Health play’s vital role in everyone’s life. To protect our health, it is crucial to monitor early signs of fatal diseases so that we can take preventative steps to lessen their impact. The diseases that threaten life the most frequently are those that affect the heart. According to studies, there are several heart conditions that might lead to heart disease, including high blood pressure, chronic diabetes, ageing, and family dynamics. But nowadays, people are having heart attacks for a variety of causes, including ignorance of their health. Therefore, it is necessary to identify the factors driving the attack to foresee the presence of the problem. For this prediction, machine learning methods are used. With the training data provided, machines can learn effectively and accurately predict the presence of heart problems. Even machines require processed, reliable data to understand the information provided. If the data is large in dimensions and has missing values, machines will not succeed. As a result, dimensionality reduction must be used, and accuracy must be examined using various classification techniques. Applying PCA and random forest classification algorithms can predict cardiac disease with a 97.80% of accuracy.

Machine learning,Prediction,Random forest,Dimensionality Reduction, Heart disease.