ARTIFICIAL INTELLIGENCE-BASED PREDICTION OF SPORTS INJURIES USING ATHLETE MONITORING DATA: A SYSTEMATIC REVIEW OF PREDICTIVE MODELS, DATA SOURCES, AND METHODOLOGICAL GAPS
JOURNAL OF SOCIAL RESEARCH DEVELOPMENT · 19.11.2026 · 7 (9) · 563-579
DOI: 10.59075/jsrd.v7i9.673 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift JOURNAL OF SOCIAL RESEARCH DEVELOPMENT, online erschienen am 19.11.2026. Verfasst von Aqsa Batool und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Sport injuries have a detrimental impact on the training, performance and future involvement of athletes. A plethora of physiological, biomechanical and training load data has become available for predicting injuries due to the growing use of wearable devices and athlete-monitoring technologies. These data can be used by artificial intelligence (AI) and machine learning (ML) to detect patterns that could point to an injury risk. The systematic review focuses on the application of AI and ML in sports injury prediction, specifically athlete-monitoring data, prediction methods, evaluation of model performance, and gaps in existing research. This review is conducted according to the PRISMA 2020 guidelines and only peer-reviewed studies published in the period 2021-2026 are included. Studies are examined according to their participants, sports, injury outcomes, data sources, AI techniques, validation methods, and predictive performance. Previous studies revealed that machine-learning methods such as Random Forest and XGBoost are popular and have proven to be effective. Variations in numbers. The definition of injuries, injury sources, and methods of injury validation make comparisons difficult. Other factors impacting generalizability of existing models are limited external validation and small datasets. The review concludes AI has a great potential in the field of sports-injury prediction. However, more studies are needed with a larger data set. Beyond this, standardized injury measures, a variety of athlete populations, external validation, and explainable AI is required before these systems can be broadly applied in sports practice.
Zitieren
APA
Batool, A., Waqas, F., Ahmed, T., Khan, A., & Ullah, R. (2026). ARTIFICIAL INTELLIGENCE-BASED PREDICTION OF SPORTS INJURIES USING ATHLETE MONITORING DATA: A SYSTEMATIC REVIEW OF PREDICTIVE MODELS, DATA SOURCES, AND METHODOLOGICAL GAPS. JOURNAL OF SOCIAL RESEARCH DEVELOPMENT, 7(9), 563-579. https://doi.org/10.59075/jsrd.v7i9.673
Vancouver
Batool A, Waqas F, Ahmed T, Khan A, Ullah R. ARTIFICIAL INTELLIGENCE-BASED PREDICTION OF SPORTS INJURIES USING ATHLETE MONITORING DATA: A SYSTEMATIC REVIEW OF PREDICTIVE MODELS, DATA SOURCES, AND METHODOLOGICAL GAPS. JOURNAL OF SOCIAL RESEARCH DEVELOPMENT. 2026;7(9):563-579. doi:10.59075/jsrd.v7i9.673
BibTeX
@article{Batool2026,
author = {Batool, Aqsa and Waqas, Faisal and Ahmed, Tahseen and Khan, Amjid and Ullah, Raheem},
title = {ARTIFICIAL INTELLIGENCE-BASED PREDICTION OF SPORTS INJURIES USING ATHLETE MONITORING DATA: A SYSTEMATIC REVIEW OF PREDICTIVE MODELS, DATA SOURCES, AND METHODOLOGICAL GAPS},
journal = {JOURNAL OF SOCIAL RESEARCH DEVELOPMENT},
year = {2026},
volume = {7},
number = {9},
pages = {563--579},
doi = {10.59075/jsrd.v7i9.673}
}
EUVIMED