Low-Power Wearable System for Real-Time Screening of Obstructive Sleep Apnea

Abstract

Abstract-Obstructive Sleep Apnea (OSA) is one of the main sleep disorders, but only 10% of the cases are diagnosed. Moreover, there is a lack of tools for long-term monitoring of OSA, since current systems are too bulky and intrusive to be used continuously. In this context, recent studies have shown that it is possible to detect it automatically based on singlelead ECG recordings. This approach can be used in non-invasive smart wearable sensors which measure and process bio-signals online. This work focuses on the implementation, optimization and integration of an algorithm for OSA detection for preventive health-care. It relies on a frequency-domain analysis while targeting an ultra-low power embedded wearable device. As it must share its resources usage with other computations, it must be as lightweight as possible. Our current results based on publicly available signals show a classification accuracy of up to 83.2% for both the offline analysis and the embedded online one. This system gives an even better classification accuracy than the best offline algorithm when using the same features for classification [1].

Online Obstructive Sleep Apnea Detection on Medical Wearable Sensors

“…As the battery is rated at 710 mAh, the total lifetime is approximately 1115 hours (46.5 days). Thus, the obstructive sleep apnea detection technique in this paper is one order of magnitude more energy-efficient than our previous work [42], while having better classification results whether we consider a patient-agnostic or patient-specific approach. This is mainly due to our fast outliers removal and time-domain apnea score computation.…”

“…2. Overview of the processing blocks integrated in the device used for the online OSA analysis in the proposed system [42]. The ECG is first filtered to remove the noise, then the fiducial points are extracted.…”

“…It is applied when considering both the RR-intervals and the RS-amplitudes of the beats. Compared to [42], the higighted blocks feature the use of our optimized outliers removal, updated apnea-score computation using a time-domain filtering and power estimation, as well as the additional RS-amplitude feature extraction along with the inclusion of the SVM classifier. of the series (Lines 3-4).…”

“…Evolution of the accuracy depending on the strength of the Thompson filter. Even a very tolerant (weak) removal significantly improves the classification accuracy, which means that only removing the few biggest outliers is desirable [42].…”

“…However, among all the devices and techniques available, none is a high-accuracy wearable system with real-time and long-term screening while satisfying the need of cardiac monitoring. In [42], we proposed a low-power wearable system for real-time OSA screening along with cardiac monitoring. In this paper, we extend our previous work by improving both the classification accuracy and battery lifetime.…”