EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Frequency-Aware Dual-Stream Deep Learning Framework for Athlete Workload Monitoring and Injury Risk Assessment: A Multi-Dataset Validation Study in Professional Team Sports

Jinnian Tong, Peng Gao

Sensors · 03.07.2026 · 26 (13) · 4228

DOI: 10.3390/s26134228 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.07.2026. Verfasst von Jinnian Tong und 1 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School, Dongshin University, Naju 58245, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Athletes, Athletic Injuries, Workload. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accumulation of training and competition loads represents a critical determinant of musculoskeletal injury risk in professional team sports, yet contemporary monitoring systems remain limited by their reliance on single-domain temporal analysis that overlooks the multi-scale rhythmic patterns inherent in athletic workload signals. This study introduces FDTM (frequency-aware dual-stream temporal model), a deep learning framework that jointly encodes time-domain dependencies and frequency-domain spectral signatures from digital athlete monitoring streams to predict individual injury risk over a forward-looking seven-game horizon. The framework integrates a stacked bidirectional long short-term memory branch augmented with temporal self-attention pooling, a spectral encoding branch employing discrete Fourier transform decomposition across high-frequency (weekly), mid-frequency (bi-weekly), and low-frequency (seasonal) bands, and a cross-modal gated attention fusion module that adaptively balances temporal and spectral representations conditioned on player context. We evaluate FDTM on three heterogeneous public sports datasets spanning basketball (NBA game-log corpus 2013–2023), Australian rules football (AFL Player Workload Dataset), and soccer (SoccerMon open monitoring corpus), comprising 612 athletes and 247,830 player-game observations across ten competitive seasons. FDTM achieves AUC-ROC values of 0.858, 0.833, and 0.821 on the three datasets respectively, outperforming the strongest deep-learning baseline (FEDformer) by 2.0 to 3.3 percentage points and the strongest non-spectral baseline (TCN) by 3.2 to 4.5 percentage points while maintaining a Brier score below 0.04. Ablation studies confirm that the spectral branch contributes 5.1 percent to overall discriminative performance. SHAP attribution analyses identify high-frequency weekly components as the dominant injury-relevant signal, followed by low-frequency seasonal trends and the cumulative acute-to-chronic workload temporal feature, with gating-weight visualizations revealing dynamic modality contributions consistent with established sports science theory. Direct spectral analysis of the raw workload signal confirms that injury-preceding windows exhibit significantly elevated weekly-band power across all three datasets (Mann–Whitney U test, p < 1 × 10−7), and the architectural advantage is shown to be robust across 30 independent training seeds. These findings suggest that frequency-aware modeling may serve as a transferable methodology for sports engineering applications in injury prevention, return-to-play planning, and individualized rehabilitation, pending further external validation in female athletes and additional team sports.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAthletesAthletic InjuriesWorkloadTeam SportsHumansRisk AssessmentBasketballSportsMonitoring, PhysiologicSoccerLong Short Term Memory

Stichwörter der Autor:innen

athlete workload monitoringbidirectional LSTMcross-modal attention fusionfrequency-aware modelinginjury risk predictionmulti-dataset validationspectral decompositionsports digital engineering

Autor:innen und Institutionen

  • Graduate School, Dongshin University, Naju 58245, Republic of Korea.
  • Department of Physical Education, Shandong Vocational University of Foreign Affairs, Weihai 264504, China.

Zitieren

APA

Tong, J., & Gao, P. (2026). A Frequency-Aware Dual-Stream Deep Learning Framework for Athlete Workload Monitoring and Injury Risk Assessment: A Multi-Dataset Validation Study in Professional Team Sports. Sensors, 26(13), 4228. https://doi.org/10.3390/s26134228

Vancouver

Tong J, Gao P. A Frequency-Aware Dual-Stream Deep Learning Framework for Athlete Workload Monitoring and Injury Risk Assessment: A Multi-Dataset Validation Study in Professional Team Sports. Sensors. 2026;26(13):4228. doi:10.3390/s26134228

BibTeX
@article{Tong2026,
  author = {Tong, Jinnian and Gao, Peng},
  title = {A Frequency-Aware Dual-Stream Deep Learning Framework for Athlete Workload Monitoring and Injury Risk Assessment: A Multi-Dataset Validation Study in Professional Team Sports},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4228},
  doi = {10.3390/s26134228}
}
Kostenlos starten →