Accurate Diagnosis of Cardiac Disease with and Without Using GRIDSEARCHCV

Anticipating cardiovascular illness is viewed as quite possibly of the most difficult undertaking in the clinical field. It requires a great deal of investment and work to find out the root cause of this issue, particularly for specialists and other clinical specialists. In this project, different ML algorithms like SVM, linear regression, KNN, Random Forest, Naïve bayes, Decision tree along with the GridSearchCV is used to predict the cardiovascular disease. A five-fold cross-validation technique is used in this framework to perform verification. Additionally, a comparative study of six different methodologies is also presented. The Heart Disease Dataset from Kaggle is utilized to investigate the models' performance. Moreover, the scientific consequences of the proposed strategy are compared with previous heart disease forecast investigations. The primary aim of this project is to develop a revolutionary approach to tackle real world problems through the generation of innovative models. In this project, Random Forest classifier algorithm with and without GridsearchCV gives the best accuracy among the specified algorithms. It is observed that Random Forest algorithm using GridsearchCV gives highest accuracy as 98.70% and Random Forest algorithm without using GridsearchCV gives accuracy as 98.05%.