Explainable Machine Learning for Predicting Competitive Swimming Performance from Biomechanical, Physiological, and Training-Load Variables
Article Sidebar
Biomechanical efficiency,
Exercise intensity,
Stroke mechanics,
Training load
Main Article Content
Djajaty Mariana Lolowang
Bekir Erhan ORHAN
Fadli Ihsan
Fredrik Alfrets Makadada
Abstract
Background: Competitive swimming performance is influenced by the interaction of biomechanical efficiency, physiological responses, anthropometric characteristics, and training exposure. Conventional analyses may overlook complex relationships among these domains.
Aims: This study aimed to develop an explainable machine-learning model for predicting 100-m swimming performance and to identify the variables contributing most strongly to prediction.
Methods: This observational study included 150 competitive swimmers (86 males and 64 females). Data comprised anthropometric variables, stroke rate, stroke length, stroke index, swimming velocity, intra-cycle velocity variability, start and turn time, resting, mean and peak heart rate, rating of perceived exertion, oxygen saturation, weekly swimming distance, training frequency, session duration, session RPE, and weekly training load. The 100-m performance time was used as the dependent outcome. Descriptive analysis, correlation analysis, and multivariable regression were combined with machine-learning prediction. Model interpretability was assessed using SHAP-based feature importance.
Results: Mean 100-m performance time was 56.9 ± 4.3 s, with values ranging from 48.00 to 65.19 s. Swimming velocity demonstrated the strongest bivariate association with performance time (r = −0.71, p < 0.001), followed by stroke index (r = −0.62, p < 0.001) and stroke length (r = −0.48, p < 0.001). The multivariable model explained 68% of performance variance (R² = 0.68). The machine-learning model achieved a test-set R² of 0.73, RMSE of 2.32 s, and MAE of 1.79 s. SHAP analysis identified swimming velocity, stroke index, intra-cycle velocity variability, stroke length, and turn time as the leading predictors.
Conclusion: Explainable machine learning can integrate multidimensional swimming data while identifying practically meaningful predictors of 100-m performance.
Downloads
Article Details
Copyright (c) 2026 Djajaty Mariana Lolowang, Bekir Erhan ORHAN, Fadli Ihsan, Fredrik Alfrets Makadada
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
- Authors retain copyright and acknowledge that the Journal of Multidisciplinary Applied Natural Science is the first publisher, licensed under a Creative Commons Attribution License.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges and earlier and greater citation of published work.
References
Abruñedo-Lombardero, J., Padrón-Cabo, A., Vélez-Serrano, D., Álvaro-Meca, A., & Iglesias-Soler, E. (2025). An Explainable Machine Learning Approach to Explain the Effects of Training and Match Load on Ultra-Short-Term Heart Rate Variability in Semi-Professional Basketball Players. Sensors (Basel, Switzerland), 25(22). https://doi.org/10.3390/s25226928
Afonso, J., Andrade, R., Rocha-Rodrigues, S., Nakamura, F. Y., Sarmento, H., Freitas, S. R., Silva, A. F., Laporta, L., Abarghoueinejad, M., Akyildiz, Z., Chen, R., Pizarro, A., Ramirez-Campillo, R., & Clemente, F. M. (2024). What We Do Not Know About Stretching in Healthy Athletes: A Scoping Review with Evidence Gap Map from 300 Trials. Sports Medicine (Auckland, N.Z.), 54(6), 1517–1551. https://doi.org/10.1007/s40279-024-02002-7
Alzahrani, A., & Ullah, A. (2024). Advanced biomechanical analytics: Wearable technologies for precision health monitoring in sports performance. Digital Health, 10, 20552076241256744. https://doi.org/10.1177/20552076241256745
Amara, S., Crowley, E., Sammoud, S., Negra, Y., Hammami, R., Chortane, O. G., Khalifa, R., Chortane, S. G., & van den Tillaar, R. (2021). What Is the Optimal Strength Training Load to Improve Swimming Performance? A Randomized Trial of Male Competitive Swimmers. International Journal of Environmental Research and Public Health, 18(22). https://doi.org/10.3390/ijerph182211770
Astridge, D. J., McKenna, M., Campbell, A., & Turner, A. P. (2024). Haemoglobin mass responses and performance outcomes among high-performance swimmers following a 3-week live-high, train-high camp at 2320 m. European Journal of Applied Physiology, 124(8), 2389–2399. https://doi.org/10.1007/s00421-024-05454-x
Baldassarre, R., Bonifazi, M., Meeusen, R., & Piacentini, M. F. (2019). The Road to Rio: A Brief Report of Training-Load Distribution of Open-Water Swimmers During the Olympic Season. International Journal of Sports Physiology and Performance, 14(2), 260–264. https://doi.org/10.1123/ijspp.2017-0845
Baydemi̇r, B., Di̇li̇can, T., Çeti̇noğlu, G., & Deni̇z, M. (2026). The relationship between stroke length, stroke frequency, glide time and performance in swimmers: a biomechanical study. BMC Sports Science, Medicine & Rehabilitation, 18(1). https://doi.org/10.1186/s13102-026-01771-0
Born, D.-P., Stöggl, T., Petrov, A., Burkhardt, D., Lüthy, F., & Romann, M. (2020). Analysis of Freestyle Swimming Sprint Start Performance After Maximal Strength or Vertical Jump Training in Competitive Female and Male Junior Swimmers. Journal of Strength and Conditioning Research, 34(2), 323–331. https://doi.org/10.1519/JSC.0000000000003390
Carvalho, D. D., Goethel, M. F., Erblang, M., Vilas-Boas, J. P., Pyne, D. B., Fernandes, R. J., & Lopes, P. (2026). Impact of an Overload Period on Heart Rate Variability, Sleep Quality, Motivation, and Performance in High-level Swimmers: Use of Explainable Artificial Intelligence (XAI) to Assess Training Load Variations. Sports Medicine (Auckland, N.Z.), 56(5), 1235–1254. https://doi.org/10.1007/s40279-025-02369-1
Chainok, P., Matjiur, R., de Jesus, K., Dos Santos Coelho, L., Cocco Mariani, V., Zacca, R., Fernandes, R. J., & Vilas-Boas, J. P. (2026). Prediction of 1500 m freestyle performance in age-group swimmers based on synthetic data and symbolic regression. Journal of Sports Sciences, 1–18. https://doi.org/10.1080/02640414.2026.2710467
Chen, X., Wang, H., Wang, S., Liu, Z., & Shen, Y. (2026). From acute responses to long-term monitoring: a scoping review of the reliability and validity of biomechanical and physiological assessment tools in elite and highly trained swimmers. BMC Sports Science, Medicine and Rehabilitation, 18(1), 253. https://doi.org/10.1186/s13102-026-01688-8
Dingley, A. A., Pyne, D. B., Youngson, J., & Burkett, B. (2015). Effectiveness of a dry-land resistance training program on strength, power, and swimming performance in paralympic swimmers. Journal of Strength and Conditioning Research, 29(3), 619–626. https://doi.org/10.1519/JSC.0000000000000684
Dong, R., Peng, Y., Liu, Q., Gómez-Ruano, M.-A., Zhang, S., Xu, X., Yang, B., & Liu, H. (2026). Winning beyond scoring: an explainable machine learning framework for identifying key performance indicators in the Chinese Basketball Association. BMC Sports Science, Medicine & Rehabilitation, 18(1). https://doi.org/10.1186/s13102-026-01620-0
Fernandes, A., Afonso, J., Noronha, F., Mezêncio, B., Vilas-Boas, J. P., & Fernandes, R. J. (2023). Intracycle Velocity Variation in Swimming: A Systematic Scoping Review. Bioengineering (Basel, Switzerland), 10(3). https://doi.org/10.3390/bioengineering10030308
Fernandes, A., Goethel, M., Marinho, D. A., Mezêncio, B., Vilas-Boas, J. P., & Fernandes, R. J. (2022). Velocity Variability and Performance in Backstroke in Elite and Good-Level Swimmers. International Journal of Environmental Research and Public Health, 19(11). https://doi.org/10.3390/ijerph19116744
Gonjo, T., Eriksrud, O., Papoutsis, F., & Olstad, B. H. (2020). Relationships between a Load-velocity Profile and Sprint Performance in Butterfly Swimming. International Journal of Sports Medicine, 41(7), 461–467. https://doi.org/10.1055/a-1103-2114
Inoue, A., Dos Santos Bunn, P., do Carmo, E. C., Lattari, E., & da Silva, E. B. (2022). Internal Training Load Perceived by Athletes and Planned by Coaches: A Systematic Review and Meta-Analysis. Sports Medicine - Open, 8(1), 35. https://doi.org/10.1186/s40798-022-00420-3
Kong, Y., Yu, B., Guan, G., Wang, Y., & He, H. (2025). Effects of sleep deprivation on sports performance and perceived exertion in athletes and non-athletes: a systematic review and meta-analysis. Frontiers in Physiology, 16, 1544286. https://doi.org/10.3389/fphys.2025.1544286
López-Belmonte, Ó., Ruiz-Navarro, J. J., Baldassarre, R., Bonifazi, M., Arellano, R., & Piacentini, M. F. (2026). Seasonal Changes in Performance, Physiological, and Kinematic Factors of Maximal Incremental Swimming in Elite Open-Water Swimmers. International Journal of Sports Physiology and Performance, 21(3), 463–471. https://doi.org/10.1123/ijspp.2025-0467
López-Belmonte, Ó., Ruiz-Navarro, J. J., Gay, A., Cuenca-Fernández, F., Arellano, R., & Cejuela, R. (2024). Swimming Performance in Elite Triathletes: Comparison Between Open Water and Pool Conditions. Scandinavian Journal of Medicine & Science in Sports, 34(8), e14702. https://doi.org/10.1111/sms.14702
López-Belmonte, Ó., Ruiz-Navarro, J. J., Gay, A., Cuenca-Fernández, F., Cejuela, R., & Arellano, R. (2023). Determinants of 1500-m Front-Crawl Swimming Performance in Triathletes: Influence of Physiological and Biomechanical Variables. International Journal of Sports Physiology and Performance, 18(11), 1328–1335. https://doi.org/10.1123/ijspp.2023-0157
Marinof, A., Martínez-Sobrino, J., Del Cerro, J. S., González-Ravé, J. M., & Veiga, S. (2026). Managing Training Load in the Lead-Up to Competition: Session-Rating of Perceived Exertion, not the Acute-to-Chronic Workload Ratio, Associated with the Performance of Elite Swimmers. Journal of Human Kinetics, 101(Spec Issue), 271–284. https://doi.org/10.5114/jhk/218950
Mitchell, L. J. G., Rattray, B., Fowlie, J., Saunders, P. U., & Pyne, D. B. (2020). The impact of different training load quantification and modeling methodologies on performance predictions in elite swimmers. European Journal of Sport Science, 20(10), 1329–1338. https://doi.org/10.1080/17461391.2020.1719211
Morais, J. E., Barbosa, T. M., Gomeñuka, N. A., & Marinho, D. A. (2024). Effects of anthropometrics, thrust, and drag on stroke kinematics and 100 m performance of young swimmers using path-analysis modeling. Scandinavian Journal of Medicine & Science in Sports, 34(2), e14578. https://doi.org/10.1111/sms.14578
Morais, J. E., Forte, P., Nevill, A. M., Barbosa, T. M., & Marinho, D. A. (2020). Upper-limb kinematics and kinetics imbalances in the determinants of front-crawl swimming at maximal speed in young international level swimmers. Scientific Reports, 10(1), 11683. https://doi.org/10.1038/s41598-020-68581-3
Morais, J. E., Silva, A. J., Marinho, D. A., Marques, M. C., Batalha, N., & Barbosa, T. M. (2016). Modeling the relationship between biomechanics and performance of young sprinting swimmers. European Journal of Sport Science, 16(6), 661–668. https://doi.org/10.1080/17461391.2016.1149227
Pla, R., Le Meur, Y., Aubry, A., Toussaint, J. F., & Hellard, P. (2019). Effects of a 6-Week Period of Polarized or Threshold Training on Performance and Fatigue in Elite Swimmers. International Journal of Sports Physiology and Performance, 14(2), 183–189. https://doi.org/10.1123/ijspp.2018-0179
Postiglione, G. L., Abbott, S., Newman, P., Mitchell, L. G., Elipot, M., Barclay, G., & Cobley, S. (2025). Race-Performance Parameters Differentiating World-Best From National-Level Swimmers: A Race Video Analysis and Machine-Learning Approach. International Journal of Sports Physiology and Performance, 20(8), 1034–1042. https://doi.org/10.1123/ijspp.2024-0486
Saeterbakken, A. H., Stien, N., Andersen, V., Scott, S., Cumming, K. T., Behm, D. G., Granacher, U., & Prieske, O. (2022). The Effects of Trunk Muscle Training on Physical Fitness and Sport-Specific Performance in Young and Adult Athletes: A Systematic Review and Meta-Analysis. Sports Medicine (Auckland, N.Z.), 52(7), 1599–1622. https://doi.org/10.1007/s40279-021-01637-0
Seifert, L., & Carmigniani, R. (2023). Coordination and stroking parameters in the four swimming techniques: a narrative review. Sports Biomechanics, 22(12), 1617–1633. https://doi.org/10.1080/14763141.2021.1959945
Seshadri, D. R., Thom, M. L., Harlow, E. R., Gabbett, T. J., Geletka, B. J., Hsu, J. J., Drummond, C. K., Phelan, D. M., & Voos, J. E. (2020). Wearable Technology and Analytics as a Complementary Toolkit to Optimize Workload and to Reduce Injury Burden. Frontiers in Sports and Active Living, 2, 630576. https://doi.org/10.3389/fspor.2020.630576
Staunton, C. A., Ruiz-Navarro, J. J., & Born, D.-P. (2025). Stroke rate-stroke length dynamics in elite freestyle swimming: application of kernel density estimation. Frontiers in Sports and Active Living, 7, 1656633. https://doi.org/10.3389/fspor.2025.1656633
Suijkerbuijk, Y. B., Schaafsma, F. G., van Mechelen, J. C., Ojajärvi, A., Corbière, M., & Anema, J. R. (2017). Interventions for obtaining and maintaining employment in adults with severe mental illness, a network meta-analysis. The Cochrane Database of Systematic Reviews, 9(9), CD011867. https://doi.org/10.1002/14651858.CD011867.pub2
Terzi, E., Skari, A., Nikolaidis, S., Papadimitriou, K., Kabasakalis, A., & Mougios, V. (2021). Relevance of a Sprint Interval Swim Training Set to the 100-Meter Freestyle Event Based on Blood Lactate and Kinematic Variables. Journal of Human Kinetics, 80, 153–161. https://doi.org/10.2478/hukin-2021-0091
Torres, G., Maia, F., Nakamura, F. Y., Neiva, H. P., & Sousa, A. (2025). Rating of perceived exertion in continuous sports: a scoping review with evidence gap map. Frontiers in Sports and Active Living, 7, 1553998. https://doi.org/10.3389/fspor.2025.1553998
Veiga, S., Cala, A., Frutos, P. G., & Navarro, E. (2014). Comparison of starts and turns of national and regional level swimmers by individualized-distance measurements. Sports Biomechanics, 13(3), 285–295. https://doi.org/10.1080/14763141.2014.910265
Veiga, S., Roig, A., & Gómez-Ruano, M. A. (2016). Do faster swimmers spend longer underwater than slower swimmers at World Championships? European Journal of Sport Science, 16(8), 919–926. https://doi.org/10.1080/17461391.2016.1153727
Vilas-Boas, J. P. (2025). Swimming biomechanics: from the pool to the lab … and back. Sports Biomechanics, 24(5), 1197–1219. https://doi.org/10.1080/14763141.2023.2237003
Wang, Z., Liu, K., Zhao, X., & Gao, J. (2025). Comparative effectiveness of physical training modalities on swimming performance: a two-tier network meta-analysis. Frontiers in Physiology, 16, 1636595. https://doi.org/10.3389/fphys.2025.1636595