Patient Health Monitoring System for Chronic Cardiac Attack Using Machine Learning

Cardiovascular disease is one of the prime principles of the demise globally. In nowadays usual contemporary life, demises on account of the cardiovascular disease had turn into one of crucial matters, that abruptly each individual lost his or her life every minute because of cardiovascular disorder. Forecasting the incidence of illness at early phases is a crucial threat these days. ML whenever executed in health protection is competent of rapid and precise identification of disorder. In this paper we provide a thorough analysis and development and implementation of a patient health monitoring system using Machine Learning techniques. The system is outlined to constantly observe and gather indispensable health data of patients in real-time, empowering healthcare providers to remotely detect and examine their health conditions. For implementing this monitoring system applying different ML algorithms, we have incorporated Logistic Regression, Naive Bayes, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Random Forest. Among these algorithms, Random Forest offered the highest accuracy.