Machine Learning project to predict heart diseases
Cardiac Arrhythmia is a of a group of conditions in which the electrical activity of the heart is irregular or is faster or slower than normal. It is the leading cause of death for both men and women in the world. In this project, we plan to predict Cardiac Arrhythmia based on a patient’s medical record. Our objective is to classify a patient into one of the Arrhythmia classes like Tachycardia and Bradycardia based on his ECG measurements and help us in understanding the application of machine learning in medical domain. After appropriate feature selection we plan to solve this problem by using Machine Learning Algorithms namely K Nearest Neighbour, Logistic Regression, Naïve Bayes and SVM.
The diagnosis of cardiac arrhythmia can be classified into various classes based on the Electrocardiogram(ECG) readings and other attributes. First class will refer to the normal patient while other classes shall represent different classes of cardiac arrhythmia like Tachycardia, Bradycardia and Coronary artery diseases. This is a supervised learning problem. The dataset for the project is taken from the UCI Repositoryhttps://archive.ics.uci.edu/ml/datasets/Arrhythmia
The variable Class is our target variable. There are in total 13 classes –
No. CLASS INSTANCES
1 Normal 245
2 Ischemic changes (Coronary Artery) 44
3 Old Anterior Myocardial Infarction 15
4 Old Inferior Myocardial Infarction 15
5 Sinus tachycardia 13
6 Sinus bradycardia 25
7 Ventricular Premature Contraction (PVC) 3
8 Supraventricular Premature Contraction 2
9 Left bundle branch block 9
10 Right bundle branch block 50
11 Left ventricle hypertrophy 4
12 Atrial Fibrillation or Flutter 5
13 Others 22