Discrimination and Investigation of Cardiac Infarction gleaned from Various Machine Learning and Optimization Methods

The analysis of data in medical field is frequently increasing for analyzing the diagnoses, various research methods need to be filtered, and adequate equipment need to be arranged according to the importance of the pathology that appear. In AI various classification of software are considered for presenting the data for best prediction. The basic system model made by us is pretty much capable of doing various data processing algorithms for analyzing various diseases of heart. Our model works basically on a specific category of data. This analysis basically allows us in obtaining a model prediction from training and then testing the data. Various optimizing techniques need to be used for classifying the present data which will help in predicting the best results. Our model’s main purpose is building a basic framework for exploring the cardiac infarction based on various distinct algorithms like DT, Random Forest, LR and KNN along with some data samples which we have examined both the training and testing purpose. Here for the effective diagnosis, the research is done using the dataset of heart disease which is provided by the UCI Machine Repository. After having training and testing, some optimization techniques like stochastic gradient descent method have also implemented in our model to find out the more refined outcome. As a result, we have gained as an approximation of 97.78% of classification accuracy.