Shining a Light on Athletes Sleep: Development of a Screening Nomogram to Flag Athletes at Risk of Poor Sleep Quality

BackgroundEmerging research indicates that light exposure may influence sleep quality. Identifying key light-exposure behaviours associated with poor sleep quality in athletes may allow practitioners to efficiently screen for sleep difficulties and prioritise athletes for further assessment. Translating these findings into a practical screening tool could enhance willingness of high-performance professionals to monitor sleep and light exposure in athletes. HypothesisKey predictor variables identified by feature reduction techniques will lead to higher predictive accuracy in determining which light behaviours are associated with poor sleep quality in athletes. Study DesignCross-sectional study. Level of EvidenceLevel 3. Methods121 athletes from varying competitive levels completed questionnaires, including the Light Exposure Behaviour Assessment (LEBA) and Pittsburgh Sleep Quality Index (PSQI). Poor sleep quality was defined using the PSQI cut-off >5. Least absolute shrinkage and selection operator (LASSO) regression identified light exposure variables from the LEBA questionnaire most strongly associated with good and poor sleep quality in athletes. Three models were compared: a full-variable model (23 items), a factor-specific model (Factor 3: screen/device use), and a feature-reduced model (LASSO-selected items). ResultsPhone use before bed, checking phone/watch during the night, were identified as variables of greatest association with poor sleep quality and used for reduced feature set modelling. On an independent test set, the feature-reduced model achieved area under the curve (AUC) 0.83, sensitivity 0.70, and specificity 0.92. ConclusionsOur findings report that phone-related behaviours before and in bed are associated with a higher likelihood of poor sleep quality. These behaviours, combined with the developed nomogram, provide a preliminary, low-burden screening tool to identify athletes who may be experiencing sleep difficulties. The high specificity indicates that athletes flagged by the tool are likely to have genuine poor sleep quality, warranting further assessment to identify underlying causes and appropriate interventions. Clinical RelevanceEducation and interventions focused on light exposure factors were identified as most influencing sleep quality in a multifaceted athletic population and could be prioritised to optimise sleep quality. The developed sleep quality nomogram may be useful as a decision-making tool to improve sleep monitoring practice among practitioners.