SleepLiteCNN: Energy-Efficient Sleep Apnea Subtype Classification with 1-Second Resolution Using Single-Lead ECG

TL;DR

This paper introduces SleepLiteCNN, an energy-efficient deep learning model for real-time sleep apnea subtype classification using single-lead ECG, suitable for wearable devices with high accuracy and low energy consumption.

Contribution

The paper presents SleepLiteCNN, a novel compact CNN architecture optimized for energy efficiency and high accuracy in sleep apnea subtype detection on wearable platforms.

Findings

Achieves over 95% accuracy in classifying sleep apnea subtypes.

Requires only 1.8 microjoules per inference after quantization.

Demonstrates reduced hardware resource usage on FPGA.

Abstract

Apnea is a common sleep disorder characterized by breathing interruptions lasting at least ten seconds and occurring more than five times per hour. Accurate, high-temporal-resolution detection of sleep apnea subtypes - Obstructive, Central, and Mixed - is crucial for effective treatment and management. This paper presents an energy-efficient method for classifying these subtypes using a single-lead electrocardiogram (ECG) with high temporal resolution to address the real-time needs of wearable devices. We evaluate a wide range of classical machine learning algorithms and deep learning architectures on 1-second ECG windows, comparing their accuracy, complexity, and energy consumption. Based on this analysis, we introduce SleepLiteCNN, a compact and energy-efficient convolutional neural network specifically designed for wearable platforms. SleepLiteCNN achieves over 95% accuracy and a 92% macro-F1 score, while requiring just 1.8 microjoules per inference after 8-bit quantization. Field Programmable Gate Array (FPGA) synthesis further demonstrates significant reductions in hardware resource usage, confirming its suitability for continuous, real-time monitoring in energy-constrained environments. These results establish SleepLiteCNN as a practical and effective solution for wearable device sleep apnea subtype detection.