Can Artificial Intelligence Take Place of Physical Medicine and Rehabilitation Physicians?: ChatGPT Versus Physical Medicine and Rehabilitation Residents
Trial Snapshot
- Phase
- Not Applicable
- Status
- Completed
- Sponsor
- Enrollment
- 314
- Locations
- 1
- Primary Endpoint
- The comparison of resident exam results and ChatGPT answers to the same questions
Study Overview
Brief Summary
The aim of this study was to assess the performance of ChatGPT on examinations administered to physical medicine and rehabilitation (PMR) residents.
Detailed Description
These exams for resident physicians are annual exams administered throughout the training period, which constitute a fundamental component of the training process towards becoming a PMR physician. In this study, we evaluated the performance of ChatGPT in these exams, made separate assessments for each training year, and compared the results of ChatGPT with the results of residents who passed the same exam.
Study Design
- Study Type
- Observational
- Observational Model
- Other
- Time Perspective
- Cross Sectional
Eligibility Criteria
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Physical medicine and rehabilitation residents exam results in May 2024
Exclusion Criteria
- Not provided
Outcomes
Primary Outcomes
The comparison of resident exam results and ChatGPT answers to the same questions
Time Frame: through study completion, an average of 10 days
In May 2024, the exam results of residents in training and research hospitals affiliated with the Health Sciences University across Türkiye will be compared with the answers and rankings given by ChatGPT to the same questions. ChatGPT accuracy rate and response time to questions will be determined. The minimum score to be obtained from this exam is 0 and the maximum score is 100.
Secondary Outcomes
No secondary outcomes reported
Investigators
Selda Çiftci
Medical Doctor, Physiatrist
Sisli Hamidiye Etfal Training and Research Hospital