Automated Scoring of Respiratory Events in Sleep With a Single Effort Belt and Deep Neural Networks.

OBJECTIVE: Automatic detection and analysis of respiratory events in sleep using a single respiratoryeffort belt and deep learning. METHODS: Using 9,656 polysomnography recordings from the Massachusetts General Hospital (MGH), we trained a neural network (WaveNet) to detect obstructive apnea, central apnea, hypopnea and respiratory-effort related arousals. Performance evaluation included event-based analysis and apnea-hypopnea index (AHI) stratification. The model was further evaluated on a public dataset, the Sleep-Heart-Health-Study-1, containing 8,455 polysomnographic recordings. RESULTS: For binary apnea event detection in the MGH dataset, the neural network obtained a sensitivity of 68%, a specificity of 98%, a precision of 65%, a F1-score of 67%, and an area under the curve for the receiver operating characteristics curve and precision-recall curve of 0.93 and 0.71, respectively. AHI prediction resulted in a mean difference of 0.41 ± 7.8 and a r2 of 0.90. For the multiclass task, we obtained varying performances: 84% of all labeled central apneas were correctly classified, whereas this metric was 51% for obstructive apneas, 40% for respiratory effort related arousals and 23% for hypopneas. CONCLUSION: Our fully automated method can detect respiratory events and assess the AHI accurately. Differentiation of event types is more difficult and may reflect in part the complexity of human respiratory output and some degree of arbitrariness in the criteria used during manual annotation. SIGNIFICANCE: The current gold standard of diagnosing sleep-disordered breathing, using polysomnography and manual analysis, is time-consuming, expensive, and only applicable in dedicated clinical environments. Automated analysis using a single effort belt signal overcomes these limitations.

Impact of stimulus duration on motor unit thresholds and alternation in compound muscle action potential scans.

OBJECTIVE: To investigate the impact of stimulus duration on motor unit (MU) thresholds and alternation within compound muscle action potential (CMAP) scans. METHODS: The stimulus duration (0.1, 0.2, 0.6, and 1.0 ms) in thenar CMAP scans and individual MUs of 14 healthy subjects was systematically varied. We quantified variability of individual MU's thresholds by relative spread (RS), MU thresholds by stimulus currents required to elicit target CMAPs of 5% (S5), 50% (S50) and 95% (S95) of the maximum CMAP, and relative range (RR) by 100*[S95-S5]/S50. We further assessed the strength-duration time constant (SDTC). Experimental observations were subsequently simulated to quantify alternation. RESULTS: RS, unaffected by stimulus duration, was 1.65% averaged over all recordings. RR increased for longer stimulus duration (11.4% per ms, p < 0.001). SDTC shortened with higher target CMAPs (0.007 ms per 10% CMAP, p < 0.001). Experiments and simulations supported that this may underlie the increased RR. A short compared to long stimulus duration recruited relative more MUs at S50 (more alternation) than at the tails (less alternation). CONCLUSIONS: The stimulus duration significantly affects MU threshold distribution and alternation within CMAP scans. SIGNIFICANCE: Stimulation settings can be further optimized and their standardization is preferred when using CMAP scans for monitoring neuromuscular diseases.