A Model for Coronary Heart Disease Prediction Using Data Mining Classification Techniques

Abstract

Nowadays the guts malady is one amongst the foremost causes of death within the world. Thus it s early prediction and diagnosing is vital in medical field, which might facilitate in on time treatment, decreasing health prices and decreasing death caused by it. The treatment values the disease is not cheap by most of the patients and Clinical choices are usually raised supported by doctors‟ intuition and skill instead of on the knowledge-rich information hidden within the stored data. The model  for prediction of heart disease using a classification techniques in data mining reduce medical errors, decreases unwanted exercise variation, enhance patient well-being and improves patient results. The model has been developed to support decision making in heart disease prediction based on data mining techniques. The experiments were performed using the model, based on the three techniques, and their accuracy in prediction noted. The decision tree, naïve Bayes, KNN (K-Nearest Neighbors) and WEKA API (Waikato Environment for Knowledge Analysis-application programming interface) were the various data mining methods that were used. The model predicts the likelihood of getting a heart disease using more input medical attributes. 13 attributes that is: blood pressure, sex, age, cholesterol, blood sugar among other factors such as genetic factors, sedentary behavior, socio-economic status and race has been use to predict the likelihood of patient getting a Heart disease until now. This study research added two more attributes that is: Obesity and Smoking.740 Record sets with medical attributes was obtained from a publicly available database for heart disease from machine learning repository with the help of the datasets, and the patterns significant to the heart attack prediction was extracted and divided into two data sets, one was used for training which consisted of 296 records & another for testing consisted of 444 records, and the fraction of accuracy of every data mining classification that was applied was used as standard for performance measure. The performance was compared by calculating the confusion matrix that assists to find the precision recall and accuracy. High performance and accuracy was provided by the complete system model. Comparison between the proposed techniques and the existing one in the prediction capability was presented. The model system assists clinicians in survival rate prediction of an individual patient and future medication is planned for. Consequently, the families, relatives, and their patients can plan for treatment preferences and plan for their budget consequently.