Training load responses modelling and model generalisation in elite sports

• Published in: Scientific reports Vol. 12; no. 1; p. 1586
• Main Authors: Imbach, Frank, Perrey, Stephane, Chailan, Romain, Meline, Thibaut, Candau, Robin
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 28.01.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/2397; 631/553; 631/553/117; 692/53/2423; Accuracy; Athletes; Bioinformatics; Computer Science; Humanities and Social Sciences; Life Sciences; Load; Machine Learning; multidisciplinary; Physical fitness; Physiology; Regression analysis; Science; Science (multidisciplinary); Statistics; Training; REGRESSION; FATIGUE; SYSTEMS-MODEL; RELIABILITY; PERFORMANCE RELATIONSHIP; SELECTION; TAPER; STRATEGIES
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-022-05392-8

This study aims to provide a transferable methodology in the context of sport performance modelling, with a special focus to the generalisation of models. Data were collected from seven elite Short track speed skaters over a three months training period. In order to account for training load accumulation over sessions, cumulative responses to training were modelled by impulse, serial and bi-exponential responses functions. The variable dose-response (DR) model was compared to elastic net (ENET), principal component regression (PCR) and random forest (RF) models, while using cross-validation within a time-series framework. ENET, PCR and RF models were fitted either individually ( M I ) or on the whole group of athletes ( M G ). Root mean square error criterion was used to assess performances of models. ENET and PCR models provided a significant greater generalisation ability than the DR model ( p = 0.018 , p < 0.001 , p = 0.004 and p < 0.001 for E N E T I , E N E T G , P C R I and P C R G , respectively). Only E N E T G and R F G were significantly more accurate in prediction than DR ( p < 0.001 and p < 0.012 ). In conclusion, ENET achieved greater generalisation and predictive accuracy performances. Thus, building and evaluating models within a generalisation enhancing procedure is a prerequisite for any predictive modelling.