A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea
Cardiovascular (CV) disorders and obstructive sleep apnea (OSA) are very prevalent diseases worldwide. Multiple studies have demonstrated that OSA is associated with increased CV risk. Clinicians need to assess the CV risk to select the proper OSA treatment. A growing number of research have employe...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9997517/ |
_version_ | 1797974445295403008 |
---|---|
author | Margaux Blanchard Mathieu Feuilloy Abdelkebir Sabil Chloe Gerves-Pinquie Frederic Gagnadoux Jean-Marc Girault |
author_facet | Margaux Blanchard Mathieu Feuilloy Abdelkebir Sabil Chloe Gerves-Pinquie Frederic Gagnadoux Jean-Marc Girault |
author_sort | Margaux Blanchard |
collection | DOAJ |
description | Cardiovascular (CV) disorders and obstructive sleep apnea (OSA) are very prevalent diseases worldwide. Multiple studies have demonstrated that OSA is associated with increased CV risk. Clinicians need to assess the CV risk to select the proper OSA treatment. A growing number of research have employed machine learning to predict CV risk by integrating clinical and sleep features. In this paper, a multiple input deep learning model was proposed to directly use sleep signals combined with clinical features. Data from 5,506 patients from the Pays de la Loire Sleep Cohort, without a history of major adverse cardiovascular events (MACE), investigated for OSA, were used. After a median follow-up of 6.0 years, 613 patients had been diagnosed with MACE according to the French national health system. Following an architecture selection, deep survival convolutional neural networks were computed to assess the MACE risk score. A custom loss function was integrated to consider the follow-up time of each patient. Based on the weights of each model input, a method for interpreting the model was also proposed to show the contribution of signals compared to clinical features. Sleep signals were extracted from a home sleep apnea test. The best results were obtained with the autonomic manifestation signal. An area under the ROC curve of 0.823 was reached. After interpretation of the models, consideration of sleep appeared to be more important in women and in those under 60. This method may help improve OSA patient care by estimating their risk of MACE during sleep diagnosis. |
first_indexed | 2024-04-11T04:20:04Z |
format | Article |
id | doaj.art-ef3006439dec44ae880a268afec601b6 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-11T04:20:04Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-ef3006439dec44ae880a268afec601b62022-12-31T00:00:55ZengIEEEIEEE Access2169-35362022-01-011013346813347810.1109/ACCESS.2022.32317439997517A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep ApneaMargaux Blanchard0https://orcid.org/0000-0001-8382-4037Mathieu Feuilloy1Abdelkebir Sabil2Chloe Gerves-Pinquie3Frederic Gagnadoux4Jean-Marc Girault5https://orcid.org/0000-0002-2356-885XESEO, Angers, FranceESEO, Angers, FranceCloud Sleep Laboratory, Paris, FrancePays de la Loire Respiratory Health Research Institute, Beaucouzé, FranceDepartment of Respiratory and Sleep Medicine, Angers University Hospital, Angers, FranceESEO, Angers, FranceCardiovascular (CV) disorders and obstructive sleep apnea (OSA) are very prevalent diseases worldwide. Multiple studies have demonstrated that OSA is associated with increased CV risk. Clinicians need to assess the CV risk to select the proper OSA treatment. A growing number of research have employed machine learning to predict CV risk by integrating clinical and sleep features. In this paper, a multiple input deep learning model was proposed to directly use sleep signals combined with clinical features. Data from 5,506 patients from the Pays de la Loire Sleep Cohort, without a history of major adverse cardiovascular events (MACE), investigated for OSA, were used. After a median follow-up of 6.0 years, 613 patients had been diagnosed with MACE according to the French national health system. Following an architecture selection, deep survival convolutional neural networks were computed to assess the MACE risk score. A custom loss function was integrated to consider the follow-up time of each patient. Based on the weights of each model input, a method for interpreting the model was also proposed to show the contribution of signals compared to clinical features. Sleep signals were extracted from a home sleep apnea test. The best results were obtained with the autonomic manifestation signal. An area under the ROC curve of 0.823 was reached. After interpretation of the models, consideration of sleep appeared to be more important in women and in those under 60. This method may help improve OSA patient care by estimating their risk of MACE during sleep diagnosis.https://ieeexplore.ieee.org/document/9997517/Deep learningcardiovascular risksurvival analysissleep apneasignal |
spellingShingle | Margaux Blanchard Mathieu Feuilloy Abdelkebir Sabil Chloe Gerves-Pinquie Frederic Gagnadoux Jean-Marc Girault A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea IEEE Access Deep learning cardiovascular risk survival analysis sleep apnea signal |
title | A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea |
title_full | A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea |
title_fullStr | A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea |
title_full_unstemmed | A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea |
title_short | A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea |
title_sort | deep survival learning approach for cardiovascular risk estimation in patients with sleep apnea |
topic | Deep learning cardiovascular risk survival analysis sleep apnea signal |
url | https://ieeexplore.ieee.org/document/9997517/ |
work_keys_str_mv | AT margauxblanchard adeepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT mathieufeuilloy adeepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT abdelkebirsabil adeepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT chloegervespinquie adeepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT fredericgagnadoux adeepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT jeanmarcgirault adeepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT margauxblanchard deepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT mathieufeuilloy deepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT abdelkebirsabil deepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT chloegervespinquie deepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT fredericgagnadoux deepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea AT jeanmarcgirault deepsurvivallearningapproachforcardiovascularriskestimationinpatientswithsleepapnea |