Why the study?
Hypertension is complex and leads to severe illnesses such as stroke and heart disease, creating a need to better understand the role of variables in modeling it and to evaluate decision tree predictive performance.
Can a decision tree machine learning model accurately predict hypertension?
Can a decision tree machine learning model accurately predict hypertension?
A decision tree machine learning model can predict hypertension with 90.5% accuracy, highlighting age, BMI, and average glucose level as key predictors.
Machine learning technology is used in advanced data analysis and optimization approaches for different kinds of medical problems. Hypertension is complicated, and every year it causes a lot of many severe illnesses such as stroke and heart disease. This study essentially had two primary goals. Firstly, this paper intends to understand the role of variables in hypertension modeling better. Secondly, the study seeks to evaluate the predictive performance of the decision trees. Based on these results, first, age, BMI, and average glucose level influence hypertension significantly, while other variables have an influence. Second, for the full model, the accuracy rate is 0.905, which implies that the error rate is 0.095. Among the patients who were predicted not to have hypertension, the accuracy that would not have hypertension was 90.51%, and the accuracy that had strike was 30.77% among the patients who were predicted to have hypertension.
No takes yet. Share an insight, caveat, or question.
Choi et al. (2020) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: