Menu
Back to AI and Diagnosis
06/11/26

Patient cognitive bias in large language model-supported health consultations: simulation-based comparative study.

Zuo, Yi; Wan, Qifeng; Wang, Shalong. J Med Internet Res.

Collection Topics
AI and Diagnosis Cognition and Decision Making
Share

Most recent

Frequency, Type, and Degree of Potential Harm of Adverse Safety Events among Pediatric Emergency Medical Services Encounters.

Cicero, Baird, Brown, et al., Prehosp Emerg Care.
09/11/26 Cognition and Decision Making Epidemiology

Emergency department revisit quality review screening: exploring human decision-making and artificial intelligence support.

Handler, Robles-Granda, Mefford, et al., arXiv
09/09/26 AI and Diagnosis Measurement, Monitoring, and Event Analysis

A five-phase evaluation framework for diagnostic and predictive medical artificial intelligence.

Ye, Chen, Huang, et al., NPJ Digit Med.
09/03/26 AI and Diagnosis

Summary

Patients using LLMs for diagnostic consultations may unintentionally bias the conversation based on how they phrase their questions. This study tests six systems to find that even small input biases can reduce diagnostic accuracy. Standard prompt rewording ("prompt-engineering") didn't improve response correctness, but pairing a conversational AI with a reasoning-focused one restored most lost accuracy. This two-part design offers a testable approach to make medical AI more reliable and sensitive to the biases humans can bring.
Read the paper
Zuo Y, Wan Q, Wang S. Patient cognitive bias in large language model-supported health consultations: simulation-based comparative study. J Med Internet Res. 2026;28:e85770.