The validity and reliability of a real-time AI-based neck exercise program among young adults in Thailand: evaluation...

Neck pain caused by weakened muscles and decreased strength may be alleviated with exercise. Integrating digital technology, such as artificial intelligence (AI), into neck exercise programs may improve their accuracy and effectiveness. This study aims to evaluate the validity and reliability of an AI-based neck exercise program to measure accuracy and execution time. The method included evaluating the validity and reliability of a real-time AI neck exercise program among 30 healthy participants aged 18-29 years, across five exercises. In the results, the outcome variables included the content validity index (IOC) for exercise accuracy and execution time. Reliability was evaluated using the intraclass correlation coefficient (ICC), and associations between variables were analyzed using Pearson's correlation coefficient. The content validity assessment indicated high validity of the AI-based neck exercise program, with IOC values between 0.86 and 1.00 across all exercises. Moderate reliability was observed for exercise accuracy (ICC = 0.63) and execution time (ICC = 0.622). Higher exercise accuracy was associated with shorter execution time; however, this relationship should be interpreted with caution, as it does not imply causality.