Heart Disease Prediction using KNN

This repository demonstrates the project of “Heart Disease Prediction using Machine Learning”. This project has been created by implementing the K Nearest Neighbors Algorithm. Initially, the Machine Learning model of KNN Algorithm is trained 67% using heart_disease_train dataset and later on the expected results are tested and obtained successfully with 33% of dataset used for the testing purposes. The accuracy of around 85.06 % was achieved after the successful execution of the Machine Learning Model.

Introduction

Among various life-threatening diseases, heart disease has garnered a great deal of attention in medical research. The diagnosis of heart disease is a challenging task, which can offer an automated prediction about the heart condition of the patient so that further treatment can be made effective. The diagnosis of heart disease is usually based on signs, symptoms, and physical examination of the patient. There are several factors that increase the risk of heart diseases, such as smoking habits, body cholesterol level, family history of heart disease, obesity, high blood pressure, and lack of physical exercise.

Heart disease describes a range of conditions that affect your heart. Diseases under the heart disease umbrella include blood vessel diseases, such as coronary artery disease, heart rhythm problems (arrhythmias) and heart defects you’re born with (congenital heart defects), among others.

This project was implemented and executed by applying the KNN algorithm with a recognition accuracy of around 85.06%. The desired results have been obtained by training the machine learning model first using 67% of the heart_disease_train data-set and later testing the model by remaining 33% of dataset and the results are obtained successfully. Concludes, that around 85.06% of patients with the symptoms as according to the dataset would suffer from heart diseases. 

Screenshots

Data Analysis

Output