Large Language Models for Differential Diagnosis: A Survey of Performance, Collaboration, and Technical Strategies
AI Medicine · 2026
DOI: 10.53941/aim.2026.100007 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI Medicine, 2026. Verfasst von Yunjia Wu und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Errors in differential diagnosis often arise while clinicians are generating and comparing candidate explanations. This review examines the use of large language models (LLMs) for this part of diagnostic reasoning. Internal medicine and pediatrics are the main focus; evidence from radiology, surgical subspecialties, infectious disease, and mental health is used to examine how findings change across specialties. Reported performance depends on the clinical setting, the quality of the input, the prompt, model adaptation, and the evaluation design. Some studies place LLMs near trainees and find that they produce wider, better-organized differentials. Experienced clinicians, however, remain more reliable overall. Domain adaptation, external knowledge, and interactive workflows have improved performance in specific evaluations, but hallucinations and automation bias remain, alongside unresolved questions of governance. Current evidence therefore supports clinician-supervised use of artificial intelligence (AI) systems rather than autonomous diagnosis, pending prospective and specialty-specific evaluation.
Zitieren
APA
Wu, Y., Yan, Q., & Tian, D. (2026). Large Language Models for Differential Diagnosis: A Survey of Performance, Collaboration, and Technical Strategies. AI Medicine. https://doi.org/10.53941/aim.2026.100007
Vancouver
Wu Y, Yan Q, Tian D. Large Language Models for Differential Diagnosis: A Survey of Performance, Collaboration, and Technical Strategies. AI Medicine. 2026. doi:10.53941/aim.2026.100007
BibTeX
@article{Wu2026,
author = {Wu, Yunjia and Yan, Qi and Tian, Dingcheng},
title = {Large Language Models for Differential Diagnosis: A Survey of Performance, Collaboration, and Technical Strategies},
journal = {AI Medicine},
year = {2026},
doi = {10.53941/aim.2026.100007}
}
EUVIMED