A worldwide health issue, cardiovascular disease necessitates advanced diagnostic methods and preventative measures. This project's objective is to use machine learning to give early heart failure identification and risk assessment. Classify cardiovascular risk using logistic regression, a trustworthy machine learning technique. Before giving them the list, use exploratory data analysis (EDA) approaches to comprehend parameter distribution and enable major data set adjustments. To find significant risk indicators, apply feature importance assessment, correlation analysis, and predictive modelling. The experimental study showed a stunning 97% classification accuracy for cardiovascular risk variables, indicating the efficacy of the suggested approach. In order to regularly display significant risk variables that raise the risk of heart disease, this work integrated EDA and machine learning techniques. EDA and machine learning together make a potent tool for identifying and preventing cardiovascular disease. This study aids in the creation of predictive models and the formulation of health care policy by identifying significant risk factors. In order to assist preventative health initiatives, future research endeavours ought to concentrate on enhancing prediction models and encouraging interdisciplinary collaboration.
Artificial Intelligence, Machine learning, convolutional neural networks, support vector machines (SVM)