Clinical Reasoning

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease labels followed by Group Relative Policy Optimization (GRPO) to refine predictions by optimizing accuracy and format without reasoning supervision. Across three radiologist-annotated datasets, SFT outperformed baselines and GRPO further improved classification and enhanced reasoning recall and comprehensiveness.

Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We tested five frontier LLMs across 36 clinician-validated scenarios for three rare neuromuscular disease pairs. No model produced a clinically relevant PubMed identifier without prompting. When explicitly asked to cite, the best model achieved 15.3% relevant PMIDs; the majority resolved to real publications in unrelated fields. We present HEG-TKG (Hierarchical Evidence-Grounded Temporal Knowledge Graphs), a system that grounds clinical claims in temporal knowledge graphs built from 4,512 PubMed records and curated sources with quality-tier stratification and 1,280 disease-trajectory milestones. In a controlled three-arm comparison using the same synthesis model, HEG-TKG matches baseline clinical feature coverage while achieving 100% evidence verifiability with 203 inline citations. Guideline-RAG, given overlapping source documents as raw text, produces zero verifiable citations. LLM judges cannot distinguish fabricated from verified citations without PubMed audit data. Independent clinician evaluation confirms the verifiability advantage (Cohen's d = 1.81, p < 0.001) with no degradation on safety or completeness. A counterfactual experiment shows 80% resistance to injected clinical errors with 100% detectability via citation trace. The system deploys on-premise via open-source models so patient data never leaves institutional infrastructure.

Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work.

Evaluating large language models (LLMs) for clinical documentation tasks such as SOAP note generation remains challenging. Unlike standard summarization, these tasks require clinical abstraction, normalization of colloquial language, and medically grounded inference. However, prevailing evaluation methods including automated metrics and LLM as judge frameworks rely on lexical faithfulness, often labeling any information not explicitly present in the transcript as hallucination. We show that such approaches systematically misclassify clinically valid outputs as errors, inflating hallucination rates and distorting model assessment. Our analysis reveals that many flagged hallucinations correspond to legitimate clinical transformations, including synonym mapping, abstraction of examination findings, diagnostic inference, and guideline consistent care planning. By aligning evaluation criteria with clinical reasoning through calibrated prompting and retrieval grounded in medical ontologies we observe a significant shift in outcomes. Under a lexical evaluation regime, the mean hallucination rate is 35%, heavily penalizing valid reasoning. With inference aware evaluation, this drops to 9%, with remaining cases reflecting genuine safety concerns. These findings suggest that current evaluation practices over penalize valid clinical reasoning and may measure artifacts of evaluation design rather than true errors, underscoring the need for clinically informed evaluation in high context domains like medicine.

Acute poly-substance intoxication requires rapid, life-saving decisions under substantial uncertainty, as clinicians must rely on incomplete ingestion details and nonspecific symptoms. Effective diagnostic reasoning in this chaotic environment requires fusing unstructured, non-medical narratives (e.g. paramedic scene descriptions and unreliable patient self-reports or known histories), with structured medical data like vital signs. While Large Language Models (LLMs) show potential for processing such heterogeneous inputs, they struggle in this setting, often underperforming simple baselines that rely solely on patient histories. To address this, we present DeToxR (Decision-support for Toxicology with Reasoning), the first adaptation of Reinforcement Learning (RL) to emergency toxicology. We design a robust data-fusion engine for multi-label prediction across 14 substance classes based on an LLM finetuned with Group Relative Policy Optimization (GRPO). We optimize the model's reasoning directly using a clinical performance reward. By formulating a multi-label agreement metric as the reward signal, the model is explicitly penalized for missing co-ingested substances and hallucinating absent poisons. Our model significantly outperforms its unadapted base LLM counterpart and supervised baselines. Furthermore, in a preliminary clinical validation study, the model indicates a clinical advantage by achieving higher micro-F1 (0.644 vs 0.473) and recall in identifying the correct poisons. These results demonstrate the potential of RL-aligned LLMs to synthesize unstructured pre-clinical narratives and structured medical data for decision support in high-stakes environments.

Large language models (LLMs) are increasingly used for medical consultation and health information support, where safety depends not only on medical knowledge but also on robust responses to unclear, inconsistent, or misleading patient input. However, most existing medical LLM evaluations assume idealized and well-posed patient questions, limiting their realism. We study challenging patient behaviors that commonly arise in real medical consultations and complicate safe clinical reasoning. We define four clinically grounded categories of such behaviors: information contradiction, factual inaccuracy, self-diagnosis, and care resistance. For each behavior, we specify concrete failure criteria that capture unsafe responses. Building on four existing medical dialogue datasets, we introduce CPB-Bench (Challenging Patient Behaviors Benchmark), a bilingual (English and Chinese) benchmark of multi-turn dialogues annotated for these behaviors. We find that although models perform well overall, they exhibit consistent behavior-specific failures, especially when handling contradictory or medically implausible patient information. We further evaluate four intervention strategies and find inconsistent improvements, with some interventions introducing unnecessary corrections.

Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices. Existing dialogue and retrieval-augmented systems condition policies on raw histories or appended passages, leaving observed evidence, missing checks, differentials, and support reliability entangled. We introduce MIND, a criteria-grounded evidence-state decision interface. At each turn, MIND constructs a typed state containing observed evidence, unresolved criterion checks, active differentials, criterion-linked supports, and reliability metadata. A training-split Psychiatric Reasoning Bank supplies gated supports, turning retrieval into state construction rather than prompt injection. The same state conditions action selection, process rewards, information-gain scoring, and trajectory rectification. Under EMR-grounded simulator protocols, MIND improves accuracy by 8.8 and 7.3 points over strong inference-only, RAG, and RL baselines, with gains transferring to public MDD-5k dialogues. Matched interventions attribute these gains to the shared state rather than prompt length, retrieval text, or formatting. MIND targets screening-level decision support, not autonomous diagnosis. Code is available at https://github.com/Lingxi-mental-health/MIND.Å

Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remains: top-performing systems are either closed-source or computationally prohibitive, precluding the on-premises deployment required for patient privacy and PHI compliance. We introduce MEDGPT-OSS, an open-weight, 20B-parameter generalist vision-language model designed to facilitate open research in clinical AI. Rather than relying on architectural complexity, MEDGPT-OSS pairs the GPT-oss language backbone with a visual front-end via a optimized, three-stage training curriculum. By progressively domain-adapting these modules through rigorous data curation and long-context multimodal alignment, we demonstrate that a 20B model can bridge the capacity gap. It successfully outperforms larger open medical models on out-of-distribution (OOD) multimodal reasoning and complex text-only clinical tasks. By unifying diverse modalities under a single instruction-following interface, MEDGPT-OSS maintains a parameter-efficient footprint fully compatible with commodity GPUs. We release the complete training recipe, open-weight checkpoints, and a rigorous evaluation harness to serve as a verifiable foundation for privacy-preserving, institution-specific clinical AI research.

Conversational diagnosis requires multi-turn history-taking, where an agent asks clarifying questions to refine differential diagnoses under incomplete information. Existing approaches often rely on the parametric knowledge of a model or assume that patients provide rich and concrete information, which is unrealistic. To address these limitations, we propose a conversational diagnosis system that explores a diagnostic knowledge graph to reason in two steps: (i) generating diagnostic hypotheses from the dialogue context, and (ii) verifying hypotheses through clarifying questions, which are repeated until a final diagnosis is reached. Since evaluating the system requires a realistic patient simulator that responds to the system's questions, we adopt PatientSim, a persona-driven patient simulator, together with patient profiles from MIMIC-IV. We further adapt it with low-specificity symptom reporting to reflect how real-world patients describe symptoms vaguely during early clinical encounters. Experiments show improved diagnostic accuracy and efficiency over strong baselines, and physician evaluations support the realism of our simulator and the clinical utility of the generated clarifying questions. Our code will be released upon publication.

Endoscopic diagnosis is an iterative process in which clinicians acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do not adequately support this process because fine-grained evidence acquisition and multi-step reasoning remain weakly coupled, complicating reconciliation of image-derived findings with their textual interpretations. This gives rise to two failure modes, hallucinated evidence and uncorrected error accumulation, that undermine diagnostic reliability. We propose EndoCogniAgent, a closed-loop agentic framework that formulates endoscopic diagnosis as a controlled state update process for integrating complementary visual and textual evidence. At each reasoning round, a central planner selects an evidence acquisition action, specialized expert tools extract spatial and semantic observations as structured textual evidence, and a self-consistency validation mechanism examines this evidence along two dimensions, knowledge consistency against the input image and temporal consistency with prior validated findings, before updating the diagnostic state. Validated observations are admitted into the evolving state to condition subsequent planning, while insufficiently supported or conflicting findings are retained with corrective feedback that redirects the planner toward additional verification. We further introduce EndoAgentBench, a workflow-oriented benchmark comprising 6,132 question-answer pairs from 11 endoscopic datasets, to evaluate diagnostic agents across a comprehensive diagnostic chain, from fine-grained visual perception to high-level diagnostic reasoning. EndoCogniAgent achieves 85.23% overall accuracy on perception tasks and 71.13% clinical acceptance rate on reasoning tasks. Blinded clinician evaluation further shows consistent improvements in diagnostic response quality over the evaluated baselines.

There is growing interest in using machine learning (ML) to support clinical diagnosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequential, resource-aware reasoning clinicians use in practice. Diagnosis remains complex and error prone, especially in high-pressure or resource-limited settings, underscoring the need for frameworks that help clinicians make timely and cost-effective decisions. We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design), a diagnostic framework that integrates Bayesian Experimental Design (BED) with large language models (LLMs) to better emulate real-world diagnostic reasoning. At each step, ACTMED selects the test expected to yield the greatest reduction in diagnostic uncertainty for a given patient. LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data. Clinicians can remain in the loop; reviewing test suggestions, interpreting intermediate outputs, and applying clinical judgment throughout. We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use. This represents a step toward transparent, adaptive, and clinician-aligned diagnostic systems that generalize across settings with reduced reliance on domain-specific data.

Large-scale language models (LLMs) often offer clinical judgments based on incomplete information, increasing the risk of misdiagnosis. Existing studies have primarily evaluated confidence in single-turn, static settings, overlooking the coupling between confidence and correctness as clinical evidence accumulates during real consultations, which limits their support for reliable decision-making. We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations. Our benchmark unifies three types of medical data for open-ended diagnostic generation and introduces an information sufficiency gradient to characterize the confidence-correctness dynamics as evidence increases. We implement and compare 27 representative methods on this benchmark; two key insights emerge: (1) medical data amplifies the inherent limitations of token-level and consistency-level confidence methods, and (2) medical reasoning must be evaluated for both diagnostic accuracy and information completeness. Based on these insights, we present MedConf, an evidence-grounded linguistic self-assessment framework that constructs symptom profiles via retrieval-augmented generation, aligns patient information with supporting, missing, and contradictory relations, and aggregates them into an interpretable confidence estimate through weighted integration. Across two LLMs and three medical datasets, MedConf consistently outperforms state-of-the-art methods on both AUROC and Pearson correlation coefficient metrics, maintaining stable performance under conditions of information insufficiency and multimorbidity. These results demonstrate that information adequacy is a key determinant of credible medical confidence modeling, providing a new pathway toward building more reliable and interpretable large medical models.

Clinical diagnosis is a gradual process of evidence integration, in which physicians move from symptoms and medical history to examinations, competing hypotheses, disease relations, and treatment decisions. Large language models have advanced medical text understanding and generation. Yet their clinical use remains limited by weak evidence grounding, opaque reasoning, and inconsistent links among differential diagnosis, final diagnosis, diagnostic basis, and treatment planning. We introduce MedCollab, a multi-agent framework for full-cycle clinical diagnosis and report generation. MedCollab coordinates specialist and examination agents according to patient records. It structures agent deliberation with an Issue-Based Information System (IBIS) protocol, so that each diagnostic position is supported by patient-specific evidence and medical knowledge. It also builds Hierarchical Disease Relation Chains (HDRC) to connect accepted hypotheses through progression, complication, and comorbidity relations. During multi-round deliberation, a verifier-guided consensus module evaluates evidence support, medical plausibility, and logical conflicts. It then adjusts agent contributions and filters unsupported reasoning. Experiments on ClinicalBench and MIMIC-IV show that MedCollab outperforms leading LLMs and medical multi-agent baselines in diagnostic accuracy, evidence consistency, and clinical reasoning quality. These results indicate that structured and auditable collaboration can produce more faithful and clinically coherent diagnostic reports.