Machine Learning-Driven Prediction and Tailored Interventions for Heart Disease Prevention

Abstract

The heart is the major organ in the human body. The prevalence of many heart-related ailments is increasing, which
can be attributed to changes in human lifestyle, stress at work, and bad dietary habits. Numerous studies have shown
that heart disorders have been the leading cause of death in Sri Lanka. According to the 2018 data, 31% of cases were
due to stroke, 23% to coronary heart disease, and 14% to ischemic heart disease. As a result, an automated system is
required to increase medical efficiency and detect such disorders in time for proper treatment. The proposed approach
evaluates a patient's risk of getting heart disease using manual input criteria from physical and medical databases of
heart patients. The prediction procedure provides the patient a risk level based on their heart condition and
recommends a customized daily strategy to assist them avoid associated risks. It also features a food planner, an
exercise program, a stress reliever, and early warning systems. The system will provide an effective tool for
forecasting cardiac issues by analysing massive volumes of complex medical data using machine learning algorithms.
Some of the approaches used include decision tree classifiers, logistic regression, and random forests, among others.
The key goals of the study are to help patients adopt a healthy lifestyle and prevent their heart problems from
worsening.