| CAN AI-GENERATED EXERCISE PRESCRIPTIONS BE CONSIDERED VALID FOR GENERAL HEALTH? |
| Paper ID : 1004-SPORTCONGRESS (R1) |
| Authors |
|
Ebrahim Ebrahimi *1, Rahman Sheikhhoseini2, Rasoul Eslami3, Hashem Piri2 1Department of Sport Injuries and Biomechanics, Faculty of Sport Sciences and Health, University of Tehran, Tehran, Iran 2Department of Corrective Exercise & Sport Injury, Faculty of Physical Education and Sport Sciences, Allameh Tabataba'i University, Tehran, Iran 3Department of Exercise Physiology, Faculty of Physical Education and Sport Sciences, Allameh Tabataba'i University, Tehran, Iran |
| Abstract |
| Introduction: The increasing use of artificial intelligence (AI) in healthcare is opening new avenues for personalized health solutions. In sports, AI is driving large-scale personalization and enhancing the effectiveness of individualized protocols. Although AI can design training programs, the evidence supporting the validity of these AI-generated exercise prescriptions is still limited. Accordingly, this study seeks to examine the validity of AI-prescribed exercise programs for the improvement of general health. Methods: This study involved developing an AI-generated exercise program, utilizing the Delphi method. The Delphi process consists of administering a questionnaire within a specific domain, where a panel of experts assesses the program’s suitability. Three methods were used to determine validity: Content Validity Ratio (CVR), Content Validity Index (CVI), and Impact Score (IS). The Fleiss Kappa coefficient (g) was calculated to assess the degree of agreement (reliability) between the experts’ responses. Data analysis was performed using SPSS version 27 and Microsoft Excel version 2024. Results: The IS results indicate that all exercises met the required validity level for weight loss. Although most exercises showed acceptable content validity, the negative kappa value reflects poor agreement among experts. Conclusion: Our findings indicate that, although ChatGPT-4o can generate largely appropriate content, it does not fully align with expert consensus. Therefore, AI should be considered a supportive adjunct for general health guidance under professional supervision, rather than a standalone tool. |
| Keywords |
| Artificial Intelligence, Validity, Health |
| Status: Abstract Accepted (Poster Presentation) |
