The Application of Artificial Intelligence in Analyzing Central and Peripheral Mechanisms in Gait Adaptation During Aging

Abstract

To investigate the role of artificial intelligence in analyzing central and peripheral mechanisms involved in gait adaptation among the elderly. This study employed a narrative review design using descriptive analysis. A systematic search was conducted across international databases from 2015 to 2025 to identify relevant studies on the use of AI in gait analysis in older adults. Extracted data were categorized based on data types (motion, neural, muscular, wearable) and the AI algorithms applied. The results indicate that AI algorithms have effectively identified abnormal gait patterns in older adults and modeled interactions between brain activity, muscle coordination, and joint dynamics. The use of multimodal data, such as EEG, EMG, fNIRS imaging, and wearable sensors, has enabled early prediction of pathological gait changes. Algorithms such as neural networks, Random Forest, and SVM demonstrated high performance in processing these datasets. Artificial intelligence, through its capacity to process complex data and detect hidden patterns, serves as a powerful tool in the analysis of gait mechanisms in aging. Despite challenges such as data quality dependency and interpretability issues, AI can play a vital role in early diagnosis, personalized rehabilitation planning, and enhancing mobility independence in older adults.