Abstract
Do athletes specialize toward sports disciplines that are well aligned with their anthropometry? Novel machine-learning algorithms now enable scientists to cluster athletes based on their individual anthropometry while integrating multiple anthropometric dimensions, which may provide new perspectives on anthropometry-dependent sports specialization. We aimed to identify clusters of competitive cyclists based on their individual anthropometry using multiple anthropometric measures, and to evaluate whether athletes with a similar anthropometry also competed in the same cycling discipline. Additionally, we assessed differences in sprint and endurance performance between the anthropometric clusters. Twenty-four nationally and internationally competitive male cyclists were included from sprint, pursuit, and road disciplines. Anthropometry was measured and k-means clustering was performed to divide cyclists into three anthropometric subgroups. Sprint performance (Wingate 1-s peak power, squat-jump mean power) and endurance performance (mean power during a 15 km time trial, (Formula presented.) O2peak) were obtained. K-means clustering assigned sprinters to a mesomorphic cluster (endo-, meso-, and ectomorphy were 2.8, 5.0, and 2.4; n = 6). Pursuit and road cyclists were distributed over a short meso-ectomorphic cluster (1.6, 3.8, and 3.9; n = 9) and tall meso-ectomorphic cluster (1.5, 3.6, and 4.0; n = 9), the former consisting of significantly lighter, shorter, and smaller cyclists (p < 0.05). The mesomorphic cluster demonstrated higher sprint performance (p < 0.05), whereas the meso-ectomorphic clusters established higher endurance performance (p < 0.001). Overall, endurance performance was associated with lean ectomorph cyclists with small girths and small frontal area (p < 0.05), and sprint performance related to cyclists with larger skinfolds, larger girths, and low frontal area per body mass (p < 0.05). Clustering optimization revealed a mesomorphic cluster of sprinters with high sprint performance and short and tall meso-ectomorphic clusters of pursuit and road cyclists with high endurance performance. Anthropometry-dependent specialization was partially confirmed, as the clustering algorithm distinguished short and tall endurance-type cyclists (matching the anthropometry of all-terrain and flat-terrain road cyclists) rather than pursuit and road cyclists. Machine-learning algorithms therefore provide new insights in how athletes match their sports discipline with their individual anthropometry.
Original language | English |
---|---|
Article number | 1276 |
Pages (from-to) | 1-10 |
Number of pages | 10 |
Journal | Frontiers in Physiology |
Volume | 10 |
DOIs | |
Publication status | Published - 9 Oct 2019 |
Bibliographical note
Copyright © 2019 van der Zwaard, de Ruiter, Jaspers and de Koning.Funding
We would like to thank all athletes involved in this study and the stakeholders KNWU, KNSB, KNRB, NOC?NSF, Tulipmed, b-Cat High Altitude, and Artinis Medical Systems. Funding. This work was supported by the Foundation for Technical Sciences (STW) of the Netherlands Organization for Scientific Research (NWO) under grant 12891. Open access publication was provided by the Vrije Universiteit Amsterdam, Netherlands.
Funders | Funder number |
---|---|
Artinis Medical Systems | |
Foundation for Technical Sciences | |
KNRB | |
KNSB | |
KNWU | |
National Science Foundation | |
Nederlandse Organisatie voor Wetenschappelijk Onderzoek | 12891 |
Stichting voor de Technische Wetenschappen |
Keywords
- anthropometry
- cycling
- data science
- machine learning
- physical performance
- sports specialization