Prediction of Heart Disease Severity Measurment Using Deep Learning Techniques

Machine learning enables AI and is used in data analytics to overcome many challenges. Machine learning was the growing method of predicting outcomes based on existing data. The computer learns characteristics from the test implementation, then applies characteristics to an unknown dataset to predict the result. Classification is an essential technique of machine learning which is widely used for forecasting. Some classification techniques predict with adequate accuracy, while others show a small precision. This research investigates a process called machine learning classification, which combines different classifiers to enhance the precision of weak architectures. Experimentation using this tool was conducted using a database on heart disease. The collecting and measuring data method were designed to decide how to use the ensemble methodology to improve predictive accuracy in cardiovascular disease. This paper aims not only to enhance the precision of poor different classifiers but also to apply the algorithm with a neural network to demonstrate its usefulness in predicting disease in its earliest stages. The study results show that various classification algorithmic strategies, such as support vector machines, successfully improve the forecasting ability of poor classifiers and show satisfactory success in recognizing heart attack risk. Using ML classification, a cumulative improvement in the accuracy was obtained for poor classification models. That process efficiency was further improved with the introduction of feature extraction and selection, and the findings show substantial improvements in predictive power.