Large language models achieve high scores on medical knowledge assessments, yet clinical reasoning requires actively deciding what to investigate under uncertainty. We developed an agentic evaluation framework in hematologic oncology in which models must proactively request clinical data across three sequential rounds before committing to a diagnosis and treatment plan. Across 32 frontier models, the best achieved only 68% overall accuracy. Information utilization, the fraction of available data actually requested, was the strongest predictor of diagnostic accuracy (R = 0.69, P<0.001), yet utilization collapsed from 57% to 26% in the final round, leaving molecular and cytogenetic data critical for treatment selection unexamined. Reasoning traces scored high on a clinical reasoning rubric (91% above threshold) but decorrelated from accuracy, revealing a gap between locally coherent rationales and globally correct conclusions. Error analysis identified search satisficing, anchoring and premature closure as the dominant failure modes, the same cognitive biases that characterize novice clinicians under dual-process models of diagnostic reasoning. These findings demonstrate that the primary limitation of current models in clinical oncology is not insufficient medical knowledge but a systematic failure of information-seeking under uncertainty.
Large language models (LLMs) show strong performance on clinical benchmarks, yet their reasoning reliability in real-world oncology care remains unclear. We evaluated LLM reasoning on authentic oncology notes using a novel hierarchical error taxonomy across two retrospective cohorts spanning breast, pancreatic, and prostate cancer. GPT-4 produced reasoning errors in 23.1% of note interpretations, the majority reflecting cognitive bias patterns. Errors were more frequent in recommendation tasks and were strongly associated with guideline-discordant recommendations and lower clinician-rated clinical impact scores. Confirmation bias, anchoring bias, and omission errors were most strongly linked to potentially harmful outputs. Compared to GPT-4, GPT-5.1 demonstrated reduced error rates and improved clinical performance but retained structured reasoning failure patterns. Automated LLM-based evaluators detected error presence but failed to reliably classify subtypes, and a preliminary self-mitigation strategy yielded only modest improvement. Endpoint accuracy alone may mask clinically meaningful reasoning failures. Therefore, evaluating and monitoring reasoning fidelity should be a prerequisite for safe deployment of LLMs in oncology decision support.
Matthew Kenaston, U. Ayub, Mihir Parmar et al.· npj Digital Medicine· 0 citations
Findings show that clinical LLM explainability has shifted toward fluent generative rationales, but evidence that such explanations reflect model reasoning remains limited, and three regulatory priorities are highlighted: prioritizing explanations that enable independent verification or logic auditing over plausibility-only rationales; preferring inspectable models where regulatory documentation is required; and prospectively validating explanations in clinical workflows before scaling.
Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A central risk is an evaluation illusion: fluent and well-structured explanations can appear clinically convincing even when the final diagnosis is incorrect. We introduce CLExEval, a human-in-the-loop framework for evaluating LLM clinical reasoning under progressive information masking. CLExEval combines 5,600 expert-physician annotations with 200 clinical reasoning traces derived from 40 rare diagnostic cases. Our analysis identifies three recurring failure patterns: (i) verbosity bias, where GPT-4o-mini's diagnostic accuracy drops from 95.0% to 32.5% under information scarcity; (ii) a hidden knowledge paradox, where a specialist model reaches 92.5% maximum diagnostic potential but fails to retrieve that knowledge reliably in verbose contexts; and (iii) a 68.6% reasoning-to-output mismatch, where correct diagnoses appear in reasoning traces but are not reflected in final answers. We further evaluate the LLM-as-a-Judge paradigm on a human-verified failure set (n = 142). GPT-4o-mini approved 47.9% of clinically incorrect outputs, while HuatuoGPT-o1 approved all validly scored failures and showed a positive self-preference bias. These results suggest that standalone automated clinical evaluations can substantially overestimate clinical reliability without expert-grounded validation.
Abin Roy, Afthab Salam Kanniyan, Jawadh Abdul Kabeer et al.· arXiv.org· 0 citations
Clinical reasoning and differential diagnosis are core competencies in medicine. Large language models (LLMs) have generated considerable interest as potential tools to support these skills. This article presents a narrative review of the available evidence, organized around five key questions: the effect of LLMs on diagnostic reasoning, the optimal design of clinician-LLM interaction, the appropriate timing of consultation during the clinical encounter, the safest models of clinical-AI integration, and the main risks associated with their use. The evidence shows that LLMs improve differential diagnosis when used by trained professionals within structured workflows. However, passive use generates biases, and clinician-AI collaboration may not consistently outperform autonomous LLMs. A practical framework stratified by degree of diagnostic uncertainty is proposed, with operational and educational recommendations oriented toward "physician-in-the-loop" models, in which LLMs amplify, challenge, and make explicit the diagnostic reasoning process under critical human oversight.
L. Corral-Gudino, M. Ramos-Casals, Miguel Marcos et al.· Medicina clínica (Ed. impres...· 0 citations
Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete information. In contrast, real-world clinical intelligence is inherently an iterative investigative process requiring strategic evidence acquisition. To bridge this gap, we formalize medical diagnosis as an Iterative Evidence-Seeking Task. We leverage Reinforcement Learning with Verifiable Rewards (RLVR) to elicit intrinsic reasoning within a closed-loop environment, guided by a novel suite of rewards that enforce diagnostic precision and examination consistency. To facilitate this, we introduce the Retrieval-Augmented Generation-based Examination Simulator (RAGES), a high-fidelity clinical oracle that provides realistic, knowledge-grounded follow-up evidence. Empirical results across diverse datasets demonstrate that our framework enables LLMs to transition from passive responders to autonomous assistants. Notably, our model demonstrates comparable performance to larger and reasoning-enhanced baselines, while RAGES proves superior to vanilla LLMs in generating biologically plausible clinical feedback.
Shengyi Hua, Kangzhe Hu, Conghui He et al.· 1 citation
A dual-view approach that connects clinical practice with computational methods is presented, establishing a five-level competency scheme following Miller’s Pyramid and linking deductive, inductive, and abductive reasoning patterns to common medical goals and tasks.