Brief digital sleep questionnaire powered by machine learning prediction models identifies common sleep disorders.

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.

The Efficacy of Low-Level Continuous Positive Airway Pressure for the Treatment of Snoring.

STUDY OBJECTIVES: To assess effects of low-level continuous positive airway pressure (CPAP) on snoring in habitual snorers without obstructive sleep apnea (OSA). METHODS: A multicenter prospective in-laboratory reversal crossover intervention trial was conducted between September 2013 and August 2014. Habitual snorers were included if they snored (inspiratory sound pressure level ≥ 40 dBA) for ≥ 30% all sleep breaths on a baseline sleep study (Night 1), and if significant OSA and daytime somnolence were absent. Included participants then underwent a CPAP titration study at 2, 4, or 6 cm H2O (Night 2) to examine snoring responses to step-increases in nasal pressure, a treatment night at optimal pressure (Night 3), followed by baseline night (Night 4). At each pressure, snoring intensity was measured on each breath. Snoring frequency was quantified as a percentage of sleep breaths at thresholds of 40, 45, 50, and 55 dBA. Sleep architecture and OSA severity were characterized using standard measurements. RESULTS: On baseline sleep studies, participants demonstrated snoring at ≥ 40 dBA on 53 ± 3% and ≥ 45 dBA on 35 ± 4% of breaths. Snoring frequency decreased progressively as nasal pressure increased from 0 to 4 cm H2O at each threshold, and plateaued thereafter. CPAP decreased snoring frequency by 67% and 85% at 40 and 45 dBA, respectively. Intervention did not alter sleep architecture and sleep apnea decreased minimally. CONCLUSIONS: Low-level CPAP below the range required to treat OSA diminished nocturnal snoring, and produced uniform reduction in nightly noise production below the World Health Organization's limit of 45 dBA. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov, identifier: NCT01949584.