DefinePK

Abstract

Background: Artificial intelligence (AI) is increasingly being integrated into rehabilitation medicine, particularly in gait analysis for individuals with mobility impairments. Conventional gait assessments often rely on subjective evaluation or limited sensor technologies, which may lack precision and adaptability. Although various AI-based tools have emerged, the clinical relevance and effectiveness of these technologies in improving rehabilitation outcomes remain inadequately consolidated in existing literature.
Objective: This systematic review aims to evaluate the effectiveness of AI-assisted gait analysis tools in physical therapy, focusing on their impact on treatment planning, functional recovery, and overall rehabilitation outcomes.
Methods: A systematic review was conducted according to PRISMA guidelines. Four electronic databases—PubMed, Scopus, Web of Science, and Cochrane Library—were searched for studies published between 2020 and 2024. Eligible studies included randomized controlled trials, cohort studies, and observational designs involving patients undergoing physical therapy for gait dysfunction, utilizing AI-based gait analysis tools. Data extraction and risk of bias assessment were performed independently by two reviewers using standardized forms and validated tools such as the Cochrane Risk of Bias Tool and Newcastle-Ottawa Scale.
Results: Eight studies met inclusion criteria, encompassing 644 participants with conditions including stroke, Parkinson’s disease, and orthopedic impairments. AI technologies included wearable sensors, robotic trainers, and vision-based tracking systems. Most studies reported significant improvements in gait parameters such as cadence, stride length, and walking distance (p < 0.05), as well as better adherence and therapy personalization. Risk of bias was generally low to moderate, with some concerns related to performance blinding.
Conclusion: AI-assisted gait analysis tools show promising clinical value in enhancing rehabilitation outcomes and supporting individualized therapy planning. While current evidence is encouraging, further large-scale and methodologically rigorous studies are needed to validate these findings and guide broader implementation.