AI Article Synopsis

  • The study explores the use of AI chatbots, specifically ChatGPT-4, as a tool for personalized counseling for Autoimmune Hepatitis (AIH) patients, assessing their performance on twelve specific patient inquiries.
  • Key metrics evaluated include accuracy, completeness, comprehensiveness, and safety of the chatbot’s responses, rated by a group of 11 experts using various scales.
  • Results reveal that while the chatbot provides good comprehensive information, its reliability is questionable, especially in diagnosing inquiries, indicating a need for further research before integrating it into clinical settings.

Article Abstract

Introduction: Artificial intelligence-based chatbots offer a potential avenue for delivering personalized counseling to patients with autoimmune hepatitis. We assessed accuracy, completeness, comprehensiveness, and safety of Chat Generative Pretrained Transformer-4 responses to 12 inquiries out of a pool of 40 questions posed by 4 patients with autoimmune hepatitis.

Methods: Questions were categorized into 3 areas: diagnosis (1-3), quality of life (4-8), and medical treatment (9-12). 11 key opinion leaders evaluated responses using a Likert scale with 6 points for accuracy, 5 points for safety, and 3 points for completeness and comprehensiveness.

Results: Median scores for accuracy, completeness, comprehensiveness, and safety were 5 (4-6), 2 (2-2), and 3 (2-3), respectively; no domain exhibited superior evaluation. Postdiagnosis follow-up question was the trickiest with low accuracy and completeness, but safe and comprehensive features. Agreement among key opinion leaders (Fleiss Kappa statistics) was slight for the accuracy (0.05) but poor for the remaining features (-0.05, -0.06, and -0.02, respectively).

Discussion: Chatbots show good comprehensibility, but lack reliability. Further studies are needed to integrate Chat Generative Pretrained Transformer within clinical practice.

Download full-text PDF

Source
http://dx.doi.org/10.14309/ajg.0000000000003179DOI Listing

Publication Analysis

Top Keywords

accuracy completeness
12
patients autoimmune
8
completeness comprehensiveness
8
comprehensiveness safety
8
chat generative
8
generative pretrained
8
key opinion
8
opinion leaders
8
accuracy
5
chatgpt-4 reliable
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!