{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:49:51Z","timestamp":1791352191259,"version":"4.3.1"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Optimizing training in elite sports while managing injury risk requires models that can learn from heterogeneous and imbalanced athlete records without contaminating evaluation data. This study presents PTI-GANFormer (Personalized Training and Injury Risk Prediction using Generative Adversarial Network-Former), an integrated decision-support framework. Its contribution is not CTGAN or self-attention in isolation; rather, it is the leakage-controlled combination of training-only conditional augmentation, three functionally separated attention pathways, five domain-engineered indicators, and a transparent risk-to-action recommendation layer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>After median imputation, plausibility-aware outlier handling, categorical embedding, scaling, and feature engineering, the data were stratified into training and untouched testing partitions. CTGAN was fitted only to the training partition and generated minority-class records until each training class matched the original majority count of 7,894. The hybrid classifier distinguishes No Injury, Minor Injury, and Major Injury, while the recommendation engine converts predicted risk into advisory workload and recovery options that require practitioner review.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across repeated stratified evaluation runs, PTI-GANFormer achieved an accuracy of 0.960 \u00b1 0.004 (95% CI: 0.957\u20130.963), precision of 0.950 \u00b1 0.006, recall of 0.960 \u00b1 0.005, F1-score of 0.950 \u00b1 0.005, and macro ROC-AUC of 0.981 \u00b1 0.004.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results support predictive risk stratification and decision support; they do not by themselves establish injury prevention or performance enhancement.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1923556","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:49:19Z","timestamp":1791348559000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid deep learning framework combining CTGAN and transformers for personalized injury mitigation in elite sports"],"prefix":"10.3389","volume":"17","author":[{"given":"Tiemin","family":"Teng","sequence":"first","affiliation":[{"name":"School of Physical Education, Harbin Normal University","place":["Harbin, Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Education College, Wenzhou Business College","place":["Wenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s13040-025-00431-2","article-title":"Machine learning models for reinjury risk prediction using cardiopulmonary exercise testing (CPET) data: optimizing athlete recovery","volume":"18","author":"Abasi","year":"2025","journal-title":"Biodata. Min."},{"key":"B2","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1186\/s13102-026-01625-9","article-title":"Adaptive ensemble sizing with reinforcement learning for real-time ankle injury detection in wearable sensor systems","volume":"18","author":"Alanazi","year":"2026","journal-title":"BMC Sports Sci. Med. Rehabil."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-34551-w","article-title":"Real-time wearable biomechanics framework for sports injury prevention and rehabilitation optimization","author":"Alzahrani","year":"2026","journal-title":"Sci. Rep"},{"key":"B4","article-title":"Time-to-injury forecasting in elite female football: A deepHit survival approach","volume-title":"Preprint","author":"Catterall","year":"2026"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fspor.2025.1607600","article-title":"A synthetic data-driven machine learning approach for athlete performance attenuation prediction","volume":"7","author":"Cordeiro","year":"2025","journal-title":"Front. Sports Active. Living."},{"key":"B6","doi-asserted-by":"publisher","first-page":"30318","DOI":"10.1038\/s41598-024-81107-5","article-title":"The analysis of generative adversarial network in sports education based on deep learning","volume":"14","author":"Eerdenisuyila","year":"2024","journal-title":"Sci. Rep."},{"key":"B7","doi-asserted-by":"publisher","first-page":"37656","DOI":"10.1038\/s41598-025-21613-2","article-title":"Sports injury risk prediction based on temporal graph encoding and graph neural networks: A cross-sport transfer learning framework","volume":"15","author":"Fang","year":"2025","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s44163-025-00254-4","article-title":"Application of flexible sensor multimodal data fusion system based on artificial synapse and machine learning in athletic injury prevention and health monitoring","volume":"5","author":"Gai","year":"2025","journal-title":"Discover. Artif. Intell."},{"key":"B9","article-title":"Revisiting deep learning models for tabular data","author":"Gorishniy","year":"2021"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.aej.2026.02.005","article-title":"Feature embedded attention-based hybrid approach for athletic injury risk prediction","volume":"139","author":"Hu","year":"2026","journal-title":"Alexandria. Eng. J."},{"key":"B11","doi-asserted-by":"publisher","first-page":"28405","DOI":"10.1038\/s41598-025-13949-6","article-title":"Internet of things enabled deep learning monitoring system for realtime performance metrics and athlete feedback in college sports","volume":"15","author":"Hu","year":"2025","journal-title":"Sci. Rep."},{"key":"B12","article-title":"TabTransformer: Tabular data modeling using contextual embeddings","author":"Huang","year":"2020"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1101\/2025.04.23.25326218","article-title":"Informed injury prediction in elite football: Decision theory meets machine learning","author":"Huth","year":"2025","journal-title":"medRxiv"},{"key":"B14","doi-asserted-by":"publisher","first-page":"894","DOI":"10.59324\/ejtas.2024.2(4).73","article-title":"Development of a predictive modeling framework for athlete injury risk assessment and prevention: A machine learning approach","volume":"2","author":"Iduh","year":"2024","journal-title":"Eur. J. Theor. Appl. Sci."},{"key":"B15","first-page":"22","article-title":"VAIR: Visual analytics for injury risk exploration in sports","author":"Lee","year":"2025"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecasting."},{"key":"B17","doi-asserted-by":"publisher","first-page":"40252","DOI":"10.1038\/s41598-025-24144-y","article-title":"SHAP-based interpretable machine learning for injury risk prediction in university football players: a multi-dimensional data analysis approach: J. Ma et\u00a0al","volume":"15","author":"Ma","year":"2025","journal-title":"Sci. Rep."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/s44443-026-00874-5","article-title":"Beyond threshold-based monitoring: A deep temporal learning framework with dual-path ACWR feature encoding for sports injury risk prediction","author":"Pan","year":"2026","journal-title":"J. King. Saud. Univ. Comput. Inf. Sci"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2026.111281","article-title":"A fine-grained attention and geometric correspondence model for musculoskeletal risk classification in athletes using multimodal visual and skeletal features","volume":"138","author":"Rahman","year":"2026","journal-title":"Comput. Electr. Eng."},{"key":"B20","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1186\/s13102-025-01502-x","article-title":"Machine learning framework for predicting athletic injuries and optimising performance","volume":"18","author":"Raju","year":"2026","journal-title":"BMC Sports Sci. Med. Rehabil."},{"key":"B21","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1186\/s12880-024-01304-6","article-title":"Real-time sports injury monitoring system based on the deep learning algorithm","volume":"24","author":"Ren","year":"2024","journal-title":"BMC Med. Imaging"},{"key":"B22","article-title":"Finding pre-injury patterns in triathletes from lifestyle, recovery and load dynamics features","author":"Rossi","year":"2025"},{"key":"B23","first-page":"1741","article-title":"Athlete injury prediction: A time series forecasting method based on wearable sensor data and deep learning","author":"Shi","year":"2025"},{"key":"B24","article-title":"SAINT: Self-attention and intersample attention transformer for tabular data","author":"Somepalli","year":"2021"},{"key":"B25","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.jclinepi.2015.12.005","article-title":"A calibration hierarchy for risk models was defined: from utopia's wood to pulsating forests","volume":"74","author":"Van Calster","year":"2016","journal-title":"J. Clin. Epidemiol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1249\/mss.0000000000003493","article-title":"Predicting musculoskeletal loading at common running injury locations using machine learning and instrumented insoles","volume":"56","author":"Van Hooren","year":"2024","journal-title":"Med. Sci. Sports Exercise"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-31591-0","article-title":"Dynamic prediction of adolescent sports injury probability based on the improved ARIMA model in the background of digital physical education teaching","author":"Wang","year":"2025","journal-title":"Sci. Rep"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-026-02413-y","article-title":"Multidisciplinary prediction of running-related injuries using machine learning","author":"Wu","year":"2026","journal-title":"NPJ Digital. Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"14565","DOI":"10.1007\/s00521-021-06440-6","article-title":"Internet of things-enabled real-time health monitoring system using deep learning","volume":"35","author":"Wu","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-03331-x","article-title":"Construction and application of a model for predicting athletes\u2019 injury risk based on machine learning","author":"Xu","year":"2025","journal-title":"BMC Med. Inf. Decis. Making"},{"key":"B31","article-title":"Modeling tabular data using conditional GAN","author":"Xu","year":"2019"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1174525","article-title":"A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning","volume":"14","author":"Ye","year":"2023","journal-title":"Front. Physiol."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1923556\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:49:44Z","timestamp":1791348584000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1923556\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":32,"alternative-id":["10.3389\/fphys.2026.1923556"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1923556","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1923556"}}