Haresh T Suppiah1,2, Richard Swinbourne3, Jericho Wee2,4, Qixiang He2,5, Johan Pion6,7, Matthew W Driller1, Paul B Gastin1, David L Carey1. 1. Sport and Exercise Science, School of Allied Health, Human Services and Sport, La Trobe University, Melbourne, Victoria, Australia. 2. National Youth Sports Institute, Singapore. 3. Singapore Sport Institute, Singapore. 4. Human Potential Translational Research Programme, Yong Loo Lin School of Medicine, National University of Singapore, Singapore. 5. Nanyang Technological University, Singapore. 6. HAN University of Applied Sciences, Arnhem, Netherlands. 7. Movement and Sports Sciences, Ghent University, Ghent, Belgium.
Abstract
BACKGROUND: Identifying key variables that predict sleep quality in youth athletes allows practitioners to monitor the most parsimonious set of variables that can improve athlete buy-in and compliance for athlete self-report measurement. Translating these findings into a decision-making tool could facilitate practitioner willingness to monitor sleep in athletes. HYPOTHESIS: Key predictor variables, identified by feature reduction techniques, will lead to higher predictive accuracy in determining youth athletes with poor sleep quality. STUDY DESIGN: Cross-sectional study. LEVEL OF EVIDENCE: Level 3. METHODS: A group (N = 115) of elite youth athletes completed questionnaires consisting of the Pittsburgh Sleep Quality Index and questions on sport participation, training, sleep environment, and sleep hygiene habits. A least absolute shrinkage and selection operator regression model was used for feature reduction and to select factors to train a feature-reduced sleep quality classification model. These were compared with a classification model utilizing the full feature set. RESULTS: Sport type, training before 8 am, training hours per week, presleep computer usage, presleep texting or calling, prebedtime reading, and during-sleep time checks on digital devices were identified as variables of greatest influence on sleep quality and used for the reduced feature set modeling. The reduced feature set model performed better (area under the curve, 0.80; sensitivity, 0.57; specificity, 0.80) than the full feature set models in classifying youth athlete sleep quality. CONCLUSION: The findings of our study highlight that sleep quality of elite youth athletes is best predicted by specific sport participation, training, and sleep hygiene habits. CLINICAL RELEVANCE: Education and interventions around the training and sleep hygiene factors that were identified to most influence the sleep quality of youth athletes could be prioritized to optimize their sleep characteristics. The developed sleep quality nomogram may be useful as a decision-making tool to improve sleep monitoring practice among practitioners.
BACKGROUND: Identifying key variables that predict sleep quality in youth athletes allows practitioners to monitor the most parsimonious set of variables that can improve athlete buy-in and compliance for athlete self-report measurement. Translating these findings into a decision-making tool could facilitate practitioner willingness to monitor sleep in athletes. HYPOTHESIS: Key predictor variables, identified by feature reduction techniques, will lead to higher predictive accuracy in determining youth athletes with poor sleep quality. STUDY DESIGN: Cross-sectional study. LEVEL OF EVIDENCE: Level 3. METHODS: A group (N = 115) of elite youth athletes completed questionnaires consisting of the Pittsburgh Sleep Quality Index and questions on sport participation, training, sleep environment, and sleep hygiene habits. A least absolute shrinkage and selection operator regression model was used for feature reduction and to select factors to train a feature-reduced sleep quality classification model. These were compared with a classification model utilizing the full feature set. RESULTS: Sport type, training before 8 am, training hours per week, presleep computer usage, presleep texting or calling, prebedtime reading, and during-sleep time checks on digital devices were identified as variables of greatest influence on sleep quality and used for the reduced feature set modeling. The reduced feature set model performed better (area under the curve, 0.80; sensitivity, 0.57; specificity, 0.80) than the full feature set models in classifying youth athlete sleep quality. CONCLUSION: The findings of our study highlight that sleep quality of elite youth athletes is best predicted by specific sport participation, training, and sleep hygiene habits. CLINICAL RELEVANCE: Education and interventions around the training and sleep hygiene factors that were identified to most influence the sleep quality of youth athletes could be prioritized to optimize their sleep characteristics. The developed sleep quality nomogram may be useful as a decision-making tool to improve sleep monitoring practice among practitioners.
Authors: Hugh H K Fullagar; Sabrina Skorski; Rob Duffield; Daniel Hammes; Aaron J Coutts; Tim Meyer Journal: Sports Med Date: 2015-02 Impact factor: 11.136
Authors: Markus Dworak; Alfred Wiater; Dirk Alfer; Egon Stephan; Wildor Hollmann; Heiko K Strüder Journal: Sleep Med Date: 2007-07-17 Impact factor: 3.492
Authors: Angelos Vlahoyiannis; George Aphamis; Gregory C Bogdanis; Giorgos K Sakkas; Eleni Andreou; Christoforos D Giannaki Journal: J Sport Health Sci Date: 2020-03-19 Impact factor: 7.179