Semi-Supervised Learning for Low-Cost Personalized Obstructive Sleep Apnea Detection Using Unsupervised Deep Learning and Single-Lead Electrocardiogram

Objective: Obstructive sleep apnea (OSA) is a common sleep-related breathing disorder that can lead to a wide range of health issues if left untreated. This study aims to address the lack of research on personalized models for single-lead electrocardiogram (ECG)-based OSA detection, by proposing an automatic semi-supervised algorithm for automated low-cost personalization fine-tuning. Methods: We utilize a convolutional neural network (CNN)-based auto-encoder (AE) with a modified training objective to detect anomalous region of OSA. An indicator based on model outputs is utilized as a benchmark measure to assign pseudo-labels with confidence to each sample. Finally, we perform validation of the semi-supervised algorithm on the same database and cross-database scenarios. Results: By introducing semi-supervised personalization, the accuracy, AUC, and mean absolute error (MAE) of the general model (GM) of 35 subjects from the same database are improved from 86.3%, 0.915, and 5.178 to 90.3%, 0.948, and 2.593. Simultaneously, in the validation of 25 subjects from a cross-database, the accuracy, AUC, and MAE of the GM are enhanced from 75.6%, 0.800, and 9.149 to 84.3%, 0.881, and 3.509. Conclusion: The improved version of AE demonstrates excellent adaptability in identifying abnormal features in OSA, employing a data-driven approach to assign pseudo-labels for unknown data automatically. Additionally, leveraging the pseudo-labels through a semi-supervised fine-tuning strategy provides a solution to overcome the limitation of clinical annotations, facilitating low-cost implementation of personalized models. Significance: The semi-supervised approach proposed in this article provides a high-performance and annotation-free solution for personalized adjustment of automatic OSA detection.

I. Introduction

Obsyructive sleep apnea (OSA) is a widely prevalent sleep disorder characterized by recurrent breathing pauses or reduced airflow during sleep [1], [2], leading to poor sleep quality, daytime fatigue, anxiety, and other adverse outcomes [3], [4], as well as serious complications such as hypoxemia, cardiovascular disease, cognitive impairment, stroke, and even death [5], [6], [7]. The clinical gold standard generally involves monitoring the subject overnight using polysomnography (PSG), which includes various modal signals such as continuous synchronized electroencephalography (EEG), electromyography (EMG), electrooculography (EOG), electrocardiography (ECG), pulse oximetric saturation, and respiratory airflow. However, utilizing PSG for OSA detection requires expensive medical costs due to the need for overnight monitoring of patients, and the limitation of medical resources also prevents large-scale screening of the population [8]. Therefore, it is necessary to find a more convenient and economical method to identify this sleep disorder [9].