Bidirectional Long Short-Term Memory for Early Detection of Running Injuries in Imbalanced Data

Authors

  • David Universitas Dian Nuswantoro
  • Defri Kurniawan Faculty of Computer Science, Universitas Dian Nuswantoro, Indonesia

DOI:

10.33395/sinkron.v10i2.15928

Keywords:

Acute:Chronic Workload Ratio, Bi-Directional Long Short-Term Memory, Focal Loss, sports injury prediction, time-series data

Abstract

Running-related injuries are a common sports health issue that can impair athletic performance and potentially terminate an athlete’s career. Early injury detection is therefore critical, as injuries are cumulative in nature and influenced by training load patterns over time. Consequently, data-driven predictive approaches based on time-series analysis are required to support athlete monitoring systems with a safety-oriented focus. This study aims to develop an efficient, accurate, and safety-first injury prediction model for running athletes. The study utilizes daily running activity time-series data obtained from Kaggle. The proposed model is based on a Bi-Directional Long Short-Term Memory (Bi-LSTM) architecture to capture bidirectional temporal dependencies, combined with Focal Loss to address extreme class imbalance. In addition, domain-specific feature engineering is applied through the Acute:Chronic Workload Ratio (ACWR). Model performance is evaluated against tabular-data-based models, namely XGBoost and Balanced Bagging, across multiple experimental configurations. Experimental results indicate that the lightweight Bi-LSTM configuration achieves a Recall of 90.7%, outperforming the benchmark models while maintaining a competitive AUC. These findings demonstrate that sequential modeling is more effective in detecting rare injury events. Overall, this study confirms that Bi-LSTM-based sequential modeling is well suited for early detection of running injuries and suggests its potential applicability in athlete monitoring systems that prioritize safety.

GS Cited Analysis

Downloads

Download data is not yet available.

References

Alizadegan, H., Rashidi Malki, B., Radmehr, A., Karimi, H., & Ilani, M. A. (2025). Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Exploration and Exploitation, 43(1), 281–301. https://doi.org/10.1177/01445987241269496

Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., & Muneer, A. (2023). LSTM Inefficiency in Long-Term Dependencies Regression Problems. Journal of Advanced Research in Applied Sciences and Engineering Technology, 30(3), 16–31. https://doi.org/10.37934/araset.30.3.1631

Fang, D., & Chen, C. (2025). Sports injury risk prediction based on temporal graph encoding and graph neural networks: A cross-sport transfer learning framework. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-21613-2

Hanafiah, A., Arta, Y., Nasution, H. O., & Lestari, Y. D. (2023). Penerapan Metode Recurrent Neural Network dengan Pendekatan Long Short-Term Memory (LSTM) Untuk Prediksi Harga Saham. Bulletin of Computer Science Research, 4(1), 27–33. https://doi.org/10.47065/bulletincsr.v4i1.321

Husain, G., Nasef, D., Jose, R., Mayer, J., Bekbolatova, M., Devine, T., & Toma, M. (2025). SMOTE vs. SMOTEENN: A Study on the Performance of Resampling Algorithms for Addressing Class Imbalance in Regression Models. Algorithms, 18(1). https://doi.org/10.3390/a18010037

Jimenez, C., & Verhagen, E. (2025). Reimagining athlete monitoring for true indicative injury prevention. In BMJ Open Sport and Exercise Medicine (Vol. 11, Number 2). BMJ Publishing Group. https://doi.org/10.1136/bmjsem-2025-002479

Kakouris, N., Yener, N., & Fong, D. T. P. (2021). A systematic review of running-related musculoskeletal injuries in runners. In Journal of Sport and Health Science (Vol. 10, Number 5, pp. 513–522). Elsevier B.V. https://doi.org/10.1016/j.jshs.2021.04.001

Kalkhoven, J. T., Watsford, M. L., Coutts, A. J., Edwards, W. B., & Impellizzeri, F. M. (2021). Training Load and Injury: Causal Pathways and Future Directions. In Sports Medicine (Vol. 51, Number 6, pp. 1137–1150). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/s40279-020-01413-6

Ko, M. S., Lee, K., Kim, J. K., Hong, C. W., Dong, Z. Y., & Hur, K. (2021). Deep Concatenated Residual Network with Bidirectional LSTM for One-Hour-Ahead Wind Power Forecasting. IEEE Transactions on Sustainable Energy, 12(2), 1321–1335. https://doi.org/10.1109/TSTE.2020.3043884

Landi, F., Baraldi, L., Cornia, M., & Cucchiara, R. (2021). Working Memory Connections for LSTM. https://doi.org/10.1016/j.neunet.2021.08.030

Leckey, C., Van Dyk, N., Doherty, C., Lawlor, A., & Delahunt, E. (2025). Machine learning approaches to injury risk prediction in sport: A scoping review with evidence synthesis. In British Journal of Sports Medicine (Vol. 59, Number 7, pp. 491–500). BMJ Publishing Group. https://doi.org/10.1136/bjsports-2024-108576

Lin, Y. J., Lee, C. C., Huang, T. W., Hsu, W. C., Wu, L. W., Lin, C. C., & Hsiu, H. (2023). Using Arterial Pulse and Laser Doppler Analyses to Discriminate between the Cardiovascular Effects of Different Running Levels. Sensors, 23(8). https://doi.org/10.3390/s23083855

Mahadevaswamy, U. B., & Swathi, P. (2022). Sentiment Analysis using Bidirectional LSTM Network. Procedia Computer Science, 218, 45–56. https://doi.org/10.1016/j.procs.2022.12.400

Pavlatos, C., Makris, E., Fotis, G., Vita, V., & Mladenov, V. (2023). Enhancing Electrical Load Prediction Using a Bidirectional LSTM Neural Network. Electronics (Switzerland), 12(22). https://doi.org/10.3390/electronics12224652

Pratama, A. Y., Tiara, S. D., Daniarti, E., Informasi, S., Nusantara, U., & Kediri, P. (2024). Analisis Cedera Atlet Lari Menggunakan Metode Decision Tree Berdasarkan Data Aktivitas Latihan. In INOTEK (Vol. 9).

Shao, Y., Li, R. D., Luo, Y. J., & Zhu, M. (2021). Research on Running Data Analysis Method Based on Attention-LSTM. Proceedings - 2021 International Conference on Intelligent Transportation, Big Data and Smart City, ICITBS 2021, 446–450. https://doi.org/10.1109/ICITBS53129.2021.00116

Syauqi, M. A., Syauqy, D., & Kurniawan, W. (2025). Sistem Wearable Deteksi Postur pada Training Lateral Raise menggunakan Sensor MPU6050 dengan Algoritma Random Forest (Vol. 1, Number 1). http://j-ptiik.ub.ac.id

Syukron, A., Saputro, E., & Widodo, P. (2023). Penerapan Metode Smote Untuk Mengatasi Ketidakseimbangan Kelas Pada Prediksi Gagal Jantung. In Jurnal Teknologi Informasi dan Terapan (J-TIT (Vol. 10, Number 1). https://doi.org/10/25047/jtit.v10i1.312

Van Eetvelde, H., Mendonça, L. D., Ley, C., Seil, R., & Tischer, T. (2021). Machine learning methods in sport injury prediction and prevention: a systematic review. In Journal of Experimental Orthopaedics (Vol. 8, Number 1). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1186/s40634-021-00346-x

van Poppel, D., van der Worp, M., Slabbekoorn, A., van den Heuvel, S. S. P., van Middelkoop, M., Koes, B. W., Verhagen, A. P., & Scholten-Peeters, G. G. M. (2021). Risk factors for overuse injuries in short- and long-distance running: A systematic review. Journal of Sport and Health Science, 10(1), 14–28. https://doi.org/10.1016/j.jshs.2020.06.006

Venckunas, T., Gumauskiene, B., Muanjai, P., Cadefau, J. A., & Kamandulis, S. (2025). High-Intensity Interval Training Improves Cardiovascular Fitness and Induces Left-Ventricular Hypertrophy During Off-Season. Journal of Functional Morphology and Kinesiology, 10(3). https://doi.org/10.3390/jfmk10030271

Wu, H., Brooke-Wavell, K., Barnes, M. R., Awan, Z., Mastana, S., Allen, S., & Blagrove, R. C. (2025). A time-sequenced approach to machine learning prognostic modelling with implementation on running-related injury prediction. https://doi.org/10.1101/2025.05.07.25327162

Ye, X., Huang, Y., Bai, Z., & Wang, Y. (2023). A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning. Frontiers in Physiology, 14. https://doi.org/10.3389/fphys.2023.1174525

Zul, M., Khairuddin, F., Sankaranarayanan, S., Hasikin, K., Anuar, N., Razak, A., & Omar, R. (2024). Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model. 20. https://doi.org/10.7717/peerj

Downloads


Crossmark Updates

How to Cite

David, D., & Kurniawan, D. (2026). Bidirectional Long Short-Term Memory for Early Detection of Running Injuries in Imbalanced Data. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 10(2), 1048-1059. https://doi.org/10.33395/sinkron.v10i2.15928

Issue

Vol. 10 No. 2 (2026): Article Research April, 2026

Section

Articles

License

Copyright (c) 2026 David David, Defri Kurniawan

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC