Alan R Schwartz1, Mairav Cohen-Zion2, Luu V Pham3, Amit Gal4, Mudiaga Sowho5, Francis P Sgambati3, Tracy Klopfer5, Michelle A Guzman5, Erin M Hawks5, Tamar Etzioni6, Laura Glasner7, Eran Druckman8, Giora Pillar6. 1. Johns Hopkins Sleep Disorders Center, Baltimore, MD, USA; Johns Hopkins Center for Interdisciplinary Sleep Research and Education, Baltimore, MD, USA(1); University of Pennsylvania Perelman School of Medicine, USA. Electronic address: aschwar02@gmail.com. 2. The Academic College of Tel Aviv-Jaffa, Tel Aviv, Israel; DayZz Live Well Ltd, Herzeliya, Israel. 3. Johns Hopkins Sleep Disorders Center, Baltimore, MD, USA; Johns Hopkins Center for Interdisciplinary Sleep Research and Education, Baltimore, MD, USA(1). 4. The Open University, Raanana, Israel. 5. Johns Hopkins Sleep Disorders Center, Baltimore, MD, USA. 6. Carmel Medical Center, Haifa, Israel; Technion School of Medicine, Haifa, Israel. 7. DayZz Live Well Ltd, Herzeliya, Israel; Sheba Medical Center, Ramat Gan, Israel. 8. Druckman Research and Statistics, Rishon Lezion, Israel.
Abstract
INTRODUCTION: We developed and validated an abbreviated Digital Sleep Questionnaire (DSQ) to identify common societal sleep disturbances including insomnia, delayed sleep phase syndrome (DSPS), insufficient sleep syndrome (ISS), and risk for obstructive sleep apnea (OSA). METHODS: The DSQ was administered to 3799 community volunteers, of which 2113 were eligible and consented to the study. Of those, 247 were interviewed by expert sleep physicians, who diagnosed ≤2 sleep disorders. Machine Learning (ML) trained and validated separate models for each diagnosis. Regularized linear models generated 15-200 features to optimize diagnostic prediction. Models were trained with five-fold cross-validation (repeated five times), followed by robust validation testing. ElasticNet models were used to classify true positives and negatives; bootstrapping optimized probability thresholds to generate sensitivities, specificities, accuracies, and area under the receiver operating curve (AUC). RESULTS: Compared to reference subgroups, physician-diagnosed sleep disorders were marked by DSQ evidence of sleeplessness (insomnia, DSPS, OSA), sleep debt (DSPS, ISS), airway obstruction during sleep (OSA), blunted circadian variability in alertness (DSPS), sleepiness (DSPS and ISS), increased alertness (insomnia) and global impairment in sleep-related quality of life (all sleep disorders). ElasticNet models validated each diagnosis with high sensitivity (80-83%), acceptable specificity (63-69%), high AUC (0.80-0.85) and good accuracy (agreement with physician diagnoses, 68-73%). DISCUSSION: A brief DSQ readily engaged and efficiently screened a large population for common sleep disorders. Powered by ML, the DSQ can accurately classify sleep disturbances, demonstrating the potential for improving the sleep, health, productivity and safety of populations.
INTRODUCTION: We developed and validated an abbreviated Digital Sleep Questionnaire (DSQ) to identify common societal sleep disturbances including insomnia, delayed sleep phase syndrome (DSPS), insufficient sleep syndrome (ISS), and risk for obstructive sleep apnea (OSA). METHODS: The DSQ was administered to 3799 community volunteers, of which 2113 were eligible and consented to the study. Of those, 247 were interviewed by expert sleep physicians, who diagnosed ≤2 sleep disorders. Machine Learning (ML) trained and validated separate models for each diagnosis. Regularized linear models generated 15-200 features to optimize diagnostic prediction. Models were trained with five-fold cross-validation (repeated five times), followed by robust validation testing. ElasticNet models were used to classify true positives and negatives; bootstrapping optimized probability thresholds to generate sensitivities, specificities, accuracies, and area under the receiver operating curve (AUC). RESULTS: Compared to reference subgroups, physician-diagnosed sleep disorders were marked by DSQ evidence of sleeplessness (insomnia, DSPS, OSA), sleep debt (DSPS, ISS), airway obstruction during sleep (OSA), blunted circadian variability in alertness (DSPS), sleepiness (DSPS and ISS), increased alertness (insomnia) and global impairment in sleep-related quality of life (all sleep disorders). ElasticNet models validated each diagnosis with high sensitivity (80-83%), acceptable specificity (63-69%), high AUC (0.80-0.85) and good accuracy (agreement with physician diagnoses, 68-73%). DISCUSSION: A brief DSQ readily engaged and efficiently screened a large population for common sleep disorders. Powered by ML, the DSQ can accurately classify sleep disturbances, demonstrating the potential for improving the sleep, health, productivity and safety of populations.
Authors: Rebecca Robbins; Matthew D Weaver; Stuart F Quan; Jason P Sullivan; Mairav Cohen-Zion; Laura Glasner; Salim Qadri; Charles A Czeisler; Laura K Barger Journal: PLoS One Date: 2022-01-05 Impact factor: 3.240