PERBANDINGAN MODEL KLASIFIKASI RANDOM FOREST DENGAN RESAMPLING DAN TANPA RESAMPLING PADA PASIEN PENDERITA GAGAL JANTUNG

Cardiovascular disease that causes heart failure is one of the diseases with highest mortality rate in world. Therefore, there a need for an accurate model to classify based on clinical information and lifestyle patients disease, as alternative solution administering appropriate drugs. This study compared classification living deceased patient using random forest method when resampling techniques not techniques. The results obtained from this are Random Forest combination SMOTE Edited Nearest Neighbors methods best classifying someone alive or dead. has high level accuracy evaluation focuses recall, namely rf_model_smoteenn can 82.96% status 90% death status.