Cargando…

Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome

This study compared the effects of 6 types of obstructive sleep apnea-hypopnea syndrome (OSAHS) prediction models to develop a reference for selecting OSAHS data mining tools in clinical practice. METHODS: This cross-sectional study included 401 cases. They were randomly divided into 2 groups: train...

Descripción completa

Detalles Bibliográficos
Autores principales: Luo, Miao, Feng, Yuan, Luo, Jingying, Li, XiaoLin, Han, JianFang, Li, Taoping
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Lippincott Williams & Wilkins 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9239632/
https://www.ncbi.nlm.nih.gov/pubmed/35776998
http://dx.doi.org/10.1097/MD.0000000000029724
_version_ 1784737343493636096
author Luo, Miao
Feng, Yuan
Luo, Jingying
Li, XiaoLin
Han, JianFang
Li, Taoping
author_facet Luo, Miao
Feng, Yuan
Luo, Jingying
Li, XiaoLin
Han, JianFang
Li, Taoping
author_sort Luo, Miao
collection PubMed
description This study compared the effects of 6 types of obstructive sleep apnea-hypopnea syndrome (OSAHS) prediction models to develop a reference for selecting OSAHS data mining tools in clinical practice. METHODS: This cross-sectional study included 401 cases. They were randomly divided into 2 groups: training (70%) and testing (30%). Logistic regression, a Bayesian network, an artificial neural network, a support vector learning machine, C5.0, and a classification and regression tree were each adopted to establish 6 prediction models. After training, the 6 models were used to test the remaining samples and calculate the correct and error rates of each model. RESULTS: Twenty-one input variables for which the difference between the patient and nonpatient groups was statistically significant were considered. The models found the abdominal circumference, neck circumference, and nocturia ≥2 per night to be the most important variables. The support vector machine, neural network, and C5.0 models performed better than the classification and regression tree, Bayesian network, and logistic regression models. CONCLUSIONS: In terms of predicting the risk of OSAHS, the support vector machine, neural network, and C5.0 were superior to the classification and regression tree, Bayesian network, and logistic regression models. However, such results were obtained based on the data of a single center, so they need to be further validated by other institutions.
format Online
Article
Text
id pubmed-9239632
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Lippincott Williams & Wilkins
record_format MEDLINE/PubMed
spelling pubmed-92396322022-06-30 Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome Luo, Miao Feng, Yuan Luo, Jingying Li, XiaoLin Han, JianFang Li, Taoping Medicine (Baltimore) Research Article This study compared the effects of 6 types of obstructive sleep apnea-hypopnea syndrome (OSAHS) prediction models to develop a reference for selecting OSAHS data mining tools in clinical practice. METHODS: This cross-sectional study included 401 cases. They were randomly divided into 2 groups: training (70%) and testing (30%). Logistic regression, a Bayesian network, an artificial neural network, a support vector learning machine, C5.0, and a classification and regression tree were each adopted to establish 6 prediction models. After training, the 6 models were used to test the remaining samples and calculate the correct and error rates of each model. RESULTS: Twenty-one input variables for which the difference between the patient and nonpatient groups was statistically significant were considered. The models found the abdominal circumference, neck circumference, and nocturia ≥2 per night to be the most important variables. The support vector machine, neural network, and C5.0 models performed better than the classification and regression tree, Bayesian network, and logistic regression models. CONCLUSIONS: In terms of predicting the risk of OSAHS, the support vector machine, neural network, and C5.0 were superior to the classification and regression tree, Bayesian network, and logistic regression models. However, such results were obtained based on the data of a single center, so they need to be further validated by other institutions. Lippincott Williams & Wilkins 2022-06-30 /pmc/articles/PMC9239632/ /pubmed/35776998 http://dx.doi.org/10.1097/MD.0000000000029724 Text en Copyright © 2022 the Author(s). Published by Wolters Kluwer Health, Inc. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License 4.0 (CCBY) (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Luo, Miao
Feng, Yuan
Luo, Jingying
Li, XiaoLin
Han, JianFang
Li, Taoping
Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
title Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
title_full Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
title_fullStr Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
title_full_unstemmed Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
title_short Predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
title_sort predictive performances of 6 data mining techniques for obstructive sleep apnea-hypopnea syndrome
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9239632/
https://www.ncbi.nlm.nih.gov/pubmed/35776998
http://dx.doi.org/10.1097/MD.0000000000029724
work_keys_str_mv AT luomiao predictiveperformancesof6dataminingtechniquesforobstructivesleepapneahypopneasyndrome
AT fengyuan predictiveperformancesof6dataminingtechniquesforobstructivesleepapneahypopneasyndrome
AT luojingying predictiveperformancesof6dataminingtechniquesforobstructivesleepapneahypopneasyndrome
AT lixiaolin predictiveperformancesof6dataminingtechniquesforobstructivesleepapneahypopneasyndrome
AT hanjianfang predictiveperformancesof6dataminingtechniquesforobstructivesleepapneahypopneasyndrome
AT litaoping predictiveperformancesof6dataminingtechniquesforobstructivesleepapneahypopneasyndrome