Automatic snoring sounds detection from sleep sounds based on deep learning

Distinguishing severe sleep apnea from habitual snoring using a neck-wearable piezoelectric sensor and deep learning: A pilot study

This study explores the development of a deep learning model using a neck-wearable piezoelectric sensor to accurately distinguish severe sleep apnea syndrome (SAS) from habitual snoring, addressing the underdiagnosis of SAS in adults. From 2018 to 2020, 60 adult habitual snorers underwent polysomnography while wearing a neck piezoelectric sensor that recorded snoring vibrations (70-250 Hz) and carotid artery pulsations (0.01-1.5 Hz). The initial dataset comprised 1167 silence, 1304 snoring, and 399 noise samples from 20 participants. Using a hybrid deep learning model comprising a one-dimensional convolutional neural network and gated-recurrent unit, the model identified snoring and apnea/hypopnea events, with sleep phases detected via pulse wave variability criteria. The model's efficacy in predicting severe SAS was assessed in the remaining 40 participants, achieving snoring detection rates of 0.88, 0.86, and 0.92, with respective loss rates of 0.39, 0.90, and 0.23. Classification accuracy for severe SAS improved from 0.85 for total sleep time to 0.90 for partial sleep time, excluding the first sleep phase, demonstrating precision of 0.84, recall of 1.00, and an F1 score of 0.91. This innovative approach of combining a hybrid deep learning model with a neck-wearable piezoelectric sensor suggests a promising route for early and precise differentiation of severe SAS from habitual snoring, aiding guiding further standard diagnostic evaluations and timely patient management. Future studies should focus on expanding the sample size, diversifying the patient population, and external validations in real-world settings to enhance the robustness and applicability of the findings.

Implementing deep learning on edge devices for snoring detection and reduction

This study introduces MinSnore, a novel deep learning model tailored for real-time snoring detection and reduction, specifically designed for deployment on low-configuration edge devices. By integrating MobileViTV3 blocks into the Dynamic MobileNetV3 backbone model architecture, MinSnore leverages both Convolutional Neural Networks (CNNs) and transformers to deliver enhanced feature representations with minimal computational overhead. The model was pre-trained on a diverse dataset of 46,349 audio files using the Self-Supervised Learning with Barlow Twins (SSL-BT) method, followed by fine-tuning on 17,355 segmented clips extracted from this dataset. MinSnore represents a significant breakthrough in snoring detection, achieving an accuracy of 96.37 %, precision of 96.31 %, recall of 94.12 %, and an F1-score of 95.02 %. When deployed on a single-board computer like a Raspberry Pi, the system demonstrated a reduction in snoring duration during real-world experiments. These results underscore the importance of this work in addressing sleep-related health issues through an efficient, low-cost, and highly accurate snoring mitigation solution.

Cascaded redundant convolutional encoder-decoder network improved apnea detection performance using tracheal sounds in post anesthesia care unit patients

Objective. Methods of detecting apnea based on acoustic features can be prone to misdiagnosed and missed diagnoses due to the influence of noise. The aim of this paper is to improve the performance of apnea detection algorithms in the Post Anesthesia Care Unit (PACU) using a denoising method that processes tracheal sounds without the need for separate background noise.Approach. Tracheal sound data from laboratory subjects was collected using a microphone. Record a segment of clinical background noise and clean tracheal sound data to synthesize the noisy tracheal sound data according to a specified signal-to-noise ratio. Extract the frequency-domain features of the tracheal sounds using the Short Time Fourier Transform (STFT) and input the Cascaded Redundant Convolutional Encoder-Decoder network (CR-CED) network for training. Patients' tracheal sound data collected in the PACU were then fed into the CR-CED network as test data and inversely transformed by STFT to obtain denoised tracheal sounds. The apnea detection algorithm was used to detect the tracheal sound after denoising.Results. Apnea events were correctly detected 207 times and normal respiratory events 11,305 times using tracheal sounds denoised by the CR-CED network. The sensitivity and specificity of apnea detection were 88% and 98.6%, respectively.Significance. The apnea detection results of tracheal sounds after CR-CED network denoising in the PACU are accurate and reliable. Tracheal sound can be denoised using this approach without separate background noise. It effectively improves the applicability of the tracheal sound denoising method in the medical environment while ensuring its correctness.

Diagnosing OSA and Insomnia at Home Based Only on an Actigraphy Total Sleep Time and RIP Belts an Algorithm "Nox Body Sleep™"

Purpose

The COVID-19 pandemic has influenced clinical sleep protocols with stricter hospital disinfection requirements. Facing these new rules, we tested if a new artificial intelligence (AI) algorithm: The Nox BodySleep™ (NBS) developed without airflow signals for the analysis of sleep might assess pertinently sleep in patients with Obstructive Sleep Apnea (OSA) and chronic insomnia (CI) as a control group, compared to polysomnography (PSG) manual scoring.

Patients-Methods

NBS is a recurrent neural network model that estimates Wake, NREM, and REM states, given features extracted from activity and respiratory inductance plethysmography (RIP) belt signals (Nox A1 PSG). Sleep states from 139 PSG studies (CI N = 72; OSA N = 67) were analyzed by NBS and compared to manually scored PSG using positive percentage agreement, negative percentage agreement, and overall agreement metrics. Similarly, we compared common sleep parameters and OSA severity using sleep states estimated by NBS for each recording and compared to manual scoring using Bland-Altman analysis and intra-class correlation coefficient.

Results

For 127,170 sleep epochs, an overall agreement of 83% was reached for Wake, NREM and REM states (92% for REM states in CI patients) between NBS and manually scored PSG. Overall agreement for estimating OSA severity was 100% for moderate-severe OSA and 91% for minimal OSA. The absolute errors of the apnea-hypopnea index (AHI) and total sleep time (TST) were significantly lower for the NBS compared to no scoring of sleep. The intra-class correlation was higher for AHI and significantly higher for TST using the NBS compared to no scoring of sleep.

Conclusion

NBS gives sleep states, parameters and AHI with a good positive and negative percentage agreement, compared with manually scored PSG.

Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals

Sleep apnea is a common sleep disorder. Traditional testing and diagnosis heavily rely on the expertise of physicians, as well as analysis and statistical interpretation of extensive sleep testing data, resulting in time-consuming and labor-intensive processes. To address the problems of complex feature extraction, data imbalance, and low model capacity, we proposed an automatic sleep apnea classification model (CA-EfficientNet) based on the wavelet transform, a lightweight neural network, and a coordinated attention mechanism. The signal is converted into a time-frequency image by wavelet transform and put into the proposed model for classification. The effects of input time window, wavelet transform type and data balancing on the classification performance are considered, and a cost-sensitive algorithm is introduced to more accurately distinguish between normal and abnormal breathing events. PhysioNet apnea ECG database was used for training and evaluation. The 3-min Frequency B-Spline wavelets transform of ECG signal was carried out, and Dice Loss was used to train the classification model of sleep breathing. The classification accuracy was 93.44%, sensitivity was 88.9%, specificity was 96.2% and most indexes were better than other related work.

Identification of OSAHS patients based on ReliefF-mRMR feature selection

Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) is a serious chronic sleep disorder. Snoring is a common and easily observable symptom of OSAHS patients. The purpose of this work is to identify OSAHS patients by analyzing the acoustic characteristics of snoring sounds throughout the entire night. Ten types of acoustic features, such as Mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC) and spectral entropy among others, were extracted from the snoring sounds. A fused feature selection algorithm based on ReliefF and Max-Relevance and Min-Redundancy (mRMR) was proposed for optimal feature set selection. Four types of machine learning models were then applied to validate the effectiveness of OSAHS patient identification. The results show that the proposed feature selection algorithm can effectively select features with high contribution, including MFCC and LPC. Based on the selected top-20 features and using a support vector machine model, the accuracies in identifying OSAHS patients under the thresholds of AHI = 5,15, and 30, were 100%, 100%, and 98.94%, respectively. This indicates that the proposed model can effectively identify OSAHS patients.

A multi-branch convolutional neural network for snoring detection based on audio

Obstructive sleep apnea (OSA) is associated with various health complications, and snoring is a prominent characteristic of this disorder. Therefore, the exploration of a concise and effective method for detecting snoring has consistently been a crucial aspect of sleep medicine. As the easily accessible data, the identification of snoring through sound analysis offers a more convenient and straightforward method. The objective of this study was to develop a convolutional neural network (CNN) for classifying snoring and non-snoring events based on audio. This study utilized Mel-frequency cepstral coefficients (MFCCs) as a method for extracting features during the preprocessing of raw data. In order to extract multi-scale features from the frequency domain of sound sources, this study proposes the utilization of a multi-branch convolutional neural network (MBCNN) for the purpose of classification. The network utilized asymmetric convolutional kernels to acquire additional information, while the adoption of one-hot encoding labels aimed to mitigate the impact of labels. The experiment tested the network's performance by utilizing a publicly available dataset consisting of 1,000 sound samples. The test results indicate that the MBCNN achieved a snoring detection accuracy of 99.5%. The integration of multi-scale features and the implementation of MBCNN, based on audio data, have demonstrated a substantial improvement in the performance of snoring classification.

Automatic snoring detection using a hybrid 1D-2D convolutional neural network

Snoring, as a prevalent symptom, seriously interferes with life quality of patients with sleep disordered breathing only (simple snorers), patients with obstructive sleep apnea (OSA) and their bed partners. Researches have shown that snoring could be used for screening and diagnosis of OSA. Therefore, accurate detection of snoring sounds from sleep respiratory audio at night has been one of the most important parts. Considered that the snoring is somewhat dangerously overlooked around the world, an automatic and high-precision snoring detection algorithm is required. In this work, we designed a non-contact data acquire equipment to record nocturnal sleep respiratory audio of subjects in their private bedrooms, and proposed a hybrid convolutional neural network (CNN) model for the automatic snore detection. This model consists of a one-dimensional (1D) CNN processing the original signal and a two-dimensional (2D) CNN representing images mapped by the visibility graph method. In our experiment, our algorithm achieves an average classification accuracy of 89.3%, an average sensitivity of 89.7%, an average specificity of 88.5%, and an average AUC of 0.947, which surpasses some state-of-the-art models trained on our data. In conclusion, our results indicate that the proposed method in this study could be effective and significance for massive screening of OSA patients in daily life. And our work provides an alternative framework for time series analysis.

Automatic stridor detection using small training set via patch-wise few-shot learning for diagnosis of multiple system atrophy

Stridor is a rare but important non-motor symptom that can support the diagnosis and prediction of worse prognosis in multiple system atrophy. Recording sounds generated during sleep by video-polysomnography is recommended for detecting stridor, but the analysis is labor intensive and time consuming. A method for automatic stridor detection should be developed using technologies such as artificial intelligence (AI) or machine learning. However, the rarity of stridor hinders the collection of sufficient data from diverse patients. Therefore, an AI method with high diagnostic performance should be devised to address this limitation. We propose an AI method for detecting patients with stridor by combining audio splitting and reintegration with few-shot learning for diagnosis. We used video-polysomnography data from patients with stridor (19 patients with multiple system atrophy) and without stridor (28 patients with parkinsonism and 18 patients with sleep disorders). To the best of our knowledge, this is the first study to propose a method for stridor detection and attempt the validation of few-shot learning to process medical audio signals. Even with a small training set, a substantial improvement was achieved for stridor detection, confirming the clinical utility of our method compared with similar developments. The proposed method achieved a detection accuracy above 96% using data from only eight patients with stridor for training. Performance improvements of 4%-13% were achieved compared with a state-of-the-art AI baseline. Moreover, our method determined whether a patient had stridor and performed real-time localization of the corresponding audio patches, thus providing physicians with support for interpreting and efficiently employing the results of this method.

Auditory Property-Based Features and Artificial Neural Network Classifiers for the Automatic Detection of Low-Intensity Snoring/Breathing Episodes

The definitive diagnosis of obstructive sleep apnea syndrome (OSAS) is made using an overnight polysomnography (PSG) test. This test requires that a patient wears multiple measurement sensors during an overnight hospitalization. However, this setup imposes physical constraints and a heavy burden on the patient. Recent studies have reported on another technique for conducting OSAS screening based on snoring/breathing episodes (SBEs) extracted from recorded data acquired by a noncontact microphone. However, SBEs have a high dynamic range and are barely audible at intensities >90 dB. A method is needed to detect SBEs even in low-signal-to-noise-ratio (SNR) environments. Therefore, we developed a method for the automatic detection of low-intensity SBEs using an artificial neural network (ANN). However, when considering its practical use, this method required further improvement in terms of detection accuracy and speed. To accomplish this, we propose in this study a new method to detect low SBEs based on neural activity pattern (NAP)-based cepstral coefficients (NAPCC) and ANN classifiers. Comparison results of the leave-one-out cross-validation demonstrated that our proposed method is superior to previous methods for the classification of SBEs and non-SBEs, even in low-SNR conditions (accuracy: 85.99 ± 5.69% vs. 75.64 ± 18.8%).

Application of substitution box of present cipher for automated detection of snoring sounds

BACKGROUND AND PURPOSE

Snoring is one of the sleep disorders, and snoring sounds have been used to diagnose many sleep-related diseases. However, the snoring sound classification is done manually which is time-consuming and prone to human errors. An automated snoring sound classification model is proposed to overcome these problems.

MATERIAL AND METHOD

This work proposes an automated snoring sound classification method using three new methods. These methods are maximum absolute pooling (MAP), the nonlinear present pattern, and two-layered neighborhood component analysis, and iterative neighborhood component analysis (NCAINCA) selector. Using these methods, a new snoring sound classification (SSC) model is presented. The MAP decomposition model is applied to snoring sounds to extract both low and high-level features. The presented model aims to attain high performance for SSC problem. The developed present pattern (Present-Pat) uses substitution box (SBox) and statistical feature generator. By deploying these feature generators, both textural and statistical features are generated. NCAINCA chooses the most informative/valuable features, and these selected features are fed to k-nearest neighbor (kNN) classifier with leave-one-out cross-validation (LOOCV). The Present-Pat based SSC system is developed using Munich-Passau Snore Sound Corpus (MPSSC) dataset comprising of four categories.

RESULTS

Our model reached an accuracy and unweighted average recall (UAR) of 97.10 % and 97.60 %, respectively, using LOOCV. Moreover, a nocturnal sound dataset is used to show the universal success of the presented model. Our model attained an accuracy of 98.14 % using the used nocturnal sound dataset.

CONCLUSIONS

Our developed classification model is ready to be tested with more data and can be used by sleep specialists to diagnose the sleep disorders based on snoring sounds.