An ensemble based decision support framework for intelligent heart disease diagnosis

摘要: Large amount of medical data leads to the need intelligent mining tools in order extract useful knowledge. Researchers have been using several statistical analysis and techniques improve disease diagnosis accuracy healthcare. Heart is considered as leading cause deaths worldwide over past 10 years. Several researchers introduced different for heart diagnosis. Using a single technique shows an acceptable level Recently, more research carried out towards hybrid models which show tremendous improvement accuracy. The objective proposed predict patient accurately. framework uses majority vote based novel classifier ensemble combine classifiers. UCI dataset used results evaluation. Analysis that sensitivity, specificity are higher compared individual techniques. We obtained 82% accuracy, 74% sensitivity 93% dataset.