SomnNET: An SpO2 Based Deep Learning Network for Sleep Apnea Detection in Smartwatches

TL;DR

This paper introduces SomnNET, a deep learning model that detects sleep apnea events from SpO2 signals in smartwatches with high accuracy, and explores model pruning for efficiency.

Contribution

The paper presents a novel high-resolution apnea detection CNN, SomnNET, and evaluates model pruning and binarization for computational efficiency.

Findings

SomnNET achieves 97.08% accuracy in apnea detection.

Pruned network with 80% sparsity maintains 89.75% accuracy.

Binarized network achieves 68.22% accuracy.

Abstract

The abnormal pause or rate reduction in breathing is known as the sleep-apnea hypopnea syndrome and affects the quality of sleep of an individual. A novel method for the detection of sleep apnea events (pause in breathing) from peripheral oxygen saturation (SpO2) signals obtained from wearable devices is discussed in this paper. The paper details an apnea detection algorithm of a very high resolution on a per-second basis for which a 1-dimensional convolutional neural network -- which we termed SomnNET -- is developed. This network exhibits an accuracy of 97.08% and outperforms several lower resolution state-of-the-art apnea detection methods. The feasibility of model pruning and binarization to reduce the computational complexity is explored. The pruned network with 80% sparsity exhibited an accuracy of 89.75%, and the binarized network exhibited an accuracy of 68.22%. The performance of the proposed networks is compared against several state-of-the-art algorithms.