Development of a Predictive Model for Heart Disease Using Clinical Data: A Focus on Feature Selection & Algorithm Optimization

Heartdisease is increasingly common among individuals, including students & working professionals, with heart
stroke being the most prevalent condition. Diagnosing heart-related problems requires a combination of pathological & clinical data to ensure accuracy. Predicting these diseases accurately is crucial for researchers. This paper introduces a model for predicting heart disease aimed at assisting medical professionals in identifying potential issues based on clinical data. The approach involves selecting key clinical features such as age, body pain, blood pressure, & blood sugar levels. An algorithm is developed using this
data to achieve high accuracy & precision. Ultimately, a user-friendly Heart Disease Prediction Model (HDPM) is created to display prediction graphs, performance metrics (execution time,accuracy, specificity), & predicted results, facilitating the classification of heart disease.