Can Artificial Intelligence Take Place of Physical Medicine and Rehabilitation Physicians?: ChatGPT Versus Physical Medicine and Rehabilitation Residents
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- 入组人数
- 314
- 试验地点
- 1
- 主要终点
- The comparison of resident exam results and ChatGPT answers to the same questions
研究概览
简要总结
The aim of this study was to assess the performance of ChatGPT on examinations administered to physical medicine and rehabilitation (PMR) residents.
详细描述
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.
研究设计
- 研究类型
- Observational
- 观察模型
- Other
- 时间视角
- Cross Sectional
入排标准
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Physical medicine and rehabilitation residents exam results in May 2024
排除标准
- 未提供
结局指标
主要结局
The comparison of resident exam results and ChatGPT answers to the same questions
时间窗: 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.
次要结局
未报告次要终点
研究者
Selda Çiftci
Medical Doctor, Physiatrist
Sisli Hamidiye Etfal Training and Research Hospital