Key result
Adding resting HRV to demographic ML models reduces aerobic fitness prediction error by ~10%.
Why the study?
The predictive value of demographic information combined with short-term resting heart rate variability for estimating aerobic endurance fitness in youth male soccer players was unclear.
Does combining demographic information with resting heart rate variability improve the machine-learning prediction of aerobic endurance in youth male soccer players compared to demographics alone?
Cross-Sectional (n=237)
No
Does combining demographic information with resting heart rate variability improve the machine-learning prediction of aerobic endurance in youth male soccer players compared to demographics alone?
Adding short-term resting heart rate variability to demographic data provides only a modest improvement in machine-learning prediction of aerobic endurance in youth male soccer players.
May support resting HRV for endurance estimation in youth soccer; leaves open prospective validation and incremental utility.
Introduction/objective This study evaluated the predictive value of demographic information and short-term resting heart rate variability (HRV) for estimating aerobic endurance fitness assessed via the Yo-Yo Intermittent Recovery Level 1 test in youth male soccer players. Methods A total of 275 players (aged 8-18) were tested during pre-season. Data included players’ characteristics, resting heart rate and it’s variability in supine and standing positions, and Yo-Yo test results. Short-term (1–5 minutes) RR intervals (RRi) were recorded using the Polar Team 2, preprocessed for artifacts, and analyzed for time-, frequency-, and non-linear HRV features. Frequency-domain metrics were extracted from linearly detrended signals to ensure stationarity. Ten datasets combining player characteristics (age, stature, body mass, BMI, body composition, maturity offset, experience, match status) and HRV were used to train multiple machine learning (ML) regression models. Model performance was evaluated using standard metrics, and SHAP values identified key predictors. Results The final sample included 237 players median (range) age and BMI were: 13 (8 – 18) years, 18.8 (13.8 – 29.3) kg/m 2 . The best models, Random Forest using 120-second supine data and Random Forrest using 240-second standing data respectively achieved RMSE 2.89 ml/kg/min (344 m), and MAE 2.27 ml/kg/min (270 m), and RMSE 2.82 ml/kg/min (336 m), and MAE 2.26 ml/kg/min (269 m). Compared to a demographics-only baseline for Random Forest returning RMSE of 3.15 ml/kg/min (375 m) and MAE 2.39 ml/kg/min (285 m), the inclusion of HRV features provided a modest but consistent improvement in predictive accuracy. Age, experience, maturity offset, and non-linear HRV features (symbolic dynamics, Higuchi’s Fractal Dimension) were most influential. Discussion ML models combining basic characteristics and short-term HRV showed moderate performance. The incremental improvement attributable to HRV was modest, and these exploratory models are not currently ready to replace Yo-Yo field testing or guide individual training decisions.
No takes yet. Share an insight, caveat, or question.
Korzeniewski et al. (2026) conducted a cross-sectional in Healthy youth male soccer players (n=237). Machine learning models combining demographic data and short-term resting HRV vs. Demographics-only baseline model was evaluated on Prediction accuracy (RMSE) of Yo-Yo IR1-derived estimated VO2max (RMSE reduction of 0.33 ml/kg/min). Machine learning models combining demographic data with short-term resting heart rate variability provided a modest improvement in predicting aerobic endurance fitness compared to demographics alone, reducing RMSE by 0.33 ml/kg/min.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: