Integration of Genetic, Epigenetic and Artificial Intelligence-Based Biomarkers in Personalized Exercise Prescription
Abstract
Traditional population-based models, while foundational, inadequately capture the biological and functional heterogeneity that shapes rehabilitation outcomes. Advances in genetic and epigenetic research have revealed mechanistic pathways such as gene polymorphisms influencing muscle performance and exercise-induced DNA methylation or miRNA remodeling that underpin interindividual variability in adaptation and recovery. These molecular insights, when coupled with AI-driven analytics, enable dynamic, data-informed personalization of therapy. AI and machine learning enhance clinical prediction, real-time monitoring, and adaptive prescription through multimodal data integration from wearable sensors, imaging, and electronic health records. Such systems allow continuous calibration of exercise intensity, progression, and feedback, extending personalized care into tele-rehabilitation contexts while maintaining clinician oversight. Across orthopedic, neurological, and chronic pain domains, current evidence supports the translational feasibility of these approaches, though randomized genotype- or epigenotype-guided trials remain limited. Ethical implementation requires transparent governance, consent for genomic data use, and fairness-aware AI design to mitigate bias and protect patient autonomy. The literature consistently underscores AI as an adjunct, not a substitute for clinical expertise, reinforcing the centrality of human judgment in interpreting biomarker-informed recommendations. Moving forward, rigorously designed, ethically grounded trials are essential to validate whether biologically and digitally personalized rehabilitation improves outcomes beyond conventional protocols. Precision rehabilitation thus represents both a scientific and ethical frontier, uniting molecular insight, computational intelligence, and patient-centered care in the pursuit of more effective and equitable physical therapy.
Keywords
Precision Medicine , Physical Therapy Modalities , Genomics , Artificial Intelligence , Rehabilitation
Kaynakça
- 1- Shields RK, Dudley-Javoroski S. Epigenetics and the International Classification of Functioning, Disability and Health model: bridging nature, nurture, and patient-centered population health. Phys Ther. 2022; 102(1): pzab247.
- 2- Severin R, Sabbahi A, Arena R, Phillips SA. Precision medicine and physical therapy: a healthy living medicine approach for the next century. Phys Ther. 2022; 102(1): pzab253.
- 3- Petrie MA, Taylor EB, Suneja M, Shields RK. Genomic and epigenomic evaluation of electrically induced exercise in people with spinal cord injury: application to precision rehabilitation. Phys Ther. 2022; 102(1): pzab243.
- 4- Egan B, Sharples AP. Molecular responses to acute exercise and their relevance for adaptations in skeletal muscle to exercise training. Physiol Rev. 2023; 103(3): 2057-2170.
- 5- Skorup JC, Pierce SR, Paremski AC, Alcott M, Prosser LA. Precision measurement of rehabilitation interventions: a secondary analysis of motor error in a clinical trial with young children with cerebral palsy. Front Pediatr. 2024; 12:1457329.
- 6- Rohaj A, Bulaj G. Digital therapeutics (DTx) expand multimodal treatment options for chronic low back pain: the nexus of precision medicine, patient education, and public health. Healthcare (Basel). 2023; 11(10):1469.
- 7- Sjúrðarson T, Nordsborg N. Angiotensin-converting enzyme and exercise adaptations: genetic variability, pharmacological modulation and future directions. J Physiol. 2025.
- 8- Krammer UDB, Sommer A, Tschida S, Mayer A, Lilja SV, Switzeny OJ, Hippe B, Rust P, Haslberger AG. PGC-1α methylation, miR-23a, and miR-30e expression as biomarkers for exercise- and diet-induced mitochondrial biogenesis in capillary blood from healthy individuals: a single-arm intervention. Sports (Basel). 2022; 10(5): 73.
- 9- Wu G, Zhang X, Gao F. The epigenetic landscape of exercise in cardiac health and disease. J Sport Health Sci. 2021; 10(6): 648–659.
- 10- Zhao X, Nie X. Subgroup state prediction under different noise levels using MODWT and XGBoost. J Healthc Eng. 2023; 2023: 6406275.