Identifying Key Training Load and Intensity Indicators in Ice Hockey Using Unsupervised Machine Learning

ABSTRACT

To identify key training load (TL) and intensity indicators in ice hockey, practice, and game data were collected using a wearable 200-Hz accelerometer and heart rate (HR) recording throughout a four-week (29 days) competitive period (23 practice sessions and 8 competitive games in 17 elite Danish players (n = 427 observations). Within-individual correlations among accelerometer- (total accelerations [Acc_tot], accelerations >2 m·s⁻² [Acc2], total accelerations [Dec_tot], decelerations <- 2 m·s⁻² [Dec2]), among HR-derived (time >85% maximum HR [t85%HR_max], Edwards’ TL and modified training impulse) TL indicators, and between acceleration- and HR-derived TL parameters were large to almost perfect (r = 0.69–0.99). No significant correlations were observed between accelerometer- and HR-derived intensity indicators. Three between- and two within-components were found. The K-means++ cluster analysis revealed five and four clusters for between- and within-loadings, respectively. The least Euclidean distance from their centroid for each cluster was reported by session-duration, Acc_tot, Dec2, TRIMP_MOD, %t85HR_max for between-loadings, whereas session-duration, Acc2, t85HR_max and Dec2/min for within-loadings. Specific TL or intensity variables might be relevant to identify similar between-subject groups (e.g. individual player, playing positions), or temporal patterns (e.g. changes in TL or intensity over time). Our study provides insights about the redundancy associated with the use of multiple TL and intensity variables in ice hockey.

KEYWORDS:

• Heart rate
• physiology
• team sports
• tracking
• wearable technology

Acknowledgment

The authors thank Adrian Muschinsky and Kasper Deylami for their cooperation as well as the players of the participating club for their involvement in the study and the coaches for the positive support. In addition, the authors would like to thank TeamDanmark for their collaboration on this project, and Dr. Ceulemans for answering our questions and advising us regarding the multilevel simultaneous component analysis. Tiago Fernandes was supported by an individual doctoral grant funded by the Portuguese Foundation for Science and Technology (2021.0581.BD).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The work was supported by the Portuguese Foundation for Science and Technology (Fundação para a Ciência e a Tecnologia) [2021.0581.BD].