Heart failure prediction based on random forest algorithm using genetic algorithm for feature selectio

A disorder or illness called heart failure results in the becoming weak damaged. In order to avoid early on, it is crucial understand causes of failure. Based on validation, two experimental processing steps will be applied dataset clinical records related Testing done first step utilizing six different classification algorithms, including K-nearest neighbor, neural network, random forest, decision tree, Naïve Bayes, and support vector machine (SVM). Cross-validation was employed conduct test. According results, forest algorithm performed better than other five algorithms tests employing algorithm. Subsequent testing uses an with best accuracy value, which then tested again using split validation varying ratios genetic as a selection feature. The value generated from feature alone, recorded produce 93.36% predicting survival patients.