Design and Deployment of ML Model for Cardiac Disease Prediction-A review

One of the most life-threatening diseases is cardiovascular disease. Its high fatality-rate catalysis nearly 17 million deaths worldwide. Prompt diagnosis assists in treating the disease at the right time to intercept mortality. Analyzing the existence and absence of the disease can be done using a variety of machine learning and deep learning techniques. In this review paper the complete procedure to make intelligent model is discussed. The UCI dataset is used in this project to classify cardiac disease using logistic regression techniques. To enhance the execution of the model, pre-processing of data by uncluttering the dataset, detecting the missing values is done and feature selection was accomplished by correlation with the target value for all the features. The distinctly positive correlated features were chosen. Then classification is performed by splitting the dataset into training data and testing data in the ratio of 80:20 split-up. The designed model secured 83.6% accuracy. The effectiveness of the proposed model was thoroughly gratifying and was competent to predict evidence of having heart disease in a certain individual which exhibited quality precision (77%) and recall (89%). This heart disease prediction system amplifies medical care and mitigates the cost. This research paper gives us significant knowledge that can help us predict, if the patient has a defective heart or not. The proposed work's evaluation has been carried out in Google Colab. Deployment has been done using the joblib library.