Comparing Physician and Artificial Intelligence Chatbot Responses to Frequently Asked Questions From Osteoarthritis Patients

Comparing Physician and Artificial Intelligence Chatbot Responses to Frequently Asked Questions From Osteoarthritis Patients: a Prospective Cross-sectional Study

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT07202286

Acronym

PARTICIPATE

Enrollment

286

Registered

2025-10-01

Start date

2024-05-22

Completion date

2024-06-05

Last updated

2025-10-06

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Acceptability, Accuracy, Artificial Intelligence (AI), Chatbot, Osteo Arthritis Knee and Hip

Keywords

chatGPT, Osteoarthritis, Acceptability, Accuracy, Artificial Intelligence, Cross-sectional

Brief summary

This study aimed to compare the patient acceptability (preference, length, and difficulty) and accuracy of Chat-Generative Pre-Trained Transformer (ChatGPT) responses to questions from people with osteoarthritis (OA) with physician responses.

Detailed description

This was a cross-sectional study where participants were invited by e-mail to participate in the questionnaire to compare Chatbot responses to physician responses.

Interventions

None listed

Study design

Observational model

OTHER

Time perspective

CROSS_SECTIONAL

Eligibility

Sex/Gender

ALL

Healthy volunteers

Inclusion criteria

* all individuals visiting the Department of Orthopedics in the Canisius Wilhelmina Hospital, a district general hospital in Nijmegen, The Netherlands, diagnosed with knee or hip OA between March 2023 and March 2024

Exclusion criteria

* partly completion of the questionnaire

Design outcomes

Primary

Measure	Time frame	Description
Preferred response	From invitation until the end of the study at two weeks	Binary outcome, chatbot or physician response. This was an average based on the preferences on the 7 FAQs.

Secondary

Measure	Time frame	Description
Rating of length	From invitation until the end of the study at two weeks	Rating of both responses (chatbot and physician response) included 'too short', 'good', and 'too long'.
Rating of difficulty	From invitation until the end of the study at two weeks	Rating of difficulty included 'too easy', 'good', and 'too difficult' for both responses.
Accuracy	From invitation until the end of the study at two weeks	Accuracy of the responses included the options 'Completely incorrect,' 'partly incorrect, ' 'approximately equally correct and incorrect,' 'mostly correct,' 'completely correct'.

Other

Measure	Time frame
Number of words of the responses	This was determined before the study started

Countries

Netherlands

Outcome results