Swimming Performance Interpreted through Explainable Artificial Intelligence (XAI)—Practical Tests and Training Variables Modelling
Source abstract
Abstract
Explainable artificial intelligence (XAI) models with Shapley additive explanation (SHAP) values allows multidimensional representation of movement performance interpreted on both global and local levels in terms understandable to human intuition. We aimed to evaluate the swimming performance (World Aquatics points) predictability of a combination of demographic, training, anthropometric, and biomechanical variables (inputs) through XAI. Forty-seven swimmers (16 males), after completing a training questionnaire (background and duration) and anthropometric assessment, performed, in a randomised order, a 25 m front crawl and three countermovement jumps, at maximal intensity. The predicted World Aquatics points (516 ± 159; mean ± SD) were highly correlated (r2 = 0.93) with the 529 ± 158 actual values. The duration of swimming training was the most important variable (95_SHAP), followed by the countermovement jump impulse (37_SHAP), both with a positive effect on performance. In contrast, a higher percentage of fat mass (21_SHAP) corresponded to lower World Aquatics points. Impulse, when interpreted together with dryland training duration and stroke rate, shows the positive effects of upper and lower limb power on swimming performance. Height should be interpreted together with arm span when exploring positive effects of anthropometric traits on swimming performance. The XAI modelling highlights the usefulness of specific training, technical and physical testing, and anthropometric factors for monitoring swimmers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Explainable Artificial Intelligence (XAI)
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
CIFI2D, Centre of Research, Education, Innovation and Intervention in Sport, Faculty of Sport, University of Porto, 4200-450 Porto, Portugal
LABIOMEP-UP, Porto Biomechanics Laboratory, Faculty of Sport, University of Porto, 4200-450 Porto, Portugal
CIDESD, Research Center in Sport, Health and Human Development, 5001-801 Vila Real, Portugal
Department of Sports, Exercise and Health Sciences, University of Trás-os-Montes and Alto Douro, 5000-801 Vila Real, Portugal
Research Institute for Sport and Exercise, University of Canberra, Canberra, ACT 2617, Australia
Funding
Portuguese Foundation for Science and Technology, I.P. (FCT) · Centre of Research, Education, Innovation and Intervention in Sport
References (61)
Show source-provided references
1. The capabilities of artificial neural networks in body composition research10.1007/s00592-003-0018-x ↗
2. Modeling and predicting the backstroke to breaststroke turns performance in age-group swimmers10.1080/14763141.2021.2005127 ↗
3. Application of Multilayer Neural Network in Sports Psychology
4. Heterogeneous versus homogeneous machine learning ensembles
5. Opening the black box of neural networks: Methods for interpreting neural network models in clinical applications10.21037/atm.2018.05.32 ↗
6. Artificial neural networks in sports: New concepts and approaches10.1080/24748668.2001.11868253 ↗
7. Modeling and prediction of competitive performance in swimming upon neural networks
8. Optical image enhancement based on convolutional neural networks for key point detection in swimming posture analysis10.1007/s11082-023-05875-6 ↗
9. Hamid, A.H.A., Othman, Z., and Suhaimi, S. (2023, January 10–11). Swimming Style Recognition for Video Sequences Using Deep Learning. Proceedings of the 2023 International Conference on Electrical Engineering and Informatics (ICEEI), Bandung, Indonesia.10.1109/ICEEI59426.2023.10346725 ↗
10. The use of neural network technology to model swimming performance
11. Application of Regression and Neural Models to Predict Competitive Swimming Performance10.2466/05.10.PMS.114.2.610-626 ↗
12. Carrard, J., Kloucek, P., and Gojanovic, B. (2020). Modelling Training Adaptation in Swimming Using Artificial Neural Network Geometric Optimisation. Sports, 8.10.3390/sports8010008 ↗
13. Modelling the relationship between biomechanics and performance of young sprinting swimmers10.1080/17461391.2016.1149227 ↗
14. Demarie, S., Chirico, E., and Galvani, C. (2022). Prediction and Analysis of Tokyo Olympic Games Swimming Results: Impact of the COVID-19 Pandemic on Swimmers’ Performance. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19042110 ↗
15. Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., and Müller, K.-R. (2019). Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, Springer.10.1007/978-3-030-28954-6 ↗
16. The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies10.1016/j.jbi.2020.103655 ↗
17. Moustakidis, S., Plakias, S., Kokkotis, C., Tsatalas, T., and Tsaopoulos, D. (2023). Predicting Football Team Performance with Explainable AI: Leveraging SHAP to Identify Key Team-Level Performance Metrics. Future Internet, 15.10.3390/fi15050174 ↗
18. Linardatos, P., Papastefanopoulos, V., and Kotsiantis, S. (2021). Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy, 23.10.3390/e23010018 ↗
19. From local explanations to global understanding with explainable AI for trees10.1038/s42256-019-0138-9 ↗
20. Leite, I., Goethel, M., Fonseca, P., Vilas-Boas, J.P., Avila-Carvalho, L., Mochizuki, L., and Conceicao, F. (2024). A Hierarchy of Variables That Influence the Force–Velocity Profile of Acrobatic Gymnasts: A Tool Based on Artificial Intelligence. Appl. Sci., 14.10.3390/app14083191 ↗
21. Combining theoretical modelling and machine learning approaches: The case of teamwork effects on individual effort expenditure10.1016/j.newideapsych.2024.101077 ↗
22. Understanding gender differences in professional European football through machine learning interpretability and match actions data10.1038/s41598-021-90264-w ↗
23. Energetics and biomechanics as determining factors of swimming performance: Updating the state of the art10.1016/j.jsams.2009.01.003 ↗
24. Effects of anthropometrics, thrust, and drag on stroke kinematics and 100 m performance of young swimmers using path-analysis modeling10.1111/sms.14578 ↗
25. The importance of reflection and evaluation processes in daily training sessions for progression toward elite level swimming performance10.1016/j.psychsport.2022.102219 ↗
26. Swimming sprint performance depends on upper/lower limbs strength and swimmers level10.1080/02640414.2023.2239610 ↗
27. Strength and Power Predictors of Swimming Starts in International Sprint Swimmers10.1519/JSC.0b013e3181c8656f ↗
28. A new model of performance classification to standardize the research results in swimming10.1080/17461391.2022.2046174 ↗
29. Analysis of standing vertical jumps using a force platform10.1119/1.1397460 ↗
30. Anaerobic Threshold Biophysical Characterisation of the Four Swimming Techniques10.1055/a-0975-9532 ↗
31. Rago, V., Brito, J., Figueiredo, P., Carvalho, T., Fernandes, T., Fonseca, P., and Rebelo, A. (2018). Countermovement Jump Analysis Using Different Portable Devices: Implications for Field Testing. Sports, 6.10.3390/sports6030091 ↗
32. Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences, Routledge. [2nd ed.].
33. Energetics of swimming in man10.1152/jappl.1974.37.1.1 ↗
34. Figueiredo, P., Pendergast, D.R., Vilas-Boas, J.P., and Fernandes, R.J. (2013). Interplay of Biomechanical, Energetic, Coordinative, and Muscular Factors in a 200 m Front Crawl Swim. Biomed. Res. Int., 2013.10.1155/2013/897232 ↗
35. Interaction of Kinematic, Kinetic, and Energetic Predictors of Young Swimmers’ Speed10.1123/ijspp.2022-0430 ↗
36. Carvalho, D.D., Soares, S., Zacca, R., Marinho, D.A., Silva, A.J., Pyne, D.B., Vilas-Boas, J.P., and Fernandes, R.J. (2019). In-Water and On-Land Swimmers’ Symmetry and Force Production. Int. J. Environ. Res. Public Health, 16.10.3390/ijerph16245018 ↗
37. Application of Neural and Regression Models in Sports Results Prediction10.1016/j.sbspro.2014.02.249 ↗
38. Swimming constraints and arm coordination10.1016/j.humov.2006.09.003 ↗
39. Effects of Low-Volume, High-Intensity Training on Performance in Competitive Swimmers: A Systematic Review10.1519/JSC.0000000000001583 ↗
40. Influence of different rest intervals during active or passive recovery on repeated sprint swimming performance10.1007/s00421-004-1244-9 ↗
41. Adaptations to swimming training: Influence of training volume10.1249/00005768-199103000-00017 ↗
42. Training using the stroke frequency-velocity relationship to combine biomechanical and metabolic paradigms
43. Modeling the residual effects and threshold saturation of training: A case study of Olympic swimmers
44. Relative contribution of arms and legs in humans to propulsion in 25-m sprint front-crawl swimming10.1007/s004210050581 ↗
45. Morouço, P.G., Marinho, D.A., Izquierdo, M., Neiva, H., and Marques, M.C. (2015). Relative Contribution of Arms and Legs in 30 s Fully Tethered Front Crawl Swimming. Biomed. Res. Int., 2015.10.1155/2015/563206 ↗
46. Contribution of limbs’ actions to the four competitive swimming strokes: A nonlinear approach10.1080/02640414.2018.1423608 ↗
47. Body composition and specific and general strength indices as predictors of 100-m front crawl performance10.37190/ABB-01665-2020-02 ↗
48. Dopsaj, M., Zuoziene, I.J., Milic, R., Cherepov, E., Erlikh, V., Masiulis, N., di Nino, A., and Vodicar, J. (2020). Body Composition in International Sprint Swimmers: Are There Any Relations with Performance?. Int. J. Environ. Res. Public Health, 17.10.3390/ijerph17249464 ↗
49. Associations Between Dry Land Strength and Power Measurements with Swimming Performance in Elite Athletes: A Pilot Study10.2478/v10078-011-0065-2 ↗
50. Wirth, K., Keiner, M., Fuhrmann, S., Nimmerichter, A., and Haff, G.G. (2022). Strength Training in Swimming. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19095369 ↗
51. Physiological, biomechanical and anthropometrical predictors of sprint swimming performance in adolescent swimmers
52. Monitoring changes in lean mass of elite male and female swimmers10.1123/ijspp.1.1.14 ↗
53. Physical Development and Swimming Performance During Biological Maturation in Young Female Swimmers
54. Biomechanics of Competitive Front Crawl Swimming10.2165/00007256-199213010-00002 ↗
55. Biomechanics, energetics and coordination during extreme swimming intensity: Effect of performance level
56. Relationships of stroke rate, distance per stroke, and velocity in competitive swimming
57. Velocity, Stroke Rate, and Distance Per Stroke during Elite Swimming Competition10.1249/00005768-198512000-00001 ↗
58. Kinematic measures and stroke rate variability in elite female 200-m swimmers in the four swimming techniques: Athens 2004 Olympic semi-finalists and French National 2004 Championship semi-finalists10.1080/02640410701332515 ↗
59. Seasonal training and performance of competitive swimmers10.1080/026404100750017805 ↗
60. Progression and variability of competitive performance of Olympic swimmers10.1080/02640410310001655822 ↗
61. Reasons for dropout in swimmers, differences between gender and age and intentions to return to competition