Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.

<h4>Purpose</h4>The aim is to develop a learning model based on clinical and survey data to assess sleep quality and identify determining factors affecting sleep quality in chronic obstructive pulmonary disease (COPD) patients.<h4>Methods</h4>The Pittsburgh Sleep Quality Inde...

Full description

Saved in:
Bibliographic Details
Main Authors: Miraç Öz, Banu Eriş Gülbay, Barış Bulut, Elif Akıncı Aydınlı, Aslıhan Gürün Kaya, Öznur Yıldız, Turan Acıcan, Sevgi Saryal
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0324480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850269815810293760
author Miraç Öz
Banu Eriş Gülbay
Barış Bulut
Elif Akıncı Aydınlı
Aslıhan Gürün Kaya
Öznur Yıldız
Turan Acıcan
Sevgi Saryal
author_facet Miraç Öz
Banu Eriş Gülbay
Barış Bulut
Elif Akıncı Aydınlı
Aslıhan Gürün Kaya
Öznur Yıldız
Turan Acıcan
Sevgi Saryal
author_sort Miraç Öz
collection DOAJ
description <h4>Purpose</h4>The aim is to develop a learning model based on clinical and survey data to assess sleep quality and identify determining factors affecting sleep quality in chronic obstructive pulmonary disease (COPD) patients.<h4>Methods</h4>The Pittsburgh Sleep Quality Index (PSQI) was administered to stable COPD patients to assess sleep quality. Patients were categorized into two groups: good sleep quality and poor sleep quality. Parameters for the best model were selected from a total of 61 clinical and laboratory parameters using recursive feature elimination (RFE) and the Bayesian Information Criterion (BIC). A logistic regression (LR) model was created. The model was evaluated using nested cross-validation with 5 inner and 5 outer folds, and this process was repeated with 1000 bootstrap iterations. Results were obtained with a 95% CI.<h4>Results</h4>The mean age of the 132 patients was 66.68 ± 8.16 years, with a predominance of males (117, or 88.6%). Of the 132 patients, 68 were in the poor sleep quality group. In this group, the prevalence of dyspnea, snoring, witnessed apneas, and excessive daytime sleepiness (EDS) was higher. The parameters included in the model and occurrence rates in the poor sleep quality group are as follows: annual exacerbation and hospitalization (71.9%), presence of EDS (35.9%), cough (64.1%), active smoking (95.4%), short-acting beta agonist (SABA) requirement (59.4%), pH level, and coronary artery disease (CAD) (20.3%). In our final model, the test set demonstrated a sensitivity, specificity, accuracy, and AUC of 70.21%, 71.76%, 70.99%, and 0.757, respectively.<h4>Conclusion</h4>Our machine learning model, developed using clinical data of COPD patients, can predict their sleep quality. We found that high annual exacerbation and hospitalization rates, the presence of EDS and cough symptoms, active smoking, and regular use of SABA as well as high pH levels, negatively affect sleep quality. Conversely, the presence of CAD under treatment in patients positively affects sleep quality.
format Article
id doaj-art-db5e0e0ae8cd4feda142d826dc0087bf
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-db5e0e0ae8cd4feda142d826dc0087bf2025-08-20T01:52:56ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032448010.1371/journal.pone.0324480Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.Miraç ÖzBanu Eriş GülbayBarış BulutElif Akıncı AydınlıAslıhan Gürün KayaÖznur YıldızTuran AcıcanSevgi Saryal<h4>Purpose</h4>The aim is to develop a learning model based on clinical and survey data to assess sleep quality and identify determining factors affecting sleep quality in chronic obstructive pulmonary disease (COPD) patients.<h4>Methods</h4>The Pittsburgh Sleep Quality Index (PSQI) was administered to stable COPD patients to assess sleep quality. Patients were categorized into two groups: good sleep quality and poor sleep quality. Parameters for the best model were selected from a total of 61 clinical and laboratory parameters using recursive feature elimination (RFE) and the Bayesian Information Criterion (BIC). A logistic regression (LR) model was created. The model was evaluated using nested cross-validation with 5 inner and 5 outer folds, and this process was repeated with 1000 bootstrap iterations. Results were obtained with a 95% CI.<h4>Results</h4>The mean age of the 132 patients was 66.68 ± 8.16 years, with a predominance of males (117, or 88.6%). Of the 132 patients, 68 were in the poor sleep quality group. In this group, the prevalence of dyspnea, snoring, witnessed apneas, and excessive daytime sleepiness (EDS) was higher. The parameters included in the model and occurrence rates in the poor sleep quality group are as follows: annual exacerbation and hospitalization (71.9%), presence of EDS (35.9%), cough (64.1%), active smoking (95.4%), short-acting beta agonist (SABA) requirement (59.4%), pH level, and coronary artery disease (CAD) (20.3%). In our final model, the test set demonstrated a sensitivity, specificity, accuracy, and AUC of 70.21%, 71.76%, 70.99%, and 0.757, respectively.<h4>Conclusion</h4>Our machine learning model, developed using clinical data of COPD patients, can predict their sleep quality. We found that high annual exacerbation and hospitalization rates, the presence of EDS and cough symptoms, active smoking, and regular use of SABA as well as high pH levels, negatively affect sleep quality. Conversely, the presence of CAD under treatment in patients positively affects sleep quality.https://doi.org/10.1371/journal.pone.0324480
spellingShingle Miraç Öz
Banu Eriş Gülbay
Barış Bulut
Elif Akıncı Aydınlı
Aslıhan Gürün Kaya
Öznur Yıldız
Turan Acıcan
Sevgi Saryal
Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.
PLoS ONE
title Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.
title_full Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.
title_fullStr Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.
title_full_unstemmed Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.
title_short Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients.
title_sort machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients
url https://doi.org/10.1371/journal.pone.0324480
work_keys_str_mv AT miracoz machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT banuerisgulbay machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT barısbulut machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT elifakıncıaydınlı machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT aslıhangurunkaya machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT oznuryıldız machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT turanacıcan machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients
AT sevgisaryal machinelearningmodelbasedonsurveyassessmentofsleepqualityinchronicobstructivepulmonarydiseasepatients