department of Medical Imaging, Radboudumc, Nijmegen, The Netherlands

Clinical Information Extraction LLM Information Extraction Medical LLMs

Mar 10, 2026

Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health

Large Language Models (LLMs) excel in Natural Language Processing (NLP) tasks, but they often propagate biases embedded in their training data, which is potentially impactful in sensitive domains like healthcare. While existing benchmarks evaluate biases related to individual social determinants of health (SDoH) such as gender or ethnicity, they often overlook interactions between these factors and lack context-specific assessments. This study investigates bias in LLMs by probing the relationships between gender and other SDoH in French patient records. Through a series of experiments, we found that embedded stereotypes can be probed using SDoH input and that LLMs rely on embedded stereotypes to make gendered decisions, suggesting that evaluating interactions among SDoH factors could usefully complement existing approaches to assessing LLM performance and bias.

Trung Hieu Ngo, Adrien Bazoge, Solen Quiniou +2

Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004, F-44000 Nantes, France · Nantes Université, CHU Nantes, Clinique des données, INSERM, CIC 1413, Nantes, France

Intersectional Bias in Language Models Social Bias in Language Models Gender Bias in Language Models Language Model Bias Evaluation Medical LLMs

Mar 9, 2026

Meissa: Multi-modal Medical Agentic Intelligence

Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely almost entirely on frontier models (e.g., GPT), whose API-based deployment incurs high cost, high latency, and privacy risks that conflict with on-premise clinical requirements. We present Meissa, a lightweight 4B-parameter medical MM-LLM that brings agentic capability offline. Instead of imitating static answers, Meissa learns both when to engage external interaction (strategy selection) and how to execute multi-step interaction (strategy execution) by distilling structured trajectories from frontier models. Specifically, we propose: (1) Unified trajectory modeling: trajectories (reasoning and action traces) are represented within a single state-action-observation formalism, allowing one model to generalize across heterogeneous medical environments. (2) Three-tier stratified supervision: the model's own errors trigger progressive escalation from direct reasoning to tool-augmented and multi-agent interaction, explicitly learning difficulty-aware strategy selection. (3) Prospective-retrospective supervision: pairing exploratory forward traces with hindsight-rationalized execution traces enables stable learning of effective interaction policies. Trained on 40K curated trajectories, Meissa matches or exceeds proprietary frontier agents in 10 of 16 evaluation settings across 13 medical benchmarks spanning radiology, pathology, and clinical reasoning. Using over 25x fewer parameters than typical frontier models like Gemini-3, Meissa operates fully offline with 22x lower end-to-end latency compared to API-based deployment. Data, models, and environments are released at https://github.com/Schuture/Meissa.

Yixiong Chen, Xinyi Bai, Yue Pan +2

Johns Hopkins University, Baltimore, MD, USA · Cornell University, Ithaca, NY, USA

Medical AI Agents Medical LLMs Multimodal Agents LLM Agent Training Multi-Agent LLM Systems Medical VLMs

Mar 9, 2026

MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment

Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting (MV) as a heuristic supervision signal, which can be unreliable in complex medical scenarios where the most frequent reasoning path is not necessarily the clinically correct one. In this work, we propose a novel and unified training paradigm that integrates medical process reward models with TTRL to bridge the gap between test-time scaling (TTS) and parametric model optimization. Specifically, we advance the TTRL framework by replacing the conventional MV with a fine-grained, expert-aligned supervision paradigm using Med-RPM. This integration ensures that reinforcement learning is guided by medical correctness rather than mere consensus, effectively distilling search-based intelligence into the model's parametric memory. Extensive evaluations on four different benchmarks have demonstrated that our developed method consistently and significantly outperforms current TTRL and standalone PRM selection. Our findings establish that transitioning from stochastic heuristics to structured, step-wise rewards is essential for developing reliable and scalable medical AI systems

Kailong Fan, Anqi Pu, Yichen Wu +7

Zhejiang University · Harvard Medical School · Harvard University

Medical LLMs RL for Language Models Process Reward Models

Mar 9, 2026

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic

Large language model (LLM)-based AI systems have shown promise for patient-facing diagnostic and management conversations in simulated settings. Translating these systems into clinical practice requires assessment in real-world workflows with rigorous safety oversight. We report a prospective, single-arm feasibility study of an LLM-based conversational AI, the Articulate Medical Intelligence Explorer (AMIE), conducting clinical history taking and presentation of potential diagnoses for patients to discuss with their provider at urgent care appointments at a leading academic medical center. 100 adult patients completed an AMIE text-chat interaction up to 5 days before their appointment. We sought to assess the conversational safety and quality, patient and clinician experience, and clinical reasoning capabilities compared to primary care providers (PCPs). Human safety supervisors monitored all patient-AMIE interactions in real time and did not need to intervene to stop any consultations based on pre-defined criteria. Patients reported high satisfaction and their attitudes towards AI improved after interacting with AMIE (p < 0.001). PCPs found AMIE's output useful with a positive impact on preparedness. AMIE's differential diagnosis (DDx) included the final diagnosis, per chart review 8 weeks post-encounter, in 90% of cases, with 75% top-3 accuracy. Blinded assessment of AMIE and PCP DDx and management (Mx) plans suggested similar overall DDx and Mx plan quality, without significant differences for DDx (p = 0.6) and appropriateness and safety of Mx (p = 0.1 and 1.0, respectively). PCPs outperformed AMIE in the practicality (p = 0.003) and cost effectiveness (p = 0.004) of Mx. While further research is needed, this study demonstrates the initial feasibility, safety, and user acceptance of conversational AI in a real-world setting, representing crucial steps towards clinical translation.

Peter Brodeur, Jacob M. Koshy, Anil Palepu +45

Healthcare Medical LLMs Clinical Language Model Evaluation Clinical Decision Support Clinical Reasoning Human-in-the-Loop AI

Mar 9, 2026

COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling

Systems that collect data on sleep, mood, and activities can provide valuable lifestyle counselling to populations affected by chronic disease and its consequences. Such systems are, however, challenging to develop; besides reliably extracting patterns from user-specific data, systems should also contextualise these patterns with validated medical knowledge to ensure the quality of counselling, and generate counselling that is relevant to a real user. We present QUORUM, a new evaluation framework that unifies these developer-, expert-, and user-centric perspectives, and show with a real case study that it meaningfully tracks convergence and divergence in stakeholder perspectives. We also present COACH, a Large Language Model-driven pipeline to generate personalised lifestyle counselling for our Healthy Chronos use case, a diary app for cancer patients and survivors. Applying our framework shows that overall, users, medical experts, and developers converge on the opinion that the generated counselling is relevant, of good quality, and reliable. However, stakeholders also diverge on the tone of the counselling, sensitivity to errors in pattern-extraction, and potential hallucinations. These findings highlight the importance of multi-stakeholder evaluation for consumer health language technologies and illustrate how a unified evaluation framework can support trustworthy, patient-centered NLP systems in real-world settings.

Yee Man Ng, Bram van Dijk, Pieter Beynen +5

Leiden University · Leiden University Medical Center · Healthy Chronos

Clinical Language Model Evaluation Medical LLMs Personalized Language Models

Mar 6, 2026

MedInjection-FR: Exploring the Role of Native, Synthetic, and Translated Data in Biomedical Instruction Tuning

Instruction tuning has become essential for adapting large language models (LLMs) to follow domain-specific prompts. Yet, in specialized fields such as medicine, the scarcity of high-quality French instruction data limits effective supervision. To address this gap, we introduce MedInjection-FR, a large-scale French biomedical instruction dataset comprising 571K instruction-response pairs drawn from three complementary sources: native, synthetic, and translated data. We design a controlled experimental framework to systematically assess how data provenance affects instruction tuning, using Qwen-4B-Instruct fine-tuned across seven configurations combining these sources. Results show that native data yield the strongest performance, while mixed setups, particularly native and translated, provide complementary benefits. Synthetic data alone remains less effective but contributes positively when balanced with native supervision. Evaluation on open-ended QA combines automatic metrics, LLM-as-a-judge assessment, and human expert review; although LLM-based judgments correlate best with human ratings, they show sensitivity to verbosity. These findings highlight that data authenticity and diversity jointly shape downstream adaptation and that heterogeneous supervision can mitigate the scarcity of native French medical instructions.

Ikram Belmadani, Oumaima El Khettari, Pacôme Constant dit Beaufils +2

Aix-Marseille Univ., CNRS, LIS UMR 7020, 13000 Marseille, France · Nantes Univ., École Centrale Nantes, CNRS, LS2N, UMR 6004, 44000 Nantes, France · Nantes Univ., CHU Nantes, PHU 11: Santé Publique, Clinique des données, INSERM, CIC 1413, 44000 Nantes, France +2

Instruction Tuning Medical LLMs Synthetic Data Generation for Language Models

Mar 6, 2026

Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks

While Large Language Models demonstrate immense potential as proactive Medical Agents, their real-world deployment is severely bottlenecked by data scarcity under privacy constraints. To overcome this, we propose State-Enhanced Logical-Skill Memory (SELSM), a training-free framework that distills simulated clinical trajectories into entity-agnostic operational rules within an abstract skill space. During inference, a Query-Anchored Two-Stage Retrieval mechanism dynamically fetches these entity-agnostic logical priors to guide the agent's step-by-step reasoning, effectively resolving the state polysemy problem. Evaluated on MedAgentBench -- the only authoritative high-fidelity virtual EHR sandbox benchmarked with real clinical data -- SELSM substantially elevates the zero-shot capabilities of locally deployable foundation models (30B--32B parameters). Notably, on the Qwen3-30B-A3B backbone, our framework completely eliminates task chain breakdowns to achieve a 100% completion rate, boosting the overall success rate by an absolute 22.67% and significantly outperforming existing memory-augmented baselines. This study demonstrates that equipping models with a dynamically updatable, state-enhanced cognitive scaffold is a privacy-preserving and computationally efficient pathway for local adaptation of AI agents to clinical information systems. While currently validated on FHIR-based EHR interactions as an initial step, the entity-agnostic design of SELSM provides a principled foundation toward broader clinical deployment.

Wanrong Yang, Zhengliang Liu, Yuan Li +6

Department of Computer Science, University of Liverpool, Liverpool, UK · School of Computing, University of Georgia, Athens, GA, USA · Beijing Normal University, Beijing, China +2

Memory-Augmented Language Model Agents Medical LLMs LLM Agent Skill Learning Privacy-Preserving Language Models

Mar 6, 2026

From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM

Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models.

Chanyong Luo, Jirui Dai, Zhendong Wang +14

the Infectious disease department, Dongfang Hospital, Beijing University of Chinese Medicine, Beijing, China · the Department of Computer Science, Johns Hopkins University, Baltimore, USA · the Gulou Hospital of Traditional Chinese Medicine of Beijing，Beijing, China +8

Traditional Chinese Medicine Medical LLMs Clinical Decision-Making

Mar 6, 2026

Training a Large Language Model for Medical Coding Using Privacy-Preserving Synthetic Clinical Data

Improving the accuracy and reliability of medical coding reduces clinician burnout and supports revenue cycle processes, freeing providers to focus more on patient care. However, automating the assignment of ICD-10-CM and CPT codes from clinical documentation remains a challenge due to heterogeneous records, nuanced coding guidelines, and long-tail distributions. Large language models have been proposed to help or automate specific medical coding tasks. However, foundation models are not explicitly trained for medical coding and zero-shot coding has yielded poor results. We investigate whether a modern open-weight foundation model can be adapted for an expert-level medical coding task using privacy-preserving synthetic training data derived from electronic health records. We fine-tune Llama 3-70B on pairs of clinical notes and gold codes generated from EHR-grounded templates and coding policies, then evaluate exact-code prediction for ICD-10-CM and CPT. A zero-shot baseline with the unadapted model achieved an F1 score of 0.18 for exact code match. After fine-tuning on the synthetic corpus, exact-match F1 exceeded 0.70, representing a large absolute gain across both code systems. Notably, performance remained high on complex categories that often require multi-step clinical reasoning and code composition, including Advanced Illness and Frailty classes, and the model retained its performance on medical comprehension tasks. These results indicate that synthetic, policy-aware data can efficiently teach a general-purpose large language model to support precise medical coding without exposing protected health information. The approach offers a practical path for training coding agents safely and iteratively on specific tasks that represent real-world populations.

John Cook, Michael Wyatt, Peng Wei +11

Veradigm · Snowflake

Automated Medical Coding Medical LLMs LLM Fine-Tuning

Mar 6, 2026

PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models

Motivation: Patient-generated text contains critical information about patients' lived experiences, social circumstances, and engagement in care, including factors that strongly influence adherence, care coordination, and health equity. However, these patient voice signals are rarely available in structured form, limiting their use in patient-centered outcomes research and clinical quality improvement. Reliable extraction of such information is therefore essential for understanding and addressing non-clinical drivers of health outcomes at scale. Results: We introduce PVminer, a benchmark for structured extraction of patient voice, and propose PVminerLLM, a supervised fine-tuned large language model tailored to this task. Across multiple datasets and model sizes, PVminerLLM substantially outperforms prompt-based baselines, achieving up to 83.82% F1 for Code prediction, 80.74% F1 for Sub-code prediction, and 87.03% F1 for evidence Span extraction. Notably, strong performance is achieved even with smaller models, demonstrating that reliable patient voice extraction is feasible without extreme model scale. These results enable scalable analysis of social and experiential signals embedded in patient-generated text. Availability and Implementation: Code, evaluation scripts, and trained LLMs will be released publicly. Annotated datasets will be made available upon request for research use. Keywords: Large Language Models, Supervised Fine-Tuning, Medical Annotation, Patient-Generated Text, Clinical NLP

Samah Fodeh, Linhai Ma, Ganesh Puthiaraju +5

Yale University, New Haven, CT, USA. · Texas State University, San Marcos, TX, USA.

Clinical Information Extraction Healthcare Medical LLMs LLM Fine-Tuning

Mar 5, 2026

Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution

Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of small language models with only three billion parameters. Trained on high-quality synthetic data newly developed in this study, Med-V1 substantially outperforms (+27.0% to +71.3%) its base models on five biomedical benchmarks unified into a verification format. Despite its smaller size, Med-V1 performs comparably to frontier LLMs such as GPT-5, along with high-quality explanations for its predictions. We use Med-V1 to conduct a first-of-its-kind use case study that quantifies hallucinations in LLM-generated answers under different citation instructions. Results show that the format instruction strongly affects citation validity and hallucination, with GPT-5 generating more claims but exhibiting hallucination rates similar to GPT-4o. Additionally, we present a second use case showing that Med-V1 can automatically identify high-stakes evidence misattributions in clinical practice guidelines, revealing potentially negative public health impacts that are otherwise challenging to identify at scale. Overall, Med-V1 provides an efficient and accurate lightweight alternative to frontier LLMs for practical, real-world biomedical evidence attribution. Med-V1 is available at https://github.com/NLM-DIR/Med-V1.

Qiao Jin, Yin Fang, Lauren He +12

Division of Intramural Research, National Library of Medicine, National Institutes of Health · Department of Computer Science, University of Virginia · Center for Cancer Research, National Cancer Institute, National Institutes of Health +3

LLM Answer Verification Healthcare Small Language Models LLM Hallucination Detection Medical LLMs Scientific Claim Verification