Clinical Reasoning

ImportanceLarge language models (LLMs) have shown promise in their performance on both multiple-choice and open-ended medical reasoning examinations, but it remains unknown whether the use of such tools improves physician diagnostic reasoning.ObjectiveTo assess the effect of an LLM on physicians' diagnostic reasoning compared with conventional resources.Design, setting, and participantsA single-blind randomized clinical trial was conducted from November 29 to December 29, 2023. Using remote video conferencing and in-person participation across multiple academic medical institutions, physicians with training in family medicine, internal medicine, or emergency medicine were recruited.InterventionParticipants were randomized to either access the LLM in addition to conventional diagnostic resources or conventional resources only, stratified by career stage. Participants were allocated 60 minutes to review up to 6 clinical vignettes.Main outcomes and measuresThe primary outcome was performance on a standardized rubric of diagnostic performance based on differential diagnosis accuracy, appropriateness of supporting and opposing factors, and next diagnostic evaluation steps, validated and graded via blinded expert consensus. Secondary outcomes included time spent per case (in seconds) and final diagnosis accuracy. All analyses followed the intention-to-treat principle. A secondary exploratory analysis evaluated the standalone performance of the LLM by comparing the primary outcomes between the LLM alone group and the conventional resource group.ResultsFifty physicians (26 attendings, 24 residents; median years in practice, 3 [IQR, 2-8]) participated virtually as well as at 1 in-person site. The median diagnostic reasoning score per case was 76% (IQR, 66%-87%) for the LLM group and 74% (IQR, 63%-84%) for the conventional resources-only group, with an adjusted difference of 2 percentage points (95% CI, -4 to 8 percentage points; P = .60). The median time spent per case for the LLM group was 519 (IQR, 371-668) seconds, compared with 565 (IQR, 456-788) seconds for the conventional resources group, with a time difference of -82 (95% CI, -195 to 31; P = .20) seconds. The LLM alone scored 16 percentage points (95% CI, 2-30 percentage points; P = .03) higher than the conventional resources group.Conclusions and relevanceIn this trial, the availability of an LLM to physicians as a diagnostic aid did not significantly improve clinical reasoning compared with conventional resources. The LLM alone demonstrated higher performance than both physician groups, indicating the need for technology and workforce development to realize the potential of physician-artificial intelligence collaboration in clinical practice.Trial registrationClinicalTrials.gov Identifier: NCT06157944.

Lymph nodes (LNs) are important hubs for metastatic cell arrest and growth, immune modulation, and secondary dissemination to distant sites through a series of mechanisms, and it has been proved that lymph node metastasis (LNM) is an essential prognostic indicator in many different types of cancer. Therefore, it is important for oncologists to understand the mechanisms of tumor cells to metastasize to LNs, as well as how LNM affects the prognosis and therapy of patients with cancer in order to provide patients with accurate disease assessment and effective treatment strategies. In recent years, with the updates in both basic and clinical studies on LNM and the application of advanced medical technologies, much progress has been made in the understanding of the mechanisms of LNM and the strategies for diagnosis and treatment of LNM. In this review, current knowledge of the anatomical and physiological characteristics of LNs, as well as the molecular mechanisms of LNM, are described. The clinical significance of LNM in different anatomical sites is summarized, including the roles of LNM playing in staging, prognostic prediction, and treatment selection for patients with various types of cancers. And the novel exploration and academic disputes of strategies for recognition, diagnosis, and therapeutic interventions of metastatic LNs are also discussed.

BackgroundIn recent years, the significance of the nervous system in the tumor microenvironment has gained increasing attention. The bidirectional communication between nerves and cancer cells plays a critical role in tumor initiation and progression. Perineural invasion (PNI) occurs when tumor cells invade the nerve sheath and/or encircle more than 33% of the nerve circumference. PNI is a common feature in various malignancies and is associated with tumor invasion, metastasis, cancer-related pain, and unfavorable clinical outcomes. The colon and rectum are highly innervated organs, and accumulating studies support PNI as a histopathologic feature of colorectal cancer (CRC). Therefore, it is essential to investigate the role of nerves in CRC and comprehend the mechanisms of PNI to impede tumor progression and improve patient survival.ConclusionThis review elucidates the clinical significance of PNI, summarizes the underlying cellular and molecular mechanisms, introduces various experimental models suitable for studying PNI, and discusses the therapeutic potential of targeting this phenomenon. By delving into the intricate interactions between nerves and tumor cells, we hope this review can provide valuable insights for the future development of CRC treatments.

ImportanceLarge language models (LLMs) are increasingly marketed for clinical use, yet their ability to replicate full-spectrum clinical reasoning remains uncertain. Existing evaluations often rely on multiple-choice examinations that do not reflect the complexity of patient care.ObjectivesTo evaluate the longitudinal clinical reasoning ability of state-of-the-art LLMs and to introduce a multidimensional, clinically meaningful benchmark for clinical-grade artificial intelligence (AI).Design, setting, and participantsIn this cross-sectional study, performance was evaluated using standardized clinical vignettes from the January 2025 update of MSD Manual vignettes. A total of 21 off-the-shelf LLMs, including recently released GPT-5, Claude 4.5 Opus, Gemini 3.0 Flash and Pro, and Grok 4, were evaluated. Models were assessed by medical student scorers in triplicate across sequential stages of the standard clinical workflow. Analyses were performed from January to December 2025.Main outcomes and measuresThe primary outcome was the Proportional Index of Medical Evaluation for LLMs (PrIME-LLM) score, defined as the normalized polygonal area representing balanced accuracy across 5 domains of clinical reasoning as follows: differential diagnosis, diagnostic testing, final diagnosis, management, and miscellaneous clinical reasoning questions. Analyses including analyses of variance, t tests, and regression models were used to compare AI model performance and demographic associations.ResultsLLMs were tested across 29 clinical vignettes (representing 16 254 responses in total). PrIME-LLM scores ranged from 0.64 (range, 0.63-0.65) (Gemini 1.5 Flash) to 0.78 (range, 0.77-0.79) (Grok 4), with reasoning-optimized models outperforming nonreasoning models and GPT models scoring highest overall. Differential diagnosis was less accurate than diagnostic testing, while final diagnosis, management, and miscellaneous reasoning were more accurate. Failure rates exceeded 0.80 (range, 0.90-1.00) for differential diagnosis in all models but were less than 0.40 (range, 0.09-0.39) for final diagnosis. Multimodal performance was robust; most LLM models showed improved accuracy with image inputs.Conclusions and relevanceIn this cross-sectional study of 21 LLMs, frontier LLMs achieved high accuracy on final diagnoses but performed poorly in generating differential diagnoses and navigating uncertainty relative to other reasoning stages. The PrIME-LLM framework provided greater separation than raw accuracy, revealing critical reasoning gaps obscured by traditional benchmarks. Thus, despite version-based improvements and advantages in reasoning-optimized models, off-the-shelf LLMs have not yet achieved the intelligence required for safe deployment and remain limited in demonstrating advanced clinical reasoning.