Influence of Perceptions of Sleep on Well-Being in Youth Athletes

Predicting daily recovery during long-term endurance training using machine learning analysis

PURPOSE

The aim of this study was to determine if machine learning models could predict the perceived morning recovery status (AM PRS) and daily change in heart rate variability (HRV change) of endurance athletes based on training, dietary intake, sleep, HRV, and subjective well-being measures.

METHODS

Self-selected nutrition intake, exercise training, sleep habits, HRV, and subjective well-being of 43 endurance athletes ranging from professional to recreationally trained were monitored daily for 12 weeks (3572 days of tracking). Global and individualized models were constructed using machine learning techniques, with the single best algorithm chosen for each model. The model performance was compared with a baseline intercept-only model.

RESULTS

Prediction error (root mean square error [RMSE]) was lower than baseline for the group models (11.8 vs. 14.1 and 0.22 vs. 0.29 for AM PRS and HRV change, respectively). At the individual level, prediction accuracy outperformed the baseline model but varied greatly across participants (RMSE range 5.5-23.6 and 0.05-0.44 for AM PRS and HRV change, respectively).

CONCLUSION

At the group level, daily recovery measures can be predicted based on commonly measured variables, with a small subset of variables providing most of the predictive power. However, at the individual level, the key variables may vary, and additional data may be needed to improve the prediction accuracy.

Sleep Indices and Cardiac Autonomic Activity Responses during an International Tournament in a Youth National Soccer Team

This study aimed to describe habitual sleep and nocturnal cardiac autonomic activity (CAA), and their relationship with training/match load in male youth soccer players during an international tournament. Eighteen elite male youth soccer players (aged 14.8 ± 0.3 years; mean ± SD) participated in the study. Sleep indices were measured using wrist actigraphy, and heart rate (HR) monitors were used to measure CAA during night-sleep throughout 5 consecutive days. Training and match loads were characterized using the session-rating of perceived exertion (s-RPE). During the five nights 8 to 17 players slept less than <8 h and only one to two players had a sleep efficiency <75%. Players' sleep duration coefficient of variation (CV) ranged between 4 and 17%. Nocturnal heart rate variability (HRV) indices for the time-domain analyses ranged from 3.8 (95% confidence interval, 3.6; 4.0) to 4.1 ln[ms] (3.9; 4.3) and for the frequency-domain analyses ranged from 5.9 (5.6; 6.5) to 6.6 (6.3; 7.4). Time-domain HRV CV ranged from 3 to 10% and frequency-domain HRV ranged from 2 to 12%. A moderate within-subjects correlation was found between s-RPE and sleep duration [r = -0.41 (-0.62; -0.14); p = 0.003]. The present findings suggest that youth soccer players slept less than the recommended during the international tournament, and sleep duration was negatively associated with training/match load.

Training Schedule and Sleep in Adolescent Swimmers

PURPOSE

Insufficient sleep duration may affect athletic performance and health. Inconsistent sleep pattern also has negative health effects, but studies on athletes' intraindividual sleep variability are scarce. The aim of this research was to compare total sleep time (TST) and variability (TST-variability), wakening after sleep onset, and sleep efficiency, during nights preceding early morning practices with other nights, and to investigate sleep characteristics of nights following a day with early morning only, evening only, or both a morning and an evening session in adolescent swimmers.

METHODS

Wrist-worn accelerometers were used to measure 1 week of sleep in 108 swimmers (mean age 16.1 [2.6] y) in Iceland. Adjusted regression analyses and linear mixed models were used to explore associations of training schedules with TST, TST-variability, wakening after sleep onset, and sleep efficiency.

RESULTS

Mean TST was 6:32 (h:min) (±39 min) and TST-variability was 63 minutes (±25 min). TST decreased and TST-variability increased with more early morning practices. TST preceding early training was 5:36 and 5:06 in <16- and ≥16-year-olds, respectively, shorter than on nights preceding later or no morning training (P < .001).

CONCLUSION

Swimmers have extremely short TST preceding early morning sessions and increased TST-variability with more early morning sessions.