Use of artificial intelligence chatbots in clinical management of immune-related adverse events

BackgroundArtificial intelligence (AI) chatbots have become a major source of general and medical information, though their accuracy and completeness are still being assessed. Their utility to answer questions surrounding immune-related adverse events (irAEs), common and potentially dangerous toxici...

Full description

Saved in:
Bibliographic Details
Published in:Journal for immunotherapy of cancer 2024-05, Vol.12 (5), p.e008599
Main Authors: Burnette, Hannah, Pabani, Aliyah, von Itzstein, Mitchell S, Switzer, Benjamin, Fan, Run, Ye, Fei, Puzanov, Igor, Naidoo, Jarushka, Ascierto, Paolo A, Gerber, David E, Ernstoff, Marc S, Johnson, Douglas B
Format: Article
Language:English
Subjects:
Accuracy
Artificial Intelligence
Chatbots
Clinical/translational cancer immunotherapy
Colitis
Drug-Related Side Effects and Adverse Reactions
Humans
Immune Checkpoint Inhibitor
Immune related adverse event - irAE
Immunotherapy - adverse effects
Immunotherapy - methods
Likert scale
Neoplasms - drug therapy
Neoplasms - immunology
Pneumonitis
Thyroid gland
Thyroiditis
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:BackgroundArtificial intelligence (AI) chatbots have become a major source of general and medical information, though their accuracy and completeness are still being assessed. Their utility to answer questions surrounding immune-related adverse events (irAEs), common and potentially dangerous toxicities from cancer immunotherapy, are not well defined.MethodsWe developed 50 distinct questions with answers in available guidelines surrounding 10 irAE categories and queried two AI chatbots (ChatGPT and Bard), along with an additional 20 patient-specific scenarios. Experts in irAE management scored answers for accuracy and completion using a Likert scale ranging from 1 (least accurate/complete) to 4 (most accurate/complete). Answers across categories and across engines were compared.ResultsOverall, both engines scored highly for accuracy (mean scores for ChatGPT and Bard were 3.87 vs 3.5, p
ISSN:2051-1426
2051-1426
DOI:10.1136/jitc-2023-008599