MobileNetV2: A lightweight classification model for home-based sleep apnea screening

2024-12-28

AI Summary

To address the need for early, at-home screening of obstructive sleep apnea (OSA), this paper proposes a lightweight, multi-signal collaborative end-to-end framework for apnea-hypopnea index (AHI) estimation. Methodologically, it introduces a dual-branch network based on MobileNetV2: one branch processes ECG time-frequency spectrograms for sleep staging, while the other models temporal respiratory features to detect respiratory events; joint multi-task optimization and AHI regression mapping ensure clinically interpretable index estimation. The key contribution is the first integration of ECG and respiratory signals within an edge-deployable architecture, balancing accuracy and interpretability while overcoming limitations of single-modality and computationally heavy models. Experiments demonstrate strong performance: OSA detection accuracy of 0.978, respiratory event classification accuracy of 0.969 (ROC-AUC = 0.98), and sleep staging on the UCDDB dataset achieving REM specificity of 0.956, Wake specificity of 0.937, and overall sleep recall of 0.906.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This study proposes a novel lightweight neural network model leveraging features extracted from electrocardiogram (ECG) and respiratory signals for early OSA screening. ECG signals are used to generate feature spectrograms to predict sleep stages, while respiratory signals are employed to detect sleep-related breathing abnormalities. By integrating these predictions, the method calculates the apnea-hypopnea index (AHI) with enhanced accuracy, facilitating precise OSA diagnosis. The method was validated on three publicly available sleep apnea databases: the Apnea-ECG database, the UCDDB dataset, and the MIT-BIH Polysomnographic database. Results showed an overall OSA detection accuracy of 0.978, highlighting the model's robustness. Respiratory event classification achieved an accuracy of 0.969 and an area under the receiver operating characteristic curve (ROC-AUC) of 0.98. For sleep stage classification, in UCDDB dataset, the ROC-AUC exceeded 0.85 across all stages, with recall for Sleep reaching 0.906 and specificity for REM and Wake states at 0.956 and 0.937, respectively. This study underscores the potential of integrating lightweight neural networks with multi-signal analysis for accurate, portable, and cost-effective OSA screening, paving the way for broader adoption in home-based and wearable health monitoring systems.

Problem

• Lightweight Neural Network
• Obstructive Sleep Apnea (OSA) Detection
• Heart Rate and Respiration Signals

Innovation

• MobileNetV2
• Sleep Apnea Detection
• Wearable Health Devices