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.

Informal Peer Interaction and Practice Type as Predictors of Physician Performance on Maintenance of Certification Examinations.

IMPORTANCE: Physicians can demonstrate mastery of the knowledge that supports continued clinical competence by passing a maintenance of certification examination (MOCEX). Performance depends on professional learning and development, which may be enhanced by informal routine interactions with colleagues. Some physicians, such as those in solo practice, may have less opportunity for peer interaction, thus negatively influencing their examination performance. OBJECTIVE: To determine the relationship among level of peer interaction, group and solo practice, and MOCEX performance. DESIGN, SETTING, AND PARTICIPANTS: Longitudinal cohort study of 568 surgeons taking the 2008 MOCEX. Survey responses reporting the level of physicians' peer interactions and their practice type were related to MOCEX scores, controlling for initial qualifying examination scores, practice type, and personal characteristics. EXPOSURES: Solo practice and amount of peer interaction. MAIN OUTCOMES AND MEASURES: Scores on the MOCEX and pass-fail status. RESULTS: Of the 568 surgeons in the study sample, 557 (98.1%) passed the examination. Higher levels of peer interaction were associated with a higher score (ß = 0.91 [95% CI, 0.31-1.52]) and higher likelihood of passing the examination (odds ratio, 2.58 [1.08-6.16]). Physicians in solo (vs group) practice had fewer peer interactions (ß = -0.49 [95% CI, -0.64 to -0.33), received lower scores (ß = -1.82 [-2.94 to -0.82]), and were less likely to pass the examination (odds ratio, 0.22 [0.06-0.77]). Level of peer interaction moderated the relationship between solo practice and MOCEX score; solo practitioners with high levels of peer interaction achieved an MOCEX performance on a par with that of group practitioners. CONCLUSIONS AND RELEVANCE: Physicians in solo practice had poorer MOCEX performance. However, solo practitioners who reported high levels of peer interaction performed as well as those in group practice. Peer interaction is important for professional learning and quality of care.