Cardiac disease is the major cause of deaths all over the world, with 17.9 million deaths annually, as per World Health Organization reports. The purpose of this study is to enable a cardiologist to early predict the patient’s condition before performing the echocardiography test. This study aims to find out whether diastolic function or diastolic dysfunction using symptoms through machine learning. We used the unexplored dataset of diastolic dysfunction disease in this study and checked the symptoms with cardiologist to be enough to predict the disease. For this study, the records of 1285 patients were used, out of which 524 patients had diastolic function and the other 761 patients had diastolic dysfunction. The input parameters considered in this detection include patient age, gender, BP systolic, BP diastolic, BSA, BMI, hypertension, obesity, and Shortness of Breath (SOB). Various machine learning algorithms were used for this detection including Random Forest, J.48, Logistic Regression, and Support Vector Machine algorithms. As a result, with an accuracy of 85.45%, Logistic Regression provided promising results and proved efficient for early prediction of cardiac disease. Other algorithms had an accuracy as follow, J.48 (85.21%), Random Forest (84.94%), and SVM (84.94%). Using a machine learning tool and a patient’s dataset of diastolic dysfunction, we can declare either a patient has cardiac disease or not.

The healthcare industry has a huge volume of patients’ health records but the discovery of hidden information using data mining techniques is missing. Data mining and its algorithm can help in this situation. This study aims to discover the hidden pattern from symptoms to detect early Stress Echocardiography before using Exercise Tolerance Test (ETT). During this study, raw ETT data of 776 patients are obtained from private heart clinic “The Heart Center Bahawalpur”, Bahawalpur, South Punjab, Pakistan. Duke treadmill score (DTS) is an output of ETT which classifies a patient’s heart is working normally or abnormally. In this work multiple machine learning algorithms like Support Vector Machine (SVM), Logistic Regression (LR), J.48, and Random Forest (RF) are used to classify patients’ hearts working normally or not using general information about a patient like a gender, age, body surface area (BSA), body mass index (BMI), blood pressure (BP) Systolic, BP Diastolic, etc. along with risk factors information like Diabetes Mellitus, Family History, Hypertension, Obesity, Old Age, Post-Menopausal, Smoker, Chest Pain and Shortness Of Breath (SOB). During this study, it is observed that the best accuracy of 85.16% is achieved using the Logistic Regression algorithm using the split percentage of 60-40.

No abstract