Determinants of Reader-LLM Interaction in Thoracic Radiology: Impact of Model Confidence and Reader Expertise

Radiology 2026

View at publisher
Authors: Jiyoung Song, Won Gi Jeong, Dae Hee Han, Hongseok Ko, Soon Ho Yoon, Hyungjin Kim, Phakhanith Naruetook, Wai Ling Leong, Sam Soo Kim, Hae Min Moon, Ji Yeong An, So Jung Koo
+3 more Meesun Lee, Eui Jin Hwang, Taehee Lee
DOI: 10.1148/radiol.253397
Cited by: 1
References: 19

Abstract

= .007) were protective, reducing acceptance of incorrect suggestions. Conclusion Successful reader-LLM collaboration is associated with model confidence and reader expertise, with rationale quality facilitating correct advice uptake but increasing overreliance on incorrect suggestions. © RSNA, 2026

Fields of Study & Subjects

Radiology practices and education Artificial Intelligence in Healthcare and Education Clinical Reasoning and Diagnostic Skills

Publication details

Journal / source
Radiology
Publisher
Radiological Society of North America (RSNA)
Volume
320
Issue
2
Pages
e253397–e253397
Publication date
1 August 2026
Language
EN