PREDICTION OF PRE-CARDIAC DISEASE USING ML & DL TECHNIQUES IN T-KINTER

Main Article Content

Dr. G. Vishnupriya, Pradeep T, Mehanethra M, Ajay Mitra VJ

Abstract

One of the biggest issues facing the globe today is heart disease. The prediction of cardiovascular illness presents a significant problem for clinical data analysis. Hybrid machine learning (ML) has demonstrated its ability to effectively support decision-making and prediction from the vast amounts of data generated by the healthcare sector and hospitals. Additionally, we have observed the employment of ML approaches in recent advancements across several IoT domains (IoT). Only a few research have used machine learning to predict cardiac disease. The narrative approach we suggest in this study tries to identify relevant features by utilising Deep learning techniques, which is the accuracy of cardiovascular disease prediction.  Classification Techniques used in the prediction model include Logistic Regression, Naive Bayes, Support Vector Machine, K Nearest Neighbors, Decision Tree, Random Forest, and XGBoost Artificial Neural Network with 1 Hidden layer. By using a hybrid random forest and DL technique Neural network to create a prediction model for heart disease, we are able to improve performance with a 92% accuracy rate. Each algorithm's accuracy is calculated along with the model's accuracy. The next step is to select the one with good accuracy. The suggested methodology combines all the data into a classification algorithm and use the Tkinter programme to compare current healthcare data with information from that particular reference distribution.

Article Details

Section
Articles