Machine Learning-Based Automatic Detection of Central Sleep Apnea Events From a Pressure Sensitive Mat

Abstract

Polysomnography (PSG) is the standard test for diagnosing sleep apnea. However, the approach is obtrusive, time-consuming, and with limited access for patients in need of sleep apnea diagnosis. In recent years, there have been many attempts to search for an alternative device or approach that avoids the limitations of PSG. Pressure-sensitive mats (PSM) have proven to be able to detect central sleep apneas (CSA) and be a potential alternative for PSG. In the current study, we combine advanced machine learning approaches with a practical unobtrusive home monitoring device (PSM) to detect CSA events from data collected nocturnally and unattended. Two deep learning methods are implemented for the automatic detection of CSA events: a temporal convolutional network (TCN) and a bidirectional long short-term memory (BiLSTM) network. The deep learning models are compared to a classical machine learning approach (linear support vector machine, SVM) and a simple threshold-based algorithm. Considering the characteristics of each method, we choose strategies, including resampling and weighted cost-functions, to optimize the methods and to perform CSA detection as anomaly detection in an imbalanced data set. We evaluate the performance of all models on a database containing 7 days of data from 9 elderly patients. From the resulting 63 days, data from 7 patients (49 days) are devoted to training for optimizing hyperparameters, and data from 2 patients (14 days) are devoted to testing. Experimental results indicate that the bestperforming model achieves an accuracy of 95.1% through training an BiLSTM network. Overall, the implemented deep learning methods achieve better performance than the conventional classification approach (SVM) and the simple threshold-based method, and show good potential for the use of PSM for practical unobtrusive monitoring of CSA. INDEX TERMS Biomedical measurement, data analysis, deep learning, machine learning, patient monitoring, pressure measurement, central sleep apnea detection.

Hybrid CNN-LSTM Network for Real-Time Apnea-Hypopnea Event Detection Based on IR-UWB Radar

“…Sleep apnea and hypopnea syndrome (SAHS) is the most common sleep-related breathing disorder in the general population and is caused by partial or complete obstruction of the upper airway [1]. This disorder is characterized by repetitive events in which breathing is shallow or paused for more than 10s during sleep [2]. These events are typically accompanied by blood oxygen desaturation and arousals during sleep, leading to daytime sleepiness, decreased cognitive function and negative mood [3], [4].…”

A Survey on Recent Advances in Machine Learning Based Sleep Apnea Detection Systems

“…However, this method requires facial images of the subject, which restricts the subject’s degree of freedom while sleeping. Other studies in the area that use non-biomedical parameters include [ 65 , 66 , 67 ].…”

“…15 statistical features were derived from these extracted epochs. Accuracy: 73% [ 65 ] 2020 9 subjects Age 65 years or more Signals from pressure sensitive mat Temporal convolutional network (TCN), bidirectional LSTM Data pre-processing included occupancy extraction, bandpass filtering, signal combination, concatenation and normalization. TCN and bidirectional LSTM approaches were compared with SVM and threshold based approaches.…”

Three-Stage Breathing Effort Quantification for Obstructive Sleep Apnea Detection Based on Thoracic and Abdominal Movement Signals

“…where vector Y is derived from the linearization of any physiological signal of y, and ymax denotes the cut-off amplitude of the sensor. The thoracic and abdominal signals from the RIP belts were bandpass-filtered between the frequencies, 0.07-0.8 Hz, including the extreme breathing rate, which can be between 4-48 beats per minute [17], [26]. Each signal was segmented into a 5-s interval with a 90% overlap.…”