Artificial Intelligence in Human Gait and Sports Biomechanics: A Review of Methods and Applications and Future Directions

Sports biomechanics and human gait are crucial for understanding movement disorders, optimizing athletic performance, and preventing injuries. Conventional biomechanical analysis relies on laboratory-based tools, such as force plates and optical motion capture systems, which are costly and limited to controlled settings. Biomechanical assessment is now portable and real-time thanks to recent developments in wearable sensors and artificial intelligence (AI). The sensing modalities and AI techniques used in gait and sports biomechanics over the past 20 years are compiled in this review. Support vector machines, convolutional neural networks, long short-term memory networks, and other deep learning and classical machine learning techniques are covered. Highlighted are important application areas, including sports performance optimization, rehabilitation monitoring, injury risk prediction, and gait classification. The issues include sensor placement, inter-subject variability, and data scarcity. The key applications of these techniques, including gait analysis, injury risk assessment, rehabilitation analysis, and sports performance optimization, are presented. In addition, key challenges, such as data availability, subject variation, sensor location problems, and lack of generalizability, are mentioned. The upcoming trends, including sensor-minimal systems, digital twins for biomechanics, and explainable AI are presented.