MétaCan
Menu
Back to cohort
Record W4411795905 · doi:10.23950/jcmk/16412

Artificial Intelligence in Sports Science: A Systematic Review on Performance Optimization, Injury Prevention, and Rehabilitation

2025· review· en· W4411795905 on OpenAlexaboutno aff
Maheshkumar Baladaniya, Aashish Choudhary

Bibliographic record

VenueJournal of Clinical Medicine of Kazakhstan · 2025
Typereview
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsnot available
Fundersnot available
KeywordsRehabilitationSports scienceSports injuryPsychologyComputer scienceMedicineEngineeringPhysical therapy

Abstract

fetched live from OpenAlex

Background: Artificial intelligence (AI) is quickly revolutionizing sports science, providing researchers and practitioners with new means to support the optimization of performance, the improvement of rehabilitation, and the prevention of injuries. Although many AI interventions have been tested in sports, there is still insufficient methodologically sound evidence on the effectiveness and feasibility of AI to support and monitoring in the sport context. Objective: The purpose of this systematic review and meta-analysis was to pool the existed studies to investigate the effects of AI-based interventions on sport performance, injury prevention and rehabilitation in human participants. Methods: A comprehensive search of five databases (PubMed, Scopus, Web of Science, IEEE Xplore, SPORTDiscus) was conducted for studies published from January 2015 to December 2024. Papers based on human subjects and reporting AI-based training or rehabilitation outcomes in sports/games were considered. Quality of the studies was determined using the Cochrane RoB 2.0 tool and Newcastle-Ottawa Scale. Random-effects meta-analysis was conducted where the effect size was for SMD, and the I² statistic was used for heterogeneity. Sensitivity and publication bias tests were also performed. Results: There were 19 studies included in total, 17 of which could be used for meta-analysis. The meta-analysis demonstrated a significant and moderate-to-large effect of the AI interventions on the outcomes (SMD = 0.68, 95% CI: 0.52–0.84, p < 0.001). The subgroup analysis demonstrated superior effectiveness in injury prevention (SMD: 0.75) and rehabilitation (SMD: 0.69), and the machine learning methods were more effective than other AI modalities. There was moderate heterogeneity (I² = 58%). Sensitivity analysis verified that the results were robust, and Egger’s test revealed no obvious publication bias (p = 0.23). Conclusion: Applications of AI in sports AI interventions have significant potential to go a long way to increase performance of sports personnel, reduce risks or injuries and support sports rehabilitation. This work has implications for integrating sport performance and clinical practice with AI-based technologies. Standards for outcomes, methodological rigour, and ethical and pragmatic consideration of AI within sport participation are recommended for future research.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.036
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Systematic review · Consensus signal: Systematic review
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.009
Threshold uncertainty score0.050

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0090.036
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0090.012
Bibliometrics0.0080.009
Science and technology studies0.0010.001
Scholarly communication0.0040.002
Open science0.0020.002
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0050.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.188
GPT teacher head0.569
Teacher spread0.381 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSystematic review
Domainnot available
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Clinical Medicine of KazakhstanSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207