Prediction of Cardiovascular Disease using Machine Learning Algorithms with Relief and Lasso Feature Selection Techniques

Authors

  • Ms. Lakshmi Devi Kadali, Prof. V. S. Ramakrishna, Dr. Chandra Mouli VSA, Dr. Rajasekhar, Gunamani Jena

DOI:

https://doi.org/10.17762/msea.v71i4.1121

Abstract

Cardiovascular diseases (CVD) are one of the most common types of serious illnesses. Early diagnosis can help stop or lessen the effects of CVDs, which could lower death rates. Using machine learning models to find risk factors is a promising idea. We'd like to suggest a model that uses different methods to predict heart disease more accurately. For our proposed model to work, we used efficient methods for Data Collection, Data Pre-processing, and Data Transformation to get accurate data for training the model. We used a group of datasets (Cleveland, Long Beach VA, Switzerland, Hungarian and Stat log). The Relief and Least Absolute Shrinkage and Selection Operator (LASSO) techniques are used to choose the right features. By combining traditional classifiers with bagging and boosting methods, which are used in the training process, new hybrid classifiers like Decision Tree Bagging Method (DTBM), Random Forest Bagging Method (RFBM), K-Nearest Neighbors Bagging Method (KNNBM), AdaBoost Boosting Method (ABBM), and Gradient Boosting Boosting Method (GBBM) are made. We also used some machine learning algorithms to figure out the Accuracy (ACC), Sensitivity (SEN), Error Rate, Precision (PRE), and F1 Score (F1) of our model, as well as the Negative Predictive Value (NPR), False Positive Rate (FPR), and False Negative Rate (FNR). We used Convolution 2D Neural Networks because other algorithms didn't give the best results and this algorithm is a deep learning and advanced version of all existing

Downloads

Published

2022-10-18

How to Cite

Ms. Lakshmi Devi Kadali, Prof. V. S. Ramakrishna, Dr. Chandra Mouli VSA, Dr. Rajasekhar, Gunamani Jena. (2022). Prediction of Cardiovascular Disease using Machine Learning Algorithms with Relief and Lasso Feature Selection Techniques. Mathematical Statistician and Engineering Applications, 71(4), 5356–5372. https://doi.org/10.17762/msea.v71i4.1121

Issue

Section

Articles