Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis

Abstract Polysomnography is the diagnostic gold standard for obstructive sleep apnea-hypopnea syndrome (OSAHS), requiring medical professionals to analyze apnea-hypopnea events from multidimensional data throughout the sleep cycle. This complex process is susceptible to variability based on the clin...

Full description

Saved in:
Bibliographic Details
Main Authors: Haoyu Wang, Xihe Qiu, Bin Li, Xiaoyu Tan, Jingjing Huang
Format: Article
Language:English
Published: Springer 2024-11-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-024-01648-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571155546898432
author Haoyu Wang
Xihe Qiu
Bin Li
Xiaoyu Tan
Jingjing Huang
author_facet Haoyu Wang
Xihe Qiu
Bin Li
Xiaoyu Tan
Jingjing Huang
author_sort Haoyu Wang
collection DOAJ
description Abstract Polysomnography is the diagnostic gold standard for obstructive sleep apnea-hypopnea syndrome (OSAHS), requiring medical professionals to analyze apnea-hypopnea events from multidimensional data throughout the sleep cycle. This complex process is susceptible to variability based on the clinician’s experience, leading to potential inaccuracies. Existing automatic diagnosis methods often overlook multimodal physiological signals and medical prior knowledge, leading to limited diagnostic capabilities. This study presents a novel heterogeneous graph convolutional fusion network (HeteroGCFNet) leveraging multimodal physiological signals and domain knowledge for automated OSAHS diagnosis. This framework constructs two types of graph representations: physical space graphs, which map the spatial layout of sensors on the human body, and process knowledge graphs which detail the physiological relationships among breathing patterns, oxygen saturation, and vital signals. The framework leverages heterogeneous graph convolutional neural networks to extract both localized and global features from these graphs. Additionally, a multi-head fusion module combines these features into a unified representation for effective classification, enhancing focus on relevant signal characteristics and cross-modal interactions. This study evaluated the proposed framework on a large-scale OSAHS dataset, combined from publicly available sources and data provided by a collaborative university hospital. It demonstrated superior diagnostic performance compared to conventional machine learning models and existing deep learning approaches, effectively integrating domain knowledge with data-driven learning to produce explainable representations and robust generalization capabilities, which can potentially be utilized for clinical use. Code is available at https://github.com/AmbitYuki/HeteroGCFNet .
format Article
id doaj-art-38335331300d4e999af1aabf5445e01c
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2024-11-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-38335331300d4e999af1aabf5445e01c2025-02-02T12:49:20ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111810.1007/s40747-024-01648-0Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosisHaoyu Wang0Xihe Qiu1Bin Li2Xiaoyu Tan3Jingjing Huang4School of Electronic and Electrical Engineering, Shanghai University of Engineering ScienceSchool of Electronic and Electrical Engineering, Shanghai University of Engineering ScienceSchool of Electronic and Electrical Engineering, Shanghai University of Engineering ScienceINF Technology (Shanghai) Co., Ltd.ENT institute and Department of Otorhinolaryngology, Eye & ENT Hospital, Fudan UniversityAbstract Polysomnography is the diagnostic gold standard for obstructive sleep apnea-hypopnea syndrome (OSAHS), requiring medical professionals to analyze apnea-hypopnea events from multidimensional data throughout the sleep cycle. This complex process is susceptible to variability based on the clinician’s experience, leading to potential inaccuracies. Existing automatic diagnosis methods often overlook multimodal physiological signals and medical prior knowledge, leading to limited diagnostic capabilities. This study presents a novel heterogeneous graph convolutional fusion network (HeteroGCFNet) leveraging multimodal physiological signals and domain knowledge for automated OSAHS diagnosis. This framework constructs two types of graph representations: physical space graphs, which map the spatial layout of sensors on the human body, and process knowledge graphs which detail the physiological relationships among breathing patterns, oxygen saturation, and vital signals. The framework leverages heterogeneous graph convolutional neural networks to extract both localized and global features from these graphs. Additionally, a multi-head fusion module combines these features into a unified representation for effective classification, enhancing focus on relevant signal characteristics and cross-modal interactions. This study evaluated the proposed framework on a large-scale OSAHS dataset, combined from publicly available sources and data provided by a collaborative university hospital. It demonstrated superior diagnostic performance compared to conventional machine learning models and existing deep learning approaches, effectively integrating domain knowledge with data-driven learning to produce explainable representations and robust generalization capabilities, which can potentially be utilized for clinical use. Code is available at https://github.com/AmbitYuki/HeteroGCFNet .https://doi.org/10.1007/s40747-024-01648-0Obstructive sleep apnea-hypopnea syndromeMultimodal signalsHeterogeneous graphPersonalized healthcare
spellingShingle Haoyu Wang
Xihe Qiu
Bin Li
Xiaoyu Tan
Jingjing Huang
Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
Complex & Intelligent Systems
Obstructive sleep apnea-hypopnea syndrome
Multimodal signals
Heterogeneous graph
Personalized healthcare
title Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
title_full Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
title_fullStr Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
title_full_unstemmed Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
title_short Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
title_sort multimodal heterogeneous graph fusion for automated obstructive sleep apnea hypopnea syndrome diagnosis
topic Obstructive sleep apnea-hypopnea syndrome
Multimodal signals
Heterogeneous graph
Personalized healthcare
url https://doi.org/10.1007/s40747-024-01648-0
work_keys_str_mv AT haoyuwang multimodalheterogeneousgraphfusionforautomatedobstructivesleepapneahypopneasyndromediagnosis
AT xiheqiu multimodalheterogeneousgraphfusionforautomatedobstructivesleepapneahypopneasyndromediagnosis
AT binli multimodalheterogeneousgraphfusionforautomatedobstructivesleepapneahypopneasyndromediagnosis
AT xiaoyutan multimodalheterogeneousgraphfusionforautomatedobstructivesleepapneahypopneasyndromediagnosis
AT jingjinghuang multimodalheterogeneousgraphfusionforautomatedobstructivesleepapneahypopneasyndromediagnosis