# Application of spectral characteristics of electrocardiogram signals in sleep apnea

## TL;DR

This paper introduces a new method for detecting sleep apnea using ECG signals by analyzing their spectral features, achieving high accuracy with a machine learning model.

## Contribution

A novel spectral feature-based approach using EEMD-ICA and time-frequency analysis for efficient sleep apnea detection from single-lead ECG signals.

## Key findings

- The femax and IMF7 components showed statistically significant differences between normal and sleep apnea subjects (p < 0.001).
- The random forest classifier achieved 92.9% accuracy, 86.6% specificity, and 100% sensitivity in sleep apnea detection.
- Spectral features from single-lead ECG signals offer an efficient and accurate method for sleep apnea detection.

## Abstract

Electrocardiogram (ECG) signals contain cardiopulmonary information that can facilitate sleep apnea detection. Traditional methods rely on extracting numerous ECG features, which is labor-intensive and computationally cumbersome.

To reduce feature complexity and enhance detection accuracy, we propose a spectral feature-based approach using single-lead ECG signals. First, the ECG signal is preprocessed via ensemble empirical mode decomposition combined with independent component analysis (EEMD-ICA) to identify the most representative intrinsic mode function (IMF) based on the maximum instantaneous frequency in the frequency domain. Next, Hilbert transform-based time-frequency analysis is applied to derive the component’s 2D time-frequency spectrum. Finally, three spectral features—maximum instantaneous frequency (femax), instantaneous frequency amplitude (V), and marginal spectrum energy (S)—are quantitatively compared between normal and sleep apnea populations using an independent-sample t-test. These features are classified via a random forest machine learning model.

The femax and IMF7 components of the reconstructed signal exhibited statistically significant differences (p < 0.001) between normal and sleep apnea subjects. The random forest classifier achieved optimal performance, with 92.9% accuracy, 86.6% specificity, and 100% sensitivity.

This study demonstrates that spectral features derived from single-lead ECG signals, combined with EEMD-ICA and time-frequency analysis, offer an efficient and accurate method for sleep apnea detection.