Key result
The XGBoost machine learning algorithm outperformed random forest and logistic regression in predicting the risk of hypertension in primary care, achieving an AUC of 0.765 in the testing set.
Why the study?
Hypertension prevention in primary care requires an effective and suitable risk assessment model, motivating the development and comparison of three machine learning algorithms.
Cross-Sectional (n=40,261)
Yes
Absolute Event Rate: 0.765% vs 0.756%
An XGBoost machine learning model using 20 routine clinical features outperformed random forest and logistic regression in predicting hypertension risk among primary care residents in China.
The prevention of hypertension in primary care requires an effective and suitable hypertension risk assessment model. The aim of this study was to develop and compare the performances of three machine learning algorithms in predicting the risk of hypertension for residents in primary care in Shanghai, China. A dataset of 40,261 subjects over the age of 35 years was extracted from Electronic Healthcare Records of 47 community health centres from 2017 to 2019 in the Pudong district of Shanghai. The XGBoost model outperformed the other two models and achieved an AUC of 0.765 in the testing set. Twenty features were selected to construct the model, including age, diabetes status, urinary protein, BMI, elderly health self-assessment, creatinine, systolic blood pressure of the upper right arm, waist circumference, smoking status, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, frequency of drinking, glucose, urea nitrogen, total cholesterol, diastolic blood pressure of the upper right arm, exercise frequency, time spent engaged in exercise, high salt consumption, and triglycerides. XGBoost outperformed random forest and logistic regression in predicting the risk of hypertension in primary care. Integration of such a risk assessment model into primary care may improve the prevention and management of hypertension in residents.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2022) conducted a cross-sectional in Hypertension (n=40,261). XGBoost machine learning algorithm vs. Random forest and logistic regression algorithms was evaluated on Area under the receiver operating characteristic curve (AUC) for predicting hypertension risk in the testing set. The XGBoost machine learning algorithm outperformed random forest and logistic regression in predicting the risk of hypertension in primary care, achieving an AUC of 0.765 in the testing set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: