Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Multidiciplinary Output Research for Actual and International Issue (Morfai Journal)
Doli Indra Harahap
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Social Sciences Other

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
CLASSIFICATION OF CHRONIC KIDNEY DISEASE USING THE XGBOOST METHOD Doli Indra Harahap; Damayanti
Multidiciplinary Output Research For Actual and International Issue (MORFAI) Vol. 5 No. 5 (2025): Multidiciplinary Output Research For Actual and International Issue
Publisher : RADJA PUBLIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54443/morfai.v5i5.4321

Abstract

Chronic Kidney Disease (CKD) is a global health problem that requires early diagnosis to prevent serious complications. This study aims to develop a CKD classification model using the XGBoost algorithm on the Kidney Disease dataset with 16,432 samples, which includes clinical features such as smoking status, diabetes mellitus, hypertension, BMI, and CRP. The method includes data preprocessing (missing value handling, categorical coding, normalization), dataset splitting (80% training, 20% testing), and hyperparameter optimization through grid search with 3-fold cross-validation. The XGBoost model was configured with optimal parameters (subsample 1.0, n_estimators 200, max_depth 6, learning_rate 0.2, colsample_bytree 0.8) for multi-class classification of CKD risk. The evaluation results showed an accuracy of 87.33%, with a macro avg F1-score of 0.87, a precision of 0.87, and a recall of 0.87, confirming balanced performance across all classes. Important features such as CRP and diabetes mellitus contribute significantly, supporting clinical interpretability. The conclusion of this study indicates that XGBoost is effective for CKD diagnosis, with potential integration into electronic health systems for mass screening, although further validation is needed on local Indonesian data. This research contributes to machine learning-based diagnostic innovations to reduce the burden of CKD.
Co-Authors Damayanti