Predicting Changes in Systolic and Diastolic Blood Pressure of Hypertensive Patients in Indonesia Using Machine...

Area of Science:

• Cardiology
• Medical Informatics
• Public Health

Background:

• Elevated blood pressure (hypertension) poses significant health risks, including heart failure, kidney failure, and cardiovascular disease.
• While numerous studies explore hypertension causes, few utilize machine learning for predictive analysis of blood pressure changes.
• Understanding factors influencing blood pressure reduction is crucial for effective hypertension management.

Purpose of the Study:

• To investigate sociodemographic, lifestyle, and clinical factors associated with decreased systolic and diastolic blood pressure.
• To employ machine learning algorithms for predicting blood pressure reduction in hypertensive individuals.
• To identify predictors for systolic and diastolic blood pressure decrease following antihypertensive drug treatment.

Main Methods:

• Retrospective analysis of patient data.
• Application of machine learning algorithms: Naïve Bayes, artificial neural network, logistic regression, and decision tree.
• Evaluation of factors including hypertension duration, substance consumption, exercise, and comorbidities like diabetes.

Main Results:

• Machine learning models demonstrated strong performance in predicting blood pressure decrease.
• Identified key factors influencing systolic and diastolic blood pressure reduction.
• The models can assist in predicting treatment response in hypertensive patients.

Conclusions:

• Machine learning offers a powerful tool for predicting blood pressure changes in hypertension management.
• Predictive models can aid clinicians in anticipating treatment outcomes for individual patients.
• Further research can refine these models for personalized hypertension therapy.