Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jayroop Ramesh, Niha Keeran, Assim Sagahyroon, Fadi Aloul
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	electronic health records machine learning obstructive polysomnography prediction sleep apnea Medicine R
Acceso en línea:	https://doaj.org/article/91bfed61427b4171beba97200c8ed0e0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:91bfed61427b4171beba97200c8ed0e0
record_format	dspace
spelling	oai:doaj.org-article:91bfed61427b4171beba97200c8ed0e02021-11-25T17:44:07ZTowards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning10.3390/healthcare91114502227-9032https://doaj.org/article/91bfed61427b4171beba97200c8ed0e02021-10-01T00:00:00Zhttps://www.mdpi.com/2227-9032/9/11/1450https://doaj.org/toc/2227-9032Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies.Jayroop RameshNiha KeeranAssim SagahyroonFadi AloulMDPI AGarticleelectronic health recordsmachine learningobstructivepolysomnographypredictionsleep apneaMedicineRENHealthcare, Vol 9, Iss 1450, p 1450 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	electronic health records machine learning obstructive polysomnography prediction sleep apnea Medicine R
spellingShingle	electronic health records machine learning obstructive polysomnography prediction sleep apnea Medicine R Jayroop Ramesh Niha Keeran Assim Sagahyroon Fadi Aloul Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
description	Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies.
format	article
author	Jayroop Ramesh Niha Keeran Assim Sagahyroon Fadi Aloul
author_facet	Jayroop Ramesh Niha Keeran Assim Sagahyroon Fadi Aloul
author_sort	Jayroop Ramesh
title	Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
title_short	Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
title_full	Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
title_fullStr	Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
title_full_unstemmed	Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
title_sort	towards validating the effectiveness of obstructive sleep apnea classification from electronic health records using machine learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/91bfed61427b4171beba97200c8ed0e0
work_keys_str_mv	AT jayroopramesh towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning AT nihakeeran towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning AT assimsagahyroon towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning AT fadialoul towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning
_version_	1718412057203703808

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

Ejemplares similares