A Comprehensive Study on a Deep-Learning-Based Electrocardiography Analysis for Estimating the Apnea-Hypopnea Index

This study introduces a deep-learning-based automatic sleep scoring system to detect sleep apnea using a single-lead electrocardiography (ECG) signal, focusing on accurately estimating the apnea-hypopnea index (AHI). Unlike other research, this work emphasizes AHI estimation, crucial for the diagnos...

Full description

Saved in:
Bibliographic Details
Published in:Diagnostics (Basel) 2024-06, Vol.14 (11), p.1134
Main Authors: Kim, Seola, Choi, Hyun-Soo, Kim, Dohyun, Kim, Minkyu, Lee, Seo-Young, Kim, Jung-Kyeom, Kim, Yoon, Lee, Woo Hyun
Format: Article
Language:English
Subjects:
Analysis
apnea–hypopnea index
Automation
Computational linguistics
Continuous positive airway pressure
Datasets
deep learning
Electrocardiogram
Electrocardiography
hypopnea
Labeling
Language processing
Natural language interfaces
Neural networks
Patients
Sleep apnea
Sleep apnea syndromes
sleep-related breathing disorder
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study introduces a deep-learning-based automatic sleep scoring system to detect sleep apnea using a single-lead electrocardiography (ECG) signal, focusing on accurately estimating the apnea-hypopnea index (AHI). Unlike other research, this work emphasizes AHI estimation, crucial for the diagnosis and severity evaluation of sleep apnea. The suggested model, trained on 1465 ECG recordings, combines the deep-shallow fusion network for sleep apnea detection network (DSF-SANet) and gated recurrent units (GRUs) to analyze ECG signals at 1-min intervals, capturing sleep-related respiratory disturbances. Achieving a 0.87 correlation coefficient with actual AHI values, an accuracy of 0.82, an F1 score of 0.71, and an area under the receiver operating characteristic curve of 0.88 for per-segment classification, our model was effective in identifying sleep-breathing events and estimating the AHI, offering a promising tool for medical professionals.
ISSN:2075-4418
2075-4418
DOI:10.3390/diagnostics14111134