Obstructive sleep apnea (OSA) is a chronic and prevalent condition with well-established comorbidities. However, many severe cases remain undiagnosed due to poor access to polysomnography (PSG), the gold standard for OSA diagnosis. Accurate home-based methods to screen for OSA are needed, which can be applied inexpensively to high-risk subjects to identify those that require PSG to fully assess their condition. A number of methods that analyse speech or breathing sounds to screen for OSA have been previously investigated. However, these methods have constraints that limit their use in home environments (e.g., they require specialised equipment, are not robust to background noise, are obtrusive or depend on tightly controlled conditions). This paper proposes a novel method to screen for OSA, which analyses sleep breathing sounds recorded with a smartphone at home. Audio recordings made over a whole night are divided into segments, each of which is classified for the presence or absence of OSA by a deep neural network. The apneahypopnea index estimated from the segments predicted as containing evidence of OSA is then used to screen for the condition. Audio recordings made during home sleep apnea testing from 103 participants for 1 or 2 nights were used to develop and evaluate the proposed system. When screening for moderate OSA the acoustics based system achieved a sensitivity of 0.79 and a specificity of 0.80. The sensitivity and specificity when screening for severe OSA were 0.78 and 0.93, respectively. The system is suitable for implementation on consumer smartphones.

Sleep-disordered breathing (SDB) is a serious and prevalent condition, and acoustic analysis via consumer devices (e.g. smartphones) offers a low-cost solution to screening for it. We present a novel approach for the acoustic identification of SDB sounds, such as snoring, using bottleneck features learned from a corpus of whole-night sound recordings. Two types of bottleneck features are described, obtained by applying a deep autoencoder to the output of an auditory model or a short-term autocorrelation analysis. We investigate two architectures for snore sound detection: a tandem system and a hybrid system. In both cases, a 'language model' (LM) was incorporated to exploit information about the sequence of different SDB events. Our results show that the proposed bottleneck features give better performance than conventional mel-frequency cepstral coefficients, and that the tandem system outperforms the hybrid system given the limited amount of labelled training data available. The LM made a small improvement to the performance of both classifiers.

This is a repository copy of Snorer diarisation based on deep neural network embeddings.

Introduction Analysis of sleep breathing sounds has been employed to screen obstructive sleep apnea (OSA). However, most current methods rely on specialized equipment (e.g., tracheal microphones), require additional physiological data (e.g., oxygen saturation), are rule-based, or are trained on data collected in-lab, making them less suitable for home use. In this study, deep learning methods were leveraged to explore the hypothesis that sleep audio recordings collected via smartphones can be used alone to screen for OSA by exploiting the temporal pattern of respiration sounds. Methods Adult participants with suspected sleep-disordered breathing of varying degrees of severity were recruited from the general population and from GP referrals to sleep clinic. Audio recordings were collected via smartphones during home sleep apnea testing (HSAT). HSAT data were scored by a registered polysomnographic technologist in accordance with current international guidelines (AASM V2.5, 2018) and used as reference. To exploit acoustic respiration temporal pattern, time interval histograms were computed for sequences of audio-words that were automatically learned from spectral features with a deep neural network. Means and standard deviations of the time intervals for each audio-word were employed by a Gaussian mixture model to classify 2-minute audio recording segments as either containing OSA events or not. Results Preliminary data from 4 valid nights’ recordings obtained from 2 consented participants was analysed. 550 segments were used for training, with 180 segments used for evaluation. Audio recording demonstrated a sensitivity of 0.71 and specificity of 0.66 when compared with manually-scored HSAT. Conclusion Preliminary results suggest that an approach to OSA screening based on deep learning with inter-audio-word intervals to capture information about respiration temporal pattern may be a useful tool in diagnosis of OSA. Further model development is underway using data collected from up to 200 patients and full study data will be presented. Support The project is supported by an Innovate UK grant (project number 157358). HR is supported by a joint scholarship from Passion for Life Healthcare Ltd and University of Sheffield. LH acknowledges the financial support of NHS Research Scotland (NRS), through NHS Lothian.

Obstructive sleep apnea (OSA) is a chronic and prevalent condition with well-established comorbidities. Due to limited diagnostic resources and high cost, a significant OSA population lives undiagnosed, and accurate and low-cost methods to screen for OSA are needed. We propose a novel screening method based on breathing sounds recorded with a smartphone and respiratory effort. Whole night recordings are divided into 30-s segments, each of which is classified for the presence or absence of OSA events by a multimodal deep neural network. Data fusion techniques were investigated and evaluated based on the apnea-hypopnea index estimated from whole night recordings. Real-world recordings made during home sleep apnea testing from 103 participants were used to develop and evaluate the proposed system. The late fusion system achieved the best sensitivity and specificity when screening for severe OSA, at 0.93 and 0.92, respectively. This offers the prospect of inexpensive OSA screening at home.