Changes in tongue morphology predict responses in pharyngeal patency to selective hypoglossal nerve stimulation.

STUDY OBJECTIVES: The major goal of the study was to determine whether changes in tongue morphology under selective hypoglossal nerve therapy for obstructive sleep apnea were associated with alterations in airway patency during sleep when specific portions of the hypoglossal nerve were stimulated. METHODS: This case series was conducted at the Johns Hopkins Sleep Disorders Center at Johns Hopkins Bayview Medical Center. Twelve patients with apnea implanted with a multichannel targeted hypoglossal nerve-stimulating system underwent midsagittal ultrasound tongue imaging during wakefulness. Changes in tongue shape were characterized by measuring the vertical height and polar dimensions between tongue surface and genioglossi origin in the mandible. Changes in patency were characterized by comparing airflow responses between stimulated and adjacent unstimulated breaths during non-rapid eye movement sleep. RESULTS: Two distinct morphologic responses were observed. Anterior tongue base and hyoid-bone movement (5.4 [0.4] to 4.1 [1.0] cm (median and [interquartile range]) with concomitant increases in tongue height (5.0 [0.9] to 5.6 [0.7] cm) were associated with decreases in airflow during stimulation. In contrast, comparable anterior hyoid movement (tongue protrusion from 5.8 [0.5] to 4.5 [0.9] cm) without significant increases in height (5.2 [1.6] to 4.6 [0.8] cm) were associated with marked increases in airflow during sleep. CONCLUSIONS: Tongue protrusion with preservation of tongue shape predicted increases in patency, whereas anterior movement with concomitant increases in height were associated with decreased pharyngeal patency. These findings suggest that pharyngeal patency can be best stabilized by stimulating lingual muscles that maintain tongue shape while protruding the tongue, thereby preventing it from prolapsing posteriorly during sleep. CITATION: Fleury Curado T, Pham L, Otvos T, et al. Changes in tongue morphology predict responses in pharyngeal patency to selective hypoglossal nerve stimulation. J Clin Sleep Med. 2023;19(5):947-955.

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.