Design and Analysis of Heart Attack Prediction System Using ML

Any diseases that is kept untreated for a long period of time directly impacts the human health and effect all the major organs of the body. Treating the chronic diseases in timely basis is highly recommended to avoid major medical problems coming over the way. On implementing Chronic Heart Attack prediction system using Hybrid SMLT (Split Multi Link trunking) technique is presented here. The proposed system considers machine learning algorithm in which Logistic regression (LR), multi-level perceptron (MLP) based on neural network, CatBoost regression (CB) algorithm and Random Forest regression algorithm (RF) is comparatively tested. Considering the data set provided, the presented approach is implemented using Python IDE and simulated in IoT (Internet of things) screen of Google Collab. A comparative analysis of various Machine learning algorithm is helpful to make the accurate processing with the help of robust method in short span of time. Further different machine learning techniques, with multiple features are considered as scope of implementation. The proposed approach is creating a machine learning model that can predict whether or not a person will experience a heart attack. The best model is used to forecast the result after many techniques have been compared.