Detection of sleep apnea using Machine learning algorithms based on ECG Signals: A comprehensive systematic review

Abstract. Sleep apnea (SA) is a common sleep disorder that is not easy to detect among several patients. Recent studies have highlighted ECG analysis as a method of diagnosing SA. Because the changes caused by SA on the ECG are so subtle, the need for new methods in diagnosing the disease is required more than ever. Machine Learning (ML) techniques are recognized as one of the most successful methods of computer aided diagnosis. ML uses new methods to diagnose diseases using past clinical results. The purpose of this study is to evaluate studies using ML algorithms and based on ECG characteristics to evaluate people with SA patients. In this study, English articles written in English and indexed in PubMed, Scopus, Web of Science, and IEEE databases, were searched with no lower time limit and until October 2020, and were systematically reviewed. Finally, 48 articles were approved for review in this study. In Within the selected articles, different ML methods were used adopted for classification. All of these studies were binary, and SA was detected from the normal state based on a full ECG stripe (per record), or based on one-minute segments (per segment). Our studies analyses showed show that the most common features used in the studies were frequency, time series and statistical features. Support-Vector Machine (SVM) and deep learning-based neural network (i.e. CNN, DNN) performed best in full record data detection. The highest accuracy, sensitivity and specificity reported between the selected studies were 100%, which was obtained by an SVM. In another case study, the classification was conducted based on ECG segments, and accordingly, the highest classification accuracy was observed in the residual neural network algorithm (RNN). The accuracy, sensitivity and specificity of this algorithm were reported to be 99%. In general, it can be stated that ML techniques based on ECG characteristics have a high capability in diagnosing SA. This can increase the diagnosis of patients with SA or the detection of SA episodes on ECG record, and can potentially prevent complications of the disease at later stages.