Predictive Modeling of Comorbid Anxiety in Young Hypertensive Patients Based on a Machine Learning Approach  

作　　者：Haiyan Xiao Aide Fan Zhiyong Liu Keping Yang 

机构地区：[1]Jingzhou Hospital Affiliated to Yangtze University,Jingzhou 434020,Hubei,China [2]Changde First Hospital of Traditional Chinese Medicine,Changde 415099,Hunan,China

出　　处：《Journal of Clinical and Nursing Research》2025年第4期130-136,共7页临床护理研究(英文)

摘　　要：Objective:To analyze the risk factors of anxiety in young hypertensive patients and build a prediction model to provide a scientific basis for clinical diagnosis and treatment.Methods:According to the research content,young hypertensive patients admitted to the hospital from January 2022 to December 2024 were selected as the research object and at least 950 patients were included according to the sample size calculation.According to the existence of anxiety,950 patients were divided into control group(n=650)and observation group(n=300),and the clinical data of all patients were collected for univariate analysis and multivariate Logistic regression analysis to get the risk factors of hypertension patients complicated with anxiety in.All patients were randomly divided into a training set(n=665)and a test set(n=285)according to the ratio of 7:3,and the evaluation efficiency of different prediction models was obtained by using machine learning algorithm.To evaluate the clinical application effect of the prediction model.Results:(1)Univariate analysis showed that age,BMI,education background,marital status,smoking,drinking,sleep disorder,family history of hypertension,history of diabetes,history of hyperlipidemia,history of cerebral infarction,and TC were important risk factors for young hypertensive patients complicated with anxiety.(2)Multivariate Logistic regression analysis showed that hypertension history,drinking history,coronary heart disease history,diabetes history,BMI,TC,and TG are important independent risk factors for young hypertensive patients complicated with anxiety.(3)Extra Trees has the highest predictive power for young people with hypertension complicated with anxiety,while Decision-Tree has the lowest predictive power.Conclusion:Hypertension history,drinking history,coronary heart disease history,diabetes history,BMI,TC,and TG are important independent risk factors that affect the anxiety of young hypertensive patients.Extra Trees model has the best prediction efficiency among different groups of

关 键 词：Machine learning method Youth hypertension ANXIETY Prediction model 

分 类 号：R544.1[医药卫生—心血管疾病]