Machine Learning-Based Detection of Sleep-Disordered Breathing Type Using Time and Time-Frequency Features

Non-obtrusive monitoring of obstructive sleep apnea syndrome based on ballistocardiography: a preliminary study

Introduction

Obstructive sleep apnea syndrome (OSAS) degrades sleep quality and is associated with serious health conditions. Instead of the gold-standard polysomnography requiring complex equipment and expertise, a non-obtrusive device such as ballistocardiography (BCG) is more suitable for home-based continuous monitoring of OSAS, which has shown promising results in previous studies. However, often due to the limited storage and computing resource, also preferred by venders, the high computational cost in many existing BCG-based methods would practically limit the deployment for home monitoring.

Methods

In this preliminary study, we propose an approach for OSAS monitoring using BCG signals. Applying fast change-point detection to first isolate apnea-suspected episodes would allow for processing only those suspected episodes for further feature extraction and OSAS severity classification. This can reduce both the data to be stored or transmitted and the computational load. Furthermore, our approach directly extracts features from BCG signals without employing a complex algorithm to derive respiratory and heart rate signals as often done in literature, further simplifying the algorithm pipeline. Apnea-hypopnea index (AHI) is then computed based on the detected apnea events (using a random forest classifier) from the identified apnea-suspected episodes. To deal with the expected underestimated AHI due to missing true apnea events during change-point detection, we apply boundary adjustment on AHI when classifying severity.

Results

Cross-validated on 32 subjects, the proposed approach achieved an accuracy of 71.9% for four-class severity classification and 87.5% for binary classification (AHI less than 15 or not).

Conclusion

These findings highlight the potential of our proposed BCG-based approach as an effective and accessible alternative for continuous OSAS monitoring.

Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review

Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart's electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012-22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling. The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%-83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%-95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.

A review of automated sleep disorder detection

Automated sleep disorder detection is challenging because physiological symptoms can vary widely. These variations make it difficult to create effective sleep disorder detection models which support hu-man experts during diagnosis and treatment monitoring. From 2010 to 2021, authors of 95 scientific papers have taken up the challenge of automating sleep disorder detection. This paper provides an expert review of this work. We investigated whether digital technology and Artificial Intelligence (AI) can provide automated diagnosis support for sleep disorders. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during the content discovery phase. We compared the performance of proposed sleep disorder detection methods, involving differ-ent datasets or signals. During the review, we found eight sleep disorders, of which sleep apnea and insomnia were the most studied. These disorders can be diagnosed using several kinds of biomedical signals, such as Electrocardiogram (ECG), Polysomnography (PSG), Electroencephalogram (EEG), Electromyogram (EMG), and snore sound. Subsequently, we established areas of commonality and distinctiveness. Common to all reviewed papers was that AI models were trained and tested with labelled physiological signals. Looking deeper, we discovered that 24 distinct algorithms were used for the detection task. The nature of these algorithms evolved, before 2017 only traditional Machine Learning (ML) was used. From 2018 onward, both ML and Deep Learning (DL) methods were used for sleep disorder detection. The strong emergence of DL algorithms has considerable implications for future detection systems because these algorithms demand significantly more data for training and testing when compared with ML. Based on our review results, we suggest that both type and amount of labelled data is crucial for the design of future sleep disorder detection systems because this will steer the choice of AI algorithm which establishes the desired decision support. As a guiding principle, more labelled data will help to represent the variations in symptoms. DL algorithms can extract information from these larger data quantities more effectively, therefore; we predict that the role of these algorithms will continue to expand.