Hyperparameter Tuning Decision Tree and Recursive Feature Elimination Technique for Improved Chronic Kidney Disease Classification

Authors

  • Aries Gilang Saputra Universitas Dian Nuswantoro Author
  • Purwanto Purwanto Universitas Dian Nuswantoro Author
  • Pujiono Pujiono Universitas Dian Nuswantoro Author

DOI:

https://doi.org/10.15294/sji.v11i3.12990

Keywords:

Chronic kidney disease, Decision tree, Grid search cv, Hyperparameter tuning, Recursive feature elimination

Abstract

Purpose: This study has the purpose of classifying patients with chronic kidney disease based on specific features and improving the classification models by tuning hyperparameters. This study aims to detect chronic kidney disease at an early stage.

Methods: In this study, a machine learning classifier in the form of a decision tree is used to classify chronic kidney disease on the Risk Factor Prediction of Chronic Kidney Disease dataset. After that, the performance of the classifier model is improved by using feature selection, namely Recursive Feature Elimination and Hyperparameter tuning with GridSearchCV.

Result: After tests were conducted 3 times namely testing with Decision Tree, Recursive Feature Elimination, and Hyperparameter tuning GridSearchCV which is the proposed method, then compared to other tests. The results from this study is using that method can improve the Decision Tree classifier in classifying chronic kidney disease patients.

Novelty: Dataset that have been used in this study is from UCI machine learning repository namely Risk Factor Prediction of Chronic Kidney Disease that have 202 instances and 28 feature and after being processess and conducting test, Recursive Feature Elimination and Hyperparameter tuning GridSearchCV can improve the Decision Tree classifier in classifying chronic kidney disease.

Downloads

Article ID

12990

Published

06-11-2024

Issue

Section

Articles

How to Cite

Hyperparameter Tuning Decision Tree and Recursive Feature Elimination Technique for Improved Chronic Kidney Disease Classification. (2024). Scientific Journal of Informatics, 11(3), 821-830. https://doi.org/10.15294/sji.v11i3.12990