Addressing wearable sleep tracking inequity: a new dataset and novel methods for a population with sleep disorders

Sleep is crucial for health, and recent advances in wearable technology and machine learning offer promising methods for monitoring sleep outside the clinical setting. However, sleep tracking using wearables is challenging, particularly for those with irregular sleep patterns or sleep disorders. In this study, we introduce a dataset collected from 100 patients from the Duke Sleep Disorders Center who wore an Empatica E4 smartwatch during an overnight sleep study with concurrent clinical-grade polysomnography (PSG) recording. This dataset encompasses diverse demographics and medical conditions. We further introduce a new methodology that addresses the limitations of existing modeling methods when applied on patients with sleep disorders. Namely, we address the inability of existing models to account for 1) temporal relationships while leveraging relatively small data, by introducing a LSTM post-processing method, and 2) group-wise characteristics that impact classification task performance (i.e., random effects), by ensembling mixed-effects boosted tree models. This approach was highly successful for sleep onset and wakefulness detection in this sleep disordered population, achieving an F1 score of 0.823 +/- 0.019, an AUROC of 0.926 +/- 0.016, and a 0.695 +/- 0.025 Cohen's Kappa. Overall, we demonstrate the utility of both the data that we collected, as well as our unique approach to address the existing gap in wearable-based sleep tracking in sleep disordered populations.