PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 27, 2023JAMA Otolaryngology–Head & Neck Surgery95 citationsOpen Access

Comparison Between ChatGPT and Google Search as Sources of Postoperative Patient Instructions

NANoel AyoubYLY.-J. LeeDGDavid R. Grimm

Key Result

ChatGPT-generated postoperative instructions scored lower in understandability (81% vs 91%) and actionability (73% vs 92%) compared to institution-specific instructions.

PICO

P
Population
Pediatric otolaryngologic procedures (n=24)
I
Intervention / Comparator
ChatGPT vs Google Search and Stanford University (institution)
O
Primary Outcome
Patient Education Materials Assessment Tool-printable (PEMAT-P) understandability score — η2 0.86 (0.67-1.00)

Main Result

Effect estimate: η2 0.86 (95% CI 0.67-1.00)

Absolute Event Rate: 81% vs 91%

Limitations

  • Only a few procedures and resources were analyzed
  • The analysis was performed only in English
  • ChatGPT limitations included lack of citations, inability to confirm accuracy, and a knowledge base with a 2021 endpoint

Abstract

This qualitative study rates the level of understandability, actionability, and procedure-specific content in postoperative instructions generated from ChatGPT, Google Search, and Stanford University.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ayoub et al. (2023) conducted a letter in Pediatric otolaryngologic procedures (n=24). ChatGPT vs. Google Search and Stanford University (institution) was evaluated on Patient Education Materials Assessment Tool-printable (PEMAT-P) understandability score (η2 0.86, 95% CI 0.67-1.00). ChatGPT-generated postoperative instructions scored lower in understandability (81% vs 91%) and actionability (73% vs 92%) compared to institution-specific instructions.

synapsesocial.com/papers/6a0ea66fe23c633afcf99aabhttps://doi.org/10.1001/jamaoto.2023.0704
Ask AI
Helpful
Bookmark
Share
View Full Paper