Screening prediction models using artificial intelligence for moderate-to-severe obstructive sleep apnea in patients with acute ischemic stroke

Huan-Jan Lin; Tian-Hsiang Huang; Hui-Ci Huang; Pao-Li Hsiao; Wen-Hsien Ho

doi:10.1016/j.jstrokecerebrovasdis.2024.108214

Screening prediction models using artificial intelligence for moderate-to-severe obstructive sleep apnea in patients with acute ischemic stroke

J Stroke Cerebrovasc Dis. 2024 Dec 24;34(2):108214. doi: 10.1016/j.jstrokecerebrovasdis.2024.108214. Online ahead of print.

Authors

Huan-Jan Lin¹, Tian-Hsiang Huang², Hui-Ci Huang³, Pao-Li Hsiao⁴, Wen-Hsien Ho⁵

Affiliations

¹ Doctoral Degree Program in Biomedical Engineering, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan; Department of Neurology, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan; Post Baccalaureate Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan.
² Department of Computer Science and Information Engineering, National Penghu University of Science and Technology, No.300, Liuhe Rd., Magong, Penghu 880011, Taiwan.
³ Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, Taiwan.
⁴ Department of Neurology, E-DA Hospital, Kaohsiung, Taiwan.
⁵ Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, 100, Ziyou 1st Road, Sanmin District, Kaohsiung 807, Taiwan; Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan; College of Professional Studies, National Pingtung University of Science and Technology, Pingtung, Taiwan. Electronic address: whho@kmu.edu.tw.

PMID: 39722420
DOI: 10.1016/j.jstrokecerebrovasdis.2024.108214

Abstract

Background: Obstructive sleep apnea (OSA) is common after stroke. Still, routine screening of OSA with polysomnography (PSG) is often unfeasible in clinical practice, primarily because of how limited resources are and the physical condition of patients. In this study, we used several artificial intelligence techniques to predict moderate-to-severe OSA and identify its features in patients with acute ischemic stroke.

Methods: A total of 146 patients with acute ischemic stroke underwent PSG screening for OSA. Their baseline demographic characteristics, including age, sex, body mass index (BMI), Epworth Sleepiness Scale (ESS) score, and stroke risk factors, were recorded. Logistic regression analysis was conducted to identify significant features associated with moderate-to-severe OSA in patients with stroke. These significant features were used with six machine learning and ensemble learning algorithms, namely decision tree, support vector machine, random forest, extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and gradient boosting, to compare the performance of several predictive models.

Results: Multivariate logistic regression analysis revealed that age, sex, BMI, neck circumference, and ESS score were significantly associated with the presence of moderate-to-severe OSA. According to the machine learning and ensemble learning results, the XGBoost model achieved the highest performance, with an area under the receiver operating characteristic curve of 0.89 and an accuracy and F1 score of 0.80.

Conclusion: This study identified key factors contributing to moderate-to-severe OSA in patients with ischemic stroke. The XGBoost model exhibited high predictive performance, indicating it has potential as a supporting tool for decision-making in health-care settings.

Keywords: Cerebral ischemia; Ensemble learning; Ischemic stroke; Machine learning; Obstructive sleep apnea; Sleep-disordered breathing.