Key result
An ensemble machine learning model combining Adaptive Boosting and logistic regression accurately predicted incident hypertension within 5 years, achieving a balanced accuracy of 0.812 and an AUROC of 0.901.
Why the study?
Cardiovascular diseases are the primary cause of death worldwide with hypertension as a key contributor, motivating the use of machine learning to predict incident hypertension from demographic data across diverse populations.
Does an ensemble machine learning model accurately predict incident hypertension within 5 years using regular health checkup data in East Asian adults?
Cohort (n=1,541,463)
Does an ensemble machine learning model accurately predict incident hypertension within 5 years using regular health checkup data in East Asian adults?
An ensemble machine learning model using routine health checkup data accurately predicts incident hypertension within 5 years across diverse East Asian populations.
Answers are grounded in this paper and cite their sources.
Demographic ML models may aid hypertension prediction; leaves open prospective validation before clinical use.
BACKGROUND: Worldwide, cardiovascular diseases are the primary cause of death, with hypertension as a key contributor. In 2019, cardiovascular diseases led to 17.9 million deaths, predicted to reach 23 million by 2030. OBJECTIVE: This study presents a new method to predict hypertension using demographic data, using 6 machine learning models for enhanced reliability and applicability. The goal is to harness artificial intelligence for early and accurate hypertension diagnosis across diverse populations. METHODS: Data from 2 national cohort studies, National Health Insurance Service-National Sample Cohort (South Korea, n=244,814), conducted between 2002 and 2013 were used to train and test machine learning models designed to anticipate incident hypertension within 5 years of a health checkup involving those aged ≥20 years, and Japanese Medical Data Center cohort (Japan, n=1,296,649) were used for extra validation. An ensemble from 6 diverse machine learning models was used to identify the 5 most salient features contributing to hypertension by presenting a feature importance analysis to confirm the contribution of each future. RESULTS: The Adaptive Boosting and logistic regression ensemble showed superior balanced accuracy (0.812, sensitivity 0.806, specificity 0.818, and area under the receiver operating characteristic curve 0.901). The 5 key hypertension indicators were age, diastolic blood pressure, BMI, systolic blood pressure, and fasting blood glucose. The Japanese Medical Data Center cohort dataset (extra validation set) corroborated these findings (balanced accuracy 0.741 and area under the receiver operating characteristic curve 0.824). The ensemble model was integrated into a public web portal for predicting hypertension onset based on health checkup data. CONCLUSIONS: Comparative evaluation of our machine learning models against classical statistical models across 2 distinct studies emphasized the former's enhanced stability, generalizability, and reproducibility in predicting hypertension onset.
No takes yet. Share an insight, caveat, or question.
Hwang et al. (2024) conducted a cohort in Incident hypertension (n=1,541,463). AdaBoost and logistic regression ensemble model vs. Other machine learning models was evaluated on Prediction of incident hypertension within 5 years (Balanced accuracy 0.812, AUROC 0.901). An ensemble machine learning model combining Adaptive Boosting and logistic regression accurately predicted incident hypertension within 5 years, achieving a balanced accuracy of 0.812 and an AUROC of 0.901.
Synapse has enriched 10 related papers. Consider them for comparative context: