Abstract

Hypertension, commonly referred to as high blood pressure, stands as a global health concern, carrying significant complications and placing substantial burdens on healthcare systems, particularly in lower-income countries (Perkovic et al. 2007). It is the most common chronic disease worldwide and a leading preventable cause of premature mortality (Chang et al. 2019). It poses a substantial risk factor for cardiovascular disease, the leading cause of mortality (LaFreniere et al. 2016). Past research has applied machine learning (ML) techniques to hypertension studies to uncover complex patterns and relationships in extensive datasets (LaFreniere et al. 2016). ML tools have the potential to identify key factors among various medical indicators, facilitating precise predictions and personalized treatment plans (Chang et al. 2019). Previous research has focused on predicting hypertension from heart rate data (Pillai and Lohani 2020). However, the existing studies have limitations. First, they were conducted on a limited dataset, potentially missing crucial relations between patient symptoms and measurements. Second, past works commonly have an inadequate emphasis on other characteristics of patients that could interact with blood pressure measurements and impact health outcomes, mainly cardiovascular diseases. To the best of our knowledge, the current ML works regarding blood pressure mainly focused on hypertension as a secondary issue. This study uses advanced models to identify early biomarkers for hypertension progression and associated complications. We predicted hypertension based on patient data, medication, comorbidities, diagnoses, procedures, lifestyle, and socio-demographic characteristics.

Share

COinS