Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 13, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Patient Cognitive Bias in Large Language Model-Supported Health Consultations: Simulation-Based Comparative Study.

Yi Zuo1, Qifeng Wan2, Shalong Wang3

  • 1School of Computer Science and Artificial Intelligence, Hunan University of Finance and Economics, Changsha, Hunan, China.

Journal of Medical Internet Research
|June 11, 2026
PubMed
Summary

Related Concept Videos

Language and Cognition01:27

Language and Cognition

Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Evaluating real-time voice AI-based virtual patients for authentic communication training.

Medical teacher·2026
Same author

Enhancing self-directed learning with custom GPT AI facilitation among medical students: A randomized controlled trial.

Medical teacher·2024
Same author

Ginsenoside Rg3 Ameliorates DSS-Induced Colitis by Inhibiting NLRP3 Inflammasome Activation and Regulating Microbial Homeostasis.

Journal of agricultural and food chemistry·2023
Same journal

Attitudes and Needs of Health Care Providers Toward Artificial Intelligence-Assisted Pediatric Palliative Care: Mixed Methods Study.

Journal of medical Internet research·2026
Same journal

Value and Credibility of Meta-Analysis: Tutorial on Enhancing Methodological Rigor and AI-Powered Efficiency.

Journal of medical Internet research·2026
Same journal

Extracting Medical Information From Unstructured Clinical Text Using Large Language Models to Enhance Health Care Interoperability: Proof-of-Concept Study.

Journal of medical Internet research·2026
Same journal

How Does That Large Language Model Make You Feel?

Journal of medical Internet research·2026
Same journal

Transformation Versus Innovation in Digital Health Care and the Future of Clinical AI.

Journal of medical Internet research·2026
Same journal

Building a Malaria Intelligence System for Real-Time Prediction and Data-Driven Intervention Planning.

Journal of medical Internet research·2026
See all related articles
This summary is machine-generated.

Patient cognitive bias significantly reduces diagnostic accuracy in large language models (LLMs) during health consultations. A dual-system framework, separating interaction from reasoning, offers a robust solution to improve LLM diagnostic performance under biased input.

Area of Science:

  • Artificial Intelligence in Medicine
  • Natural Language Processing
  • Clinical Decision Support

Background:

  • Large language models (LLMs) are increasingly utilized by patients for health information and preliminary medical advice.
  • Patient input in LLM consultations can be cognitively biased, emphasizing preferred diagnoses or explanations.
  • This bias can constrain the diagnostic context and steer LLM reasoning in health consultations.

Purpose of the Study:

  • To quantify the impact of patient cognitive bias on LLM diagnostic performance in multiturn consultations.
  • To assess the effectiveness of prompt-based mitigation and decoding temperature adjustments.
  • To evaluate a dual-system framework for enhancing LLM robustness against biased interactions.

Main Methods:

  • A simulated patient agent generated unbiased and biased consultations using US Medical Licensing Examination cases.
Keywords:
artificial intelligenceclinical consultationcognitive biashealth information seekinghuman-AI interactionlarge language models

Related Experiment Videos

Last Updated: Jun 13, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

  • Six LLMs were evaluated in 3-round dialogues, assessing diagnostic accuracy.
  • Prompt strategies, decoding temperatures, and a dual-system framework (conversational LLM + reasoning LLM) were tested.

    • Main Results:

    • Cognitive bias reduced diagnostic accuracy by 7-39 percentage points across models, particularly impacting lower-capacity LLMs.
    • Prompt strategies and temperature adjustments showed limited effectiveness in mitigating bias.
    • The dual-system framework significantly improved accuracy under bias (10-39 percentage points), recovering performance lost to bias.

    Conclusions:

    • Patient cognitive bias poses a significant risk in LLM-supported health consultations.
    • Standard mitigation techniques offer limited resilience against bias.
    • A dual-system framework separating interaction and reasoning enhances diagnostic robustness and offers a scalable design for safer medical AI.