Key result
AI and genomics show promise for predicting athletic performance and injury risk but lack clinical utility.
Why the study?
Traditional sports training models based on generalised protocols may overlook individual variations in training adaptation, recovery, and injury susceptibility.
The integration of AI and genomics in sports science offers potential for personalized training and injury prevention, though challenges like limited reproducibility and data integration remain.
Should not yet change sports training practices; leaves open validation needs in larger, diverse cohorts.
The integration of artificial intelligence (AI) and genomics in sports science has immense potential in the field by enabling personalised, predictive, and data-driven approaches to enhance athletes' performance and mitigate injury risk. Traditional training models based on generalised protocols may overlook individual variations in training adaptation, recovery, and injury susceptibility. Recent breakthroughs in genomics, wearable technologies, multi-omics profiling, and machine learning have produced new possibilities for precision sports medicine. This review explores the molecular and physiological foundations of athletic performance, highlighting the influence of key genetic polymorphisms, such as ACTN3 , ACE , PPARGC1A , and collagen-related genes, on endurance, strength, metabolism, and injury vulnerability. The review additionally analyses the use of AI technologies, including machine learning, deep learning, predictive analytics, and systems biology approaches, in analysing complex physiological, biomechanical, and genomic datasets. The applications of AI-driven individualised training, nutrigenomics, biomarker-guided recovery, wearable sensor technologies, and injury prediction models are thoroughly reviewed. The integration of genomics with AI-driven predictive algorithms may support athlete classification, training optimisation, and assessment of fatigue and musculoskeletal injuries through polygenic risk score and multi-omics analysis. Concerns regarding ethics and legality related to genetic privacy, data security, discrimination, and the misuse of genome technology in sports are also highlighted. Although significant obstacles such as limited reproducibility, small sample numbers, population bias, and difficulties in data integration remain serious limitations, future developments in single-cell omics, digital twins, and real-time biosensing technologies may further contribute to precision sports science and personalised athlete management.
No takes yet. Share an insight, caveat, or question.
Patani et al. (2026) conducted a review in Athletic performance and injury susceptibility. Artificial intelligence and genomics integration vs. Traditional training models was evaluated. The integration of artificial intelligence and genomics in sports science shows promise for predicting athletic performance and injury risk, but clinical utility remains limited by small sample sizes, lack of external validation, and ethnic bias.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: