Utilizing Fuzzy Logic in MATLAB for Visualizing Risk Factors associated with Cardiovascular Attacks

Data mining techniques are commonly used into clinical decision support systems to gather and diagnose various medical conditions accurately. Clinical decision support systems play an important role in cardiovascular disease diagnosis, showing their crucial role in recognizing significant death rates associated with heart disease globally. Heart disease prediction systems primarily use clinical datasets from lab analyses, but often overlook crucial factors like age, family history, diabetes, hypertension, hypercholesterolemia, nicotine/liquor use, obesity, or sedentary lifestyle. A system built upon these risk factors serves as a valuable tool for healthcare professionals, offering proactive indications of potential heart disease to patients. This proactive approach has reduced the need for hospital visits or expensive medical checkups. As a result, the current research presents a way for predicting heart disease by leveraging significant risk factors. This approach utilizes the highly effective fuzzy decision support system, a prominent tool in data mining, for enhancing risk stratification processes. The system uses patient age, blood pressure, blood cholesterol levels, and physical activity as input parameters to generate a single output giving the status of risk. This risk status is segmented into categories of varying severity, including "Not serious," "Serious," and "Very serious," facilitating determine risk assessment and stratification.