Sleep apnea is caused by several endophenotypic traits, namely pharyngeal collapsibility, poor muscle compensation, ventilatory instability (high loop gain), and arousability from sleep (low arousal threshold). Measures of these traits have shown promise for predicting outcomes of therapies (e.g. oral appliances, surgery, hypoglossal nerve stimulation, CPAP, and pharmaceuticals), which may become an integral part of precision sleep medicine. Currently the methods Sands et al. [1] developed for endotyping sleep apnea from polysomnography (PSG) are embedded in the original authors’ code, which is computationally expensive and requires technological expertise to run. We present a re-implementation and validation of the integrity of the original authors’ code by reproducing the endo-Phenotype Using Polysomnography (PUP) method of Sands et al. [1, 2] The original MATLAB methods were reprogrammed in Python; efficient methods were developed to detect breaths, calculate normalized ventilation (moving time-average), and model ventilatory drive (intended ventilation). The new implementation (PUPpy) was validated by comparing the endotypes from PUPpy with the original PUP results. Both endotyping methods were applied to 38 manually scored polysomnographic studies. Results of the new implementation were strongly correlated with the original (p<10 -6 for all): ventilation at eupnea V̇passive (ICC=0.97), ventilation at arousal onset V̇active (ICC=0.97), loop-gain (ICC=0.96), and arousal threshold (ICC=0.90). We successfully implemented the original method by Sands et.al. [1, 2] providing further evidence of its integrity. Additionally, we created a cloud-based version for scaling up sleep apnea endotyping that can be used more easily by a wider audience of researchers and clinicians.
We present a method for classifying target sleep arousal regions of polysomnographies. Time-and frequencydomain features of clinical and statistical origins were derived from the polysomnography signals and the features fed into a Bidirectional Recurrent Neural Network, using Long Short-Term Memory units (BRNN-LSTM). The predictions of five recurrent neural networks, trained using different features and training sets, were averaged for each sample, to yield a more robust classifier. The proposed method was developed and validated on the PhysioNet Challenge dataset which consisted of a training set of 994 subjects and a hidden test set of 989 subjects. Five-fold cross-validation on the training set resulted in an area under precision-recall curve (AUPRC) score of 0.452, an area under receiver operating characteristic curve (AUROC) score of 0.901 and intraclass correlation ICC(2,1) of 0.59. The classifier was further validated on the PhysioNet Challenge test set, resulting in an AUPRC score of 0.45.
Purpose
In this proof of principle study, we evaluated the diagnostic accuracy of the novel Nox BodySleepTM 1.0 algorithm (Nox Medical, Iceland) for the estimation of disease severity and sleep stages based on features extracted from actigraphy and respiratory inductance plethysmography (RIP) belts. Validation was performed against in-lab polysomnography (PSG) in patients with sleep-disordered breathing (SDB).
Methods
Patients received PSG according to AASM. Sleep stages were manually scored using the AASM criteria and the recording was evaluated by the novel algorithm. The results were analyzed by descriptive statistics methods (IBM SPSS Statistics 25.0).
Results
We found a strong Pearson correlation (r=0.91) with a bias of 0.2/h for AHI estimation as well as a good correlation (r=0.81) and an overestimation of 14 min for total sleep time (TST). Sleep efficiency (SE) was also valued with a good Pearson correlation (r=0.73) and an overestimation of 2.1%. Wake epochs were estimated with a sensitivity of 0.65 and a specificity of 0.59 while REM and non-REM (NREM) phases were evaluated a sensitivity of 0.72 and 0.74, respectively. Specificity was 0.74 for NREM and 0.68 for REM. Additionally, a Cohen’s kappa of 0.62 was found for this 3-class classification problem.
Conclusion
The algorithm shows a moderate diagnostic accuracy for the estimation of sleep. In addition, the algorithm determines the AHI with good agreement with the manual scoring and it shows good diagnostic accuracy in estimating wake-sleep transition. The presented algorithm seems to be an appropriate tool to increase the diagnostic accuracy of portable monitoring. The validated diagnostic algorithm promises a more appropriate and cost-effective method if integrated in out-of-center (OOC) testing of patients with suspicion for SDB.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.