Detection of risk factors of hypertension in people with sleep disorders using machine learning

Background: Sleep disorders are one of the etiologic factors in the development of hypertension, and the risk of hypertension in patients with sleep disorders is increasing due to the increase in the prevalence of sleep disorders in recent years. We hypothesized that machine learning could establish a prediction model for hypertension in patients with sleep disorders. Methods: The data for patients diagnosed with sleep disorders were collected from two hospitals from 2019 to 2023, including medical history and biochemical indicators. After data processing, Logistic Regression, Decision Tree, Artificial Neural Network, Support Vector Machine, Naive Bayes, Adaptive Boosting, Random Forest, and Extreme Gradient Boosting (XGBoost) were selected for training. Five-fold cross-validation was used to evaluate the models, and accuracy, precision, recall, F1-score, and the area under the curve (AUC) were used to verify the discrimination and clinical practicability of the models. SHapley Additive exPlanation (SHAP) was used to explain the optimal model. Results: The XGBoost model was superior to other models, with an accuracy of 0.7216, a precision of 0.7576, a recall of 0.7660, an F1-score of 0.7430, and an AUC of 0.844. The SHAP results showed that age, weight, white blood cells, creatine, uric acid, glycosylated hemoglobin, and platelets were the risk factors of hypertension in people with sleep disorders, while high density lipoprotein cholesterol was a protective factor. Conclusion: Machine learning algorithms established a predictive risk model of hypertension in people with sleep disorders, which provides significant guidance to prevent and treat hypertension in people with sleep disorders. ### Competing Interest Statement The authors have declared no competing interest. ### Clinical Trial Registration number: ChiCTR2200059161. ### Funding Statement This work was supported by the grants from the National Natural Science Foundation of China (grant number 82274631), the Key Research and Development Plan of Jiangsu Province (Social Development, BE2021751), the Key Research and Development Plan of Jiangsu Province (Social Development, BE2023793) and Jiangsu Commission of Health (Prevention Subject, Ym2023105). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The Ethics Committee of Jiangsu Provincial Hospital of Chinese Medicine (Approved No. of ethic committee: 2021NL-202-02). I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes The data for this study are obtained from the electronic medical systems of Jiangsu Provincial Hospital of Chinese Medicine and Jiangsu Provincial Government Hospital. For patient privacy protection, the data of this study are only provided to some of the collaborators. Data supporting the study results can be obtained from the authors upon reasonable request.