The medical condition known as hypertension, or high blood pressure, is
characterized by persistently elevated blood pressure against the arterial walls.
Generally speaking, an individual should maintain blood pressure from 120/80 mm Hg.
Whenever blood pressure continuously registers at 130/80 mm Hg or above,
hypertension is frequently diagnosed. The exact origins are unknown, but factors that
accelerate its growth include obesity, high-stress levels, aging, increased sodium
intake, and decreased physical activity. Numerous organs and systems inside the body
can be significantly impacted by hypertension or high blood pressure. It can cause
several major health issues and diseases, including renal disease and stroke if left
unchecked and untreated. When it comes to the identification and treatment of
hypertension, or high blood pressure, machine learning can be an invaluable tool. It can
help medical practitioners with several procedures, such as risk evaluation, early
detection, and individualized care. Decision-support tools that provide treatment
suggestions based on the most recent medical research and patient-specific data are one
way that machine learning can help healthcare providers. This can assist physicians in
making better-informed choices regarding medication and lifestyle modifications.
Patients with hypertension can benefit from individualized therapy regimens designed
with the help of machine learning. A variety of machine learning algorithms are
available for the prediction of hypertension and related risk variables, including
decision trees (DT), Random Forests (RF), gradient boosting machines (GBM),
extreme gradient boosting (XG Boost), logistic regression (LR), and linear discriminant
analysis (LDA). The quality of the available dataset and the suitable technique are
critical to the effectiveness of machine learning in the detection and management of
hypertension.
Keywords: Feature scaling, Hypertension, Healthcare, Random forest, Risk assessment, Stroke.
