AUTHOR=Ji Weidong , Zhang Yushan , Cheng Yinlin , Wang Yushan , Zhou Yi 

TITLE=Development and validation of prediction models for hypertension risks: A cross-sectional study based on 4,287,407 participants

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.928948

DOI=10.3389/fcvm.2022.928948

ISSN=2297-055X

ABSTRACT=Objective: To develop an optimal screening model identifying the individuals with high-risk of hypertension in China through comparing tree-based machine learning models such as classification and regression tree, random forest, adaboost with decision tree, extreme gradient boosting decision tree, other machine learning models like artificial neural network, naive bayes, and traditional logistic regression models.
Methods: A total of 4,287,407 adults participating in the national physical examination were included in the study. Features were selected using the least absolute shrinkage and selection operator regression. Borderline-synthetic minority over-sampling technique was used for data balance. Non-laboratory and semi-laboratory analyses were carried out in combination with the selected features. The tree-based machine learning models, other machine learning models, and traditional logistic regression models were constructed to identify individuals with hypertension, respectively. Top features selected using the best algorithm and the corresponding variable importance score were visualized.
Results: 24 variables were finally included for analyses after least absolute shrinkage and selection operator regression model. The sample size of hypertensive in the training set was expanded from 689,025 to 2,312,160 using borderline-synthetic minority over-sampling technique algorithm. Extreme gradient boosting decision tree algorithm had the best results (area under the receiver operating characteristic curve of non-laboratory: 0.893, area under the receiver operating characteristic curve of semi-laboratory: 0.894). This study found that age, systolic blood pressure, waist circumference, diastolic blood pressure, albumin, drinking frequency, electrocardiogram, ethnicity(uyghur, hui, other), body mass index, sex(female), exercise frequency, diabetes mellitus and total bilirubin are important factors reflecting hypertension. Besides, some algorithms included in the semi-laboratory analyses showed less improvement in predictive performance compared to the non-laboratory analyses.
Conclusions: Using multiple methods, more significant prediction model can be built, which discovers risk factors and provides new insights into the prediction and prevention of hypertension.