Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity
Abstract As the incidence of obstructive sleep apnea syndrome (OSAS) increases worldwide, the need for a new screening method that can compensate for the shortcomings of the traditional diagnostic method, polysomnography (PSG), is emerging. In this study, data from 4014 patients were used, and both...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-04-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-33170-7 |
_version_ | 1797841066018209792 |
---|---|
author | Hyewon Han Junhyoung Oh |
author_facet | Hyewon Han Junhyoung Oh |
author_sort | Hyewon Han |
collection | DOAJ |
description | Abstract As the incidence of obstructive sleep apnea syndrome (OSAS) increases worldwide, the need for a new screening method that can compensate for the shortcomings of the traditional diagnostic method, polysomnography (PSG), is emerging. In this study, data from 4014 patients were used, and both supervised and unsupervised learning methods were used. Clustering was conducted with hierarchical agglomerative clustering, K-means, bisecting K-means algorithm, Gaussian mixture model, and feature engineering was carried out using both medically researched methods and machine learning techniques. For classification, we used gradient boost-based models such as XGBoost, LightGBM, CatBoost, and Random Forest to predict the severity of OSAS. The developed model showed high performance with 88%, 88%, and 91% of classification accuracy for three thresholds for the severity of OSAS: Apnea-Hypopnea Index (AHI) $$\ge $$ ≥ 5, AHI $$\ge $$ ≥ 15, and AHI $$\ge $$ ≥ 30, respectively. The results of this study demonstrate significant evidence of sufficient potential to utilize machine learning in predicting OSAS severity. |
first_indexed | 2024-04-09T16:25:01Z |
format | Article |
id | doaj.art-3ac78ea3f07a4ba1b846486d650dedb7 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-09T16:25:01Z |
publishDate | 2023-04-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-3ac78ea3f07a4ba1b846486d650dedb72023-04-23T11:16:43ZengNature PortfolioScientific Reports2045-23222023-04-011311910.1038/s41598-023-33170-7Application of various machine learning techniques to predict obstructive sleep apnea syndrome severityHyewon Han0Junhyoung Oh1Department of Computer Engineering, Hongik UniversityInstitute for Business Research and Education, Korea UniversityAbstract As the incidence of obstructive sleep apnea syndrome (OSAS) increases worldwide, the need for a new screening method that can compensate for the shortcomings of the traditional diagnostic method, polysomnography (PSG), is emerging. In this study, data from 4014 patients were used, and both supervised and unsupervised learning methods were used. Clustering was conducted with hierarchical agglomerative clustering, K-means, bisecting K-means algorithm, Gaussian mixture model, and feature engineering was carried out using both medically researched methods and machine learning techniques. For classification, we used gradient boost-based models such as XGBoost, LightGBM, CatBoost, and Random Forest to predict the severity of OSAS. The developed model showed high performance with 88%, 88%, and 91% of classification accuracy for three thresholds for the severity of OSAS: Apnea-Hypopnea Index (AHI) $$\ge $$ ≥ 5, AHI $$\ge $$ ≥ 15, and AHI $$\ge $$ ≥ 30, respectively. The results of this study demonstrate significant evidence of sufficient potential to utilize machine learning in predicting OSAS severity.https://doi.org/10.1038/s41598-023-33170-7 |
spellingShingle | Hyewon Han Junhyoung Oh Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity Scientific Reports |
title | Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity |
title_full | Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity |
title_fullStr | Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity |
title_full_unstemmed | Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity |
title_short | Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity |
title_sort | application of various machine learning techniques to predict obstructive sleep apnea syndrome severity |
url | https://doi.org/10.1038/s41598-023-33170-7 |
work_keys_str_mv | AT hyewonhan applicationofvariousmachinelearningtechniquestopredictobstructivesleepapneasyndromeseverity AT junhyoungoh applicationofvariousmachinelearningtechniquestopredictobstructivesleepapneasyndromeseverity |