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

Miraç Öz, Banu Eriş Gülbay, Peace Cloud, Elif Akinci Aydinli, Aslihan Gürün Kaya, Oznur Yildiz, Turan Acican,  Sevgi Saryal

Abstract

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.

Introduction

Chronic obstructive pulmonary disease (COPD) is a heterogeneous lung disease that is characterized by chronic respiratory symptoms (such as dyspnea, cough, sputum production, and exacerbations) caused by irreversible, usually worsening obstruction of airflow in the airways (bronchitis, bronchiolitis) and abnormalities in the air spaces (emphysema) [1].

Materials and methods

Our study was conducted prospectively between January 01, 2023, and January 01, 2024, including stable COPD patients who presented to the Chest Diseases outpatient clinic, with the approval of the Ankara University Faculty of Medicine Ethics Committee dated August 01, 2022 (approval number: İ07-397-22).

Results

The study included 132 patients diagnosed with stable COPD who consented to participate. These patients were categorized based on their sleep quality as assessed by the PSQI.

Discussion

Assessing sleep quality in patients with COPD is crucial for improving their overall health and patient care. The current literature indicates that various machine learning models have been developed to predict sleep quality based on data collected using wearable devices or polysomnography [6,22].

Conclusion

There is no model developed in the literature to predict poor sleep quality in COPD patients. In our study, the model we developed, which includes the number of annual exacerbations and hospitalizations, the presence of EDS and cough, smoking status, pH values, SABA use, and CAD presence, can be used to predict sleep quality in COPD patients.

Citation: Öz M, Gülbay BE, Bulut B, Aydınlı EA, Kaya AG, Yıldız Ö, et al. (2025) Machine learning model based on survey assessment of sleep quality in chronic obstructive pulmonary disease patients. PLoS One 20(5): e0324480. https://doi.org/10.1371/journal.pone.0324480

Editor: Thomas Penzel, Charité - Universitätsmedizin Berlin, GERMANY

Received: January 21, 2025; Accepted: April 25, 2025; Published: May 21, 2025

Copyright: © 2025 Öz et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All relevant data are within the manuscript.

Funding: The author(s) received no specific funding for this work.

Competing interests: The authors have declared that no competing interests exist.