Nature and Science of Sleep (Jan 2025)
Development and Evaluation of a Hypertension Prediction Model for Community-Based Screening of Sleep-Disordered Breathing
Abstract
Tong Feng,1 Guangliang Shan,2 Yaoda Hu,2 Huijing He,2 Guo Pei,1 Ruohan Zhou,1 Qiong Ou1 1Sleep Center, Department of Geriatric Respiratory, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, People’s Republic of China; 2Department of Epidemiology and Statistics, Institute of Basic Medical Sciences, School of Basic Medicine, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, People’s Republic of ChinaCorrespondence: Qiong Ou, Sleep Center, Department of Geriatric Respiratory, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, No. 106 Zhongshan Road, Yuexiu District, Guangzhou City, Guangdong Province, People’s Republic of China, Tel +86 13609717251, Email [email protected]: Approximately 30% of patients with sleep-disordered breathing (SDB) present with masked hypertension, primarily characterized by elevated nighttime blood pressure. This study aimed to develop a hypertension prediction model tailored for primary care physicians, utilizing simple, readily available predictors derived from type IV sleep monitoring devices.Patients and Methods: Participants were recruited from communities in Guangdong Province, China, between April and May 2021. Data collection included demographic information, clinical indicators, and results from type IV sleep monitors, which recorded oxygen desaturation index (ODI), average nocturnal oxygen saturation (MeanSpO2), and lowest recorded oxygen saturation (MinSpO2). Hypertension was diagnosed using blood pressure monitoring or self-reported antihypertensive medication use. A nomogram was constructed using multivariate logistic regression after Least Absolute Shrinkage and Selection Operator (LASSO) regression identified six predictors: waist circumference, age, ODI, diabetes status, family history of hypertension, and apnea. Model performance was evaluated using area under the curve (AUC), calibration plots, and decision curve analysis (DCA).Results: The model, developed in a cohort of 680 participants and validated in 401 participants, achieved an AUC of 0.775 (95% CI: 0.730– 0.820) in validation set. Calibration plots demonstrated excellent agreement between predictions and outcomes, while DCA confirmed significant clinical utility.Conclusion: This hypertension prediction model leverages easily accessible indicators, including oximetry data from type IV sleep monitors, enabling effective screening during community-based SDB assessments. It provides a cost-effective and practical tool for prioritizing early intervention and management strategies in both primary care and clinical settings.Keywords: sleep-disordered breathing, prediction model, hypertension, risk predictors
