Skip to main content
2024 AAPD Annual Meeting Main banner
Itinerary Planner Sponsored by Cheng Crowns
Information & Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Ticket Required
Ticket Required
Sold Out
Sold Out
Recorded Session
Recorded Session
Back
Rate ePoster
View ePoster

Other

381 - Pediatric Dentists’ Perspectives on Accuracy/Helpfulness of ChatGPT’s Oral Health Information

Saturday, May 25, 2024
10:00 AM – 10:10 AM EST
Location: Exhibit Hall (back left corner of the hall, space 137)

    Presenting Author(s)

  • Victoria C. Chang, DMD (she/her/hers)

    Post-Doctoral Pediatric Dentistry Resident
    University of Illinois at Chicago, Chicago IL
    University of Illinois Chicago
    Lititz, Pennsylvania, United States

    • Co-Author(s)

  • ND

    Nawal Dairi, BS

    University of Pennsylvania, Philadelphia, PA

    • Research Mentor(s)

  • David M. Avenetti, DDS, MSD, MPH (he/him/his)

    Associate Professor and Head, Department of Pediatric Dentistry
    University of Illinois at Chicago, Chicago IL
    University of Illinois Chicago, Dept. of Pediatric Dentistry
    Chicago, Illinois, United States

    • Program Director(s)

  • Brittaney J. Hill, DDS, MS, MPH

    Clinical Assistant Professor and Program Director, Department of Pediatric Dentistry
    University of Illinois at Chicago
    University of Illinois at Chicago
    Chicago, Illinois, United States

Abstract:

Purpose: Artificial intelligence (AI) is being utilized for various emerging applications in healthcare, including research, education, and diagnostics. Chatbots using a large language model, such as ChatGPT by OpenAI, have the potential to provide meaningful oral health information to patients and caregivers/parents. However, AI in healthcare comes with reported cautions, such as verifying the accuracy of ChatGPT-generated content. The aim of this pilot study was to assess pediatric dentists’ perceived accuracy and helpfulness of ChatGPT responses to common clinical questions. 


Methods: ChatGPT was queried for responses to 15 questions about access to care, prevention, treatment, emergencies, growth/development, dental materials, and safety. An electronic questionnaire was sent to program directors of CODA-approved pediatric dentistry residencies in January 2024. Questions included demographics, AI usage/familiarity, and the 15 ChatGPT-generated responses. Respondents rated the ‘accuracy’ and ‘helpfulness’ of each response. Descriptive and bivariate statistics were calculated with statistical significance set at α < 0.05.


Results: Preliminary data suggests that the familiarity and adoption of ChatGPT is highly variable among residency program directors. The accuracy of ChatGPT-generated content was rated as “both correct and comprehensive” for most items, and the helpfulness of information to patients was rated as “very” or “somewhat helpful” for most items. Data collection in progress; final results pending.


Conclusions: ChatGPT may have the potential to provide accurate and helpful pediatric oral health content to patients and caregivers. Whether responses are useful to all demographic and socioeconomic groups with varying health literacy and access to ChatGPT warrants further investigation.

Identify Supporting Agency and Grant Number: