Perbandingan Kinerja Algoritma Naive Bayes, Support Vector Machine dan Random forest untuk Prediksi Penyakit Ginjal Kronis

Abstract

Chronic kidney disease (CKD) is a serious condition that affects human health worldwide, leading to a gradual decline in kidney function and triggering severe complications, including kidney failure. Early prediction of CKD can provide significant benefits in preventing serious complications and enabling timely interventions. In recent decades, the use of algorithm-based predictive methods in data science has shown great potential in the field of healthcare, including disease prediction. This research aims to compare the performance of three algorithms, namely Naive Bayes, SVM, and Random Forest. The test results show that, with a data split of 70% for training and 30% for testing, the classification processing using the Naive Bayes algorithm achieved an accuracy of 97.14%, while the classification processing using the Support Vector Machine algorithm achieved 92.50%, and the Random Forest algorithm achieved 99.64%. This study demonstrates that the Random Forest algorithm performs the best in predicting Chronic Kidney Disease.

Keywords : Chronic kidney disease; Naive Bayes; Support Vector Machine; Random forest; Predictions