Key result
A Variational Gaussian Process model classifies cyclist training response with ~93% accuracy.
Why the study?
Individual athletes respond differently to training, making it challenging for coaches to detect improvement, accumulated fatigue, or overreaching.
Does machine learning based on cardiovascular drift and aerobic decoupling accurately predict training response in well-trained cyclists?
Observational (n=20)
No
Does machine learning based on cardiovascular drift and aerobic decoupling accurately predict training response in well-trained cyclists?
Absolute Event Rate: 0.931% vs 0.906%
Machine learning applied to cardiovascular drift and aerobic decoupling provides highly accurate classification of training response in cyclists, offering a tool for personalized training monitoring.
ML-based tracking of endurance training responses needs prospective validation before use; leaves open its utility in cardiovascular performance research.
Purpose: The most important parameter influencing performance in endurance sports is aerobic fitness, the quality of the cardiovascular system for efficient oxygen supply of working muscles to produce mechanical work. Each individual athlete responds differently to training. However, for coaches it is not always easy to see improvement, accumulated fatigue, or overreaching. In the new era of technology, we propose an experimental method using machine learning (ML) to measure response quantified as aerobic fitness level based on cardiovascular drift and aerobic decoupling data. Methods: Twenty well-trained athletes in cycling-based sports performed monthly aerobic fitness tests over five months, riding at 75% of their functional threshold power for 60 min. Based on aerobic decoupling (power-to-heart rate ratio) and cardiovascular drift of each test ride, a prediction model was created using ML (Logistic regression, Variational Gaussian Process models and k-nearest neighbors algorithm) that indicated whether or not an athlete was responding to the training. Athletes were spitted as responders (i.e., those showing improvements in cardiovascular drift and aerobic decoupling) or non-responders. Results: Cardiovascular drift and aerobic decoupling demonstrated a significant strong linear correlation. All ML models achieved good predictive performance in classifying athletes as responders or non-responders, with cross-validation accuracy ranging from 0.87 to 0.9. Average predictive accuracy of 0.86 was for k-nearest neighbors, 0.91 for logistic regression, 0.93 for Variational Gaussian Process model. The Variational Gaussian Process model achieved the highest classification for training response. Conclusion: Cardiovascular drift and aerobic decoupling are reliable indicators of response to training stimulus. ML is a promising tool for monitoring training response in endurance sports, offering early and sensitive insights into fitness adaptations or fatigue that can support more personalized training decisions for coaches and athletes.
No takes yet. Share an insight, caveat, or question.
Barsumyan et al. (2025) conducted an observational in Aerobic fitness in endurance athletes (n=20). Variational Gaussian Process (VGP) machine learning model vs. Logistic regression and K-nearest neighbors models was evaluated on Mean test set accuracy for classifying training response. The Variational Gaussian Process machine learning model accurately classified training response in cyclists based on cardiovascular drift and aerobic decoupling, achieving a mean test set accuracy of 93.1%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: