Simulated evaluation of large language model stepwise diagnostic reasoning with real-world chest pain encounters and Bayesian networks

Abstract Background Real-world evaluation of large language models (LLMs) as clinical diagnostic aids is limited by the reliance on static vignettes and retrospective data, which inadequately reflect the dynamic, iterative nature of clinical decision-making and may overestimate LLMs’ performance. He...

Descrición completa

Detalles Bibliográficos

Principais autores:	Conrad W. Safranek, Vimig Socrates, Donald Wright, Thomas Huang, Alaa Alashi, Kent McCann, R. Andrew Taylor, David Chartash
Formato:	Artigo
Idioma:	Inglês
Publicado:	BMC 2026-02-01
Series:	BMC Medical Informatics and Decision Making
Assuntos:	Large Language Models (LLMs) Artificial intelligence Bayesian networks Non-traumatic chest pain Emergency department diagnostics Diagnostic decision-making
Acceso en liña:	https://doi.org/10.1186/s12911-026-03381-9
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!