Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

Abstract Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care. This survey examines recent progress in medical LLMs, focusing on reasoning applications and requirements. We present a dual-view approach that connects clinical practice with computational methods. On the clinical side, we establish a five-level competency scheme following Miller’s Pyramid, progressing from knowledge recall to dynamic case management. On the computational side, we link deductive, inductive, and abductive reasoning patterns to common medical goals and tasks. We also introduce a benchmark dataset spanning five levels of medical reasoning capability and report results on 18 state-of-the-art models, revealing that medical specialist models excel in diagnosis-centric tasks while general models lead in decision support and dialogue. We conclude by discussing current progress and open challenges, including data limitations, hallucination, and grounding issues, and outline directions toward safer, more reliable, and more workflow-ready systems.

Authors

Institutions

Publication Details

Journal
Machine Intelligence Research
Published
2026-07-31
DOI
https://doi.org/10.1007/s11633-026-1659-4
Citations
1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

Xiaoyong Wei, Kecheng Gong, J. C. Li, Xiao-Yong Wei et al.
1 citations
Machine Intelligence Research
Artificial Intelligence in Healthcare and Education
article

Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

Xiaoyong Wei, Kecheng Gong, J. C. Li, Xiao-Yong Wei, Qi Peng, Sirui Huang, Changmeng Zheng, Shijie Ye, Qing Li, Qing Li, Xiaobo Yang, Ran Ding, Yiyang Jiang, Yiyang Jiang, Kaisong Gong, Jin Huang, Ronger Ding, Yi Cai
article en
1 citations

Abstract

Abstract Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care. This survey examines recent progress in medical LLMs, focusing on reasoning applications and requirements. We present a dual-view approach that connects clinical practice with computational methods. On the clinical side, we establish a five-level competency scheme following Miller’s Pyramid, progressing from knowledge recall to dynamic case management. On the computational side, we link deductive, inductive, and abductive reasoning patterns to common medical goals and tasks. We also introduce a benchmark dataset spanning five levels of medical reasoning capability and report results on 18 state-of-the-art models, revealing that medical specialist models excel in diagnosis-centric tasks while general models lead in decision support and dialogue. We conclude by discussing current progress and open challenges, including data limitations, hallucination, and grounding issues, and outline directions toward safer, more reliable, and more workflow-ready systems.

Machine Intelligence Research
Hong Kong Polytechnic University (HK), University of Toronto (CA), Chinese Academy of Medical Sciences & Peking Union Medical College (CN), Sichuan University (CN), Peking Union Medical College Hospital (CN), West China Hospital of Sichuan University (CN), University of Hong Kong (HK), South China University of Technology (CN)
Commonwealth Scientific and Industrial Research Organisation, National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, Hunan University, Hong Kong Polytechnic University, Zhejiang University, Sichuan University, South China University of Technology, Wuhan University, University of Science and Technology of China, Fundamental Research Funds for the Central Universities, Science and Technology Planning Project of Guangdong Province, West China Hospital, Sichuan University
Openalex Percentile: Top 100%
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.