EUVIMEDEUVIMED entdecken
Crossref

ATHLETE INJURY PREDICTION USING MACHINE LEARNING (ML)

Dhruv Rajput, Uday Suresh Kamdi, Het Patel, Om Bhatt, Ramchandran P

International Journal of Drug Delivery Technology · 17.06.2026 · 16 (54s)

DOI: 10.25258/ijddt.16.54s.40 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 17.06.2026. Verfasst von Dhruv Rajput und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Against the dynamic backdrop of sports, escalating rates and serious ramifications of sports injuries pose a key challenge on all levels of involvement. Athletes, both amateur and professional, incur not only physical strain and emotional distress but interrupt their career development, often at a high price of medical interventions and lost time. On the organizational front, clubs and teams incur high expenses of treatment, rehabilitation, and decreased availability of players, both on-field performance and organizational revenue. Conventional prevention strategies founded on historical records and broad-based rules do not always mediate well with complex and multifarious dynamics of risk factors varying from one athlete to another. Recognizing these deficiencies, a surging trend in the sports science community has been to embrace machine learning (ML) as a modern and data-driven solution. ML is a powerful tool for predicting injuries on a personal level with a view to uncovering complex dynamics across physical, biomechanical, and environmental variables. This review explores in depth the multifarious role of ML in predicting sports-related injuries with various classes of injuries, a snapshot of contributing factors, data sources such as wearable sensors and performance analysis devices, and diverseness of ML models used—all the way from classical routines to advanced deep learning architectures. It also touches on main challenges involving inconsistency of data quality, scaleability constraints on various populations of athletes, difficulties in clinical deployment, and opaque complexity of advanced architecture limiting interpretability. Additionally, the paper does pose concerns on ethics as well, with special focus on data security, personal privacy, and fairness in decision-making by a computer program. As technology advances, aggregating responsible robust data governance frameworks as well as transparent practices by AI becomes increasingly pivotal. Ultimately, the review points to future emphasis: designing standardized data infrastructure, boosting model robustness and interpretability, integrating multi-source inputs, and harmonizing ML tools with on-field sport contexts. Closing these divides will hold the key to translating innovative research into realizable applications, with ultimate emphasis on maximizing athlete longevity and resilience, health, and performance. Coordinated innovation could see machine learning revolutionize predictions, prevention, and treatment of sporting injury. Machine learning isn't just transforming injury prevention—it's redefining how we understand and preserve athlete performance, health, and longevity in sport.

Zitieren

APA

Rajput, D., Kamdi, U. S., Patel, H., Bhatt, O., & P, R. (2026). ATHLETE INJURY PREDICTION USING MACHINE LEARNING (ML). International Journal of Drug Delivery Technology, 16(54s). https://doi.org/10.25258/ijddt.16.54s.40

Vancouver

Rajput D, Kamdi US, Patel H, Bhatt O, P R. ATHLETE INJURY PREDICTION USING MACHINE LEARNING (ML). International Journal of Drug Delivery Technology. 2026;16(54s). doi:10.25258/ijddt.16.54s.40

BibTeX
@article{Rajput2026,
  author = {Rajput, Dhruv and Kamdi, Uday Suresh and Patel, Het and Bhatt, Om and P, Ramchandran},
  title = {ATHLETE INJURY PREDICTION USING MACHINE LEARNING (ML)},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {54s},
  doi = {10.25258/ijddt.16.54s.40}
}
Kostenlos starten →