Hao Jie, Yao Zixuan, Tang Yaogeng, Remis Andréas, Wu Kangchao, Yu Xin
Department of Physical Therapy and Rehabilitation, Southeast Colorado Hospital, Springfield, CO, 81073, USA.
Global Health Opportunities Program, University of Nebraska Medical Center, Omaha, NE, USA.
Ann Biomed Eng. 2025 Jan;53(1):9-13. doi: 10.1007/s10439-025-03676-4. Epub 2025 Jan 6.
The integration of artificial intelligence into medicine has attracted increasing attention in recent years. ChatGPT has emerged as a promising tool for delivering evidence-based recommendations in various clinical domains. However, the application of ChatGPT to physical therapy for musculoskeletal conditions has yet to be investigated.
Thirty clinical questions related to spinal, lower extremity, and upper extremity conditions were quired to ChatGPT-4. Responses were assessed for accuracy against clinical practice guidelines by two reviewers. Intra- and inter-rater reliability were measured using Fleiss' kappa (k).
ChatGPT's responses were consistent with CPG recommendations for 80% of the questions. Performance was highest for upper extremity conditions (100%) and lowest for spinal conditions (60%), with a moderate performance for lower extremity conditions (87%). Intra-rater reliability was good (k = 0.698 and k = 0.631 for the two reviewers), and inter-rater reliability was very good (k = 0.847).
ChatGPT demonstrates promise as a supplementary decision-making support tool for physical therapy, with good accuracy and reliability in aligning with clinical practice guideline recommendations. Further research is needed to evaluate its performance across broader scenarios and refine its clinical applicability.
近年来，人工智能在医学领域的整合受到了越来越多的关注。ChatGPT已成为在各个临床领域提供循证建议的有前景的工具。然而，ChatGPT在肌肉骨骼疾病物理治疗中的应用尚未得到研究。
向ChatGPT-4提出了30个与脊柱、下肢和上肢疾病相关的临床问题。两位评审员根据临床实践指南评估回答的准确性。使用Fleiss' kappa（κ）测量评分者内和评分者间的可靠性。
ChatGPT的回答与CPG对80%的问题的建议一致。上肢疾病的表现最高（100%），脊柱疾病的表现最低（60%），下肢疾病的表现中等（87%）。评分者内可靠性良好（两位评审员的κ分别为0.698和0.631），评分者间可靠性非常好（κ = 0.847）。
ChatGPT作为物理治疗的辅助决策支持工具显示出前景，在与临床实践指南建议保持一致方面具有良好的准确性和可靠性。需要进一步研究以评估其在更广泛场景中的表现并完善其临床适用性。
