Search research articles

Related Concept Videos

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Home
Comparing Large Language Models And Human Doctors In Symptom-driven Online Medical Consultations: A Case Study On Trigeminal Neuralgia.

Home
Comparing Large Language Models And Human Doctors In Symptom-driven Online Medical Consultations: A Case Study On Trigeminal Neuralgia.

Related Experiment Video

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Comparing large language models and human doctors in symptom-driven online medical consultations: A case study on

Liantan Duan¹, Zhong Yao^2,3,4, Xiaoyu Li¹

¹School of Management, Shandong University, Jinan, China.

|October 30, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Generative AI tools like Ernie Bot and ChatGPT show promise in enhancing online medical consultations, particularly in empathy and clarity. However, they require further refinement for clinical accuracy and complex cases.

Keywords:

Healthcare consultation large language models medical expertise patient experience response quality evaluation text features

More Related Videos

$Subcutaneous Trigeminal Nerve Field Stimulation for Refractory Facial Pain$

Subcutaneous Trigeminal Nerve Field Stimulation for Refractory Facial Pain

Published on: May 10, 2017

Microvascular Decompression: Salient Surgical Principles and Technical Nuances

Microvascular Decompression: Salient Surgical Principles and Technical Nuances

Published on: July 5, 2011

Related Experiment Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

$Subcutaneous Trigeminal Nerve Field Stimulation for Refractory Facial Pain$

Subcutaneous Trigeminal Nerve Field Stimulation for Refractory Facial Pain

Published on: May 10, 2017

Microvascular Decompression: Salient Surgical Principles and Technical Nuances

Microvascular Decompression: Salient Surgical Principles and Technical Nuances

Published on: July 5, 2011

Area of Science:

Medical Informatics
Artificial Intelligence in Healthcare
Digital Health

Background:

Online medical consultations face challenges in meeting healthcare demands.
Generative AI tools offer potential solutions for healthcare accessibility.

Purpose of the Study:

To evaluate Ernie Bot and ChatGPT performance in Chinese online medical consultations.
To assess AI's accuracy, safety, and empathy in healthcare.
To explore AI's role in bridging the healthcare supply-demand gap.

Main Methods:

Analysis of 233 trigeminal neuralgia consultations from a Chinese platform.
Comparison of AI-generated responses (ChatGPT-3.5, Ernie Bot) against doctor replies.
Evaluation by blinded raters (doctors, patients) using DISCERN and PEMAT.

Main Results:

Ernie Bot achieved the highest overall score, excelling in empathy and clarity.
AI tools demonstrated strengths in communication but showed factual errors.
Linguistic analysis revealed correlations between specific features and perceived response quality.

Conclusions:

AI tools show potential as adjuncts for non-urgent consultations, improving perceived empathy and clarity.
Limitations in clinical accuracy and high-risk decision-making necessitate further AI development.
Refinement is crucial for AI to meet precise and personalized healthcare standards.