ARTIFICIAL INTELLIGENCE-DRIVEN PRECISION SPORTS REHABILITATION: INTEGRATING WEARABLE SENSORS, BIOMECHANICAL ANALYSIS, AND DIGITAL HEALTH TECHNOLOGIES FOR INJURY PREVENTION AND RETURN-TO-PLAY OPTIMIZATION
Keywords:
Artificial intelligence; precision rehabilitation; wearable sensors; biomechanical analysis; return-to-play; digital health; sports injury; tele-rehabilitation; ACL reconstruction; ankle sprainAbstract
Background: Traditional sports rehabilitation relies on subjective, time-based protocols that often increase re-injury risks, while clinical evidence for AI-driven precision alternatives remains limited.
Objective: To evaluate the efficacy of an AI-driven rehabilitation protocol, utilizing wearable sensors and tele-rehabilitation, against conventional physiotherapy for athletes recovering from ACL reconstructions or Grade II ankle sprains.
Methods: A prospective, single-blind, randomized controlled trial was conducted at the National Institute of Sports Medicine (NISM), Islamabad, Pakistan (January–December 2025). A total of 110 athletes (aged 18–35 years) were randomized (1:1) into an intervention group (n = 55) receiving AI-driven precision rehabilitation and a control group (n = 55) receiving standard care. Primary outcomes were time to return-to-play (RTP) and re-injury rate at six months. Secondary outcomes included Limb Symmetry Index (LSI), final IKDC/FAAM scores, and rehabilitation adherence. Data were analyzed using log-rank tests, independent t-tests, chi-square tests, and multiple linear regression.
Results: The intervention group demonstrated significantly faster RTP (18.2 ± 2.8 vs. 22.5 ± 3.1 weeks; p < .001; Cohen's d = 1.45), a lower re-injury rate (8.3% vs. 21.6%; p = .028), superior LSI (94.2% vs. 86.5%; p < .001; d = 1.72), higher final IKDC/FAAM scores (91.4 vs. 85.1; p = .003; d = 1.18), and markedly greater rehabilitation adherence (88.5% vs. 62.0%; p < .001; d = 2.21). Multiple regression confirmed that group assignment (β = −.42; p < .001) and adherence rate (β = −.31; p = .001) were the strongest independent predictors of RTP time.
Conclusion: AI-driven precision sports rehabilitation significantly accelerates return-to-play, reduces re-injury risk, enhances functional recovery, and improves rehabilitation adherence compared to conventional physiotherapy. These findings support the integration of wearable sensors, AI analytics, and digital health platforms into standard sports rehabilitation practice to enable objective, individualized, and data-driven recovery management.
