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

• URL: http://arxiv.org/abs/2603.10492v2
• Date: Wed, 18 Mar 2026 12:58:09 GMT
• Title: Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent
• Abstract summary: PULSE is a medical reasoning agent that combines a domain-tuned large language model with scientific literature retrieval.<n>In experiments, we compared PULSE's performance against physicians with varying levels of expertise.
• Score: 23.12438916515353
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning [66.94527468532843]
  We propose MultiDx, a two-stage diagnostic reasoning framework.<n>It first generates suspected diagnoses and reasoning paths by leveraging knowledge from web search, SOAP-formatted case, and clinical case database.<n>Then it integrates multi-perspective evidence through matching, voting, and differential diagnosis to generate the final prediction.
  arXiv  Detail & Related papers  (2026-04-27T08:46:29Z)
• MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus [24.19892707167392]
  Existing AI approaches for clinical diagnosis often lack transparency, structured reasoning, and deployability.<n>We propose MedCoRAG, an end-to-end framework that generates diagnostic hypotheses from standardized abnormal findings.<n>It then constructs a patient-specific evidence package by jointly retrieving and pruning UMLS knowledge graph paths and clinical guidelines.
  arXiv  Detail & Related papers  (2026-03-05T12:58:45Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• How to Evaluate Medical AI [4.23552814358972]
  We introduce Relative Precision and Recall of Algorithmic Diagnostics (RPAD and RRAD)<n>RPAD and RRAD compare AI outputs against multiple expert opinions rather than a single reference.<n>Large-scale study shows that top-performing models, such as DeepSeek-V3, achieve consistency on par with or exceeding expert consensus.
  arXiv  Detail & Related papers  (2025-09-15T14:01:22Z)
• End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning [52.12425911708585]
  Deep-DxSearch is an agentic RAG system trained end-to-end with reinforcement learning (RL)<n>In Deep-DxSearch, we first construct a large-scale medical retrieval corpus comprising patient records and reliable medical knowledge sources.<n> Experiments demonstrate that our end-to-end RL training framework consistently outperforms prompt-engineering and training-free RAG approaches.
  arXiv  Detail & Related papers  (2025-08-21T17:42:47Z)
• Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model [71.40113970879219]
  We propose a paradigm shift that reverses the relationship between physicians and AI.<n>We present DxDirector-7B, an LLM endowed with advanced deep thinking capabilities, enabling it to drive the full-process diagnosis with minimal physician involvement.<n>In evaluations across rare, complex, and real-world cases under full-process diagnosis setting, DxDirector-7B not only achieves significant superior diagnostic accuracy but also substantially reduces physician workload.
  arXiv  Detail & Related papers  (2025-08-14T09:51:20Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis [30.943705201552643]
  We propose a framework to model the diagnosis process in the real world by adaptively fusing probability distributions of agents over potential diseases. Our approach requires significantly less parameter updating and training time, enhancing efficiency and practical utility.
  arXiv  Detail & Related papers  (2024-01-29T12:25:30Z)
• Enabling Collaborative Clinical Diagnosis of Infectious Keratitis by Integrating Expert Knowledge and Interpretable Data-driven Intelligence [28.144658552047975]
  This study investigates the performance, interpretability, and clinical utility of knowledge-guided diagnosis model (KGDM) in the diagnosis of infectious keratitis (IK) The diagnostic odds ratios (DOR) of the interpreted AI-based biomarkers are effective, ranging from 3.011 to 35.233. The participants with collaboration achieved a performance exceeding that of both humans and AI.
  arXiv  Detail & Related papers  (2024-01-14T02:10:54Z)
• Towards Conversational Diagnostic AI [32.84876349808714]
  We introduce AMIE (Articulate Medical Intelligence Explorer), a Large Language Model (LLM) based AI system optimized for diagnostic dialogue. AMIE uses a self-play based simulated environment with automated feedback mechanisms for scaling learning across diverse disease conditions. AMIE demonstrated greater diagnostic accuracy and superior performance on 28 of 32 axes according to specialist physicians and 24 of 26 axes according to patient actors.
  arXiv  Detail & Related papers  (2024-01-11T04:25:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.