OPTIMIZING THE KNN ALGORITHM FOR CLASSIFYING CHRONIC KIDNEY DISEASE USING GRIDSEARCHCV
Open Access
- 3 February 2025
- journal article
- Published by LPPM Universitas Nusa Mandiri in JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer)
- Vol. 10 (3) , 680-689
Abstract
Chronic Kidney Disease (CKD) is a progressive condition that impairs kidney function and cannot be cured. Early detection is crucial for effective management and therapy. However, diagnosing CKD is challenging as patients often have comorbidities such as diabetes, hypertension, or heart disease, which complicate diagnosis and treatment. Accurate classification methods are essential for early detection. K-Nearest Neighbor (KNN) is a classification algorithm that groups data based on feature similarity. K-NN is an algorithm that is resistant to outliers, easy to implement, and highly adaptable. It only requires distance calculations between data points and does not involve complex parameters. However, its performance depends on hyperparameters such as the number of neighbors (k), weighting, and distance metric. Incorrect hyperparameter selection can lead to overfitting, underfitting, or reduced accuracy. To address these issues, GridSearchCV is used to optimize KNN by systematically selecting the best hyperparameters, ensuring improved accuracy and reduced overfitting. This optimization enhances the model’s reliability in early CKD detection compared to other methods. This study aims to determine the optimal KNN parameters for CKD classification using GridSearchCV. The results show 8.05% accuracy improvement and reduction in overfitting, with the prediction gap between training and testing decreasing from 6% to only 1.15%. These enhancements contribute to more reliable CKD diagnosis, enabling accurate early detection and better clinical decision-making.Keywords
This publication has 28 references indexed in Scilit:
- K-Nearest Neighbor Method for Early Detection of Diabetes Patients Based on Symptoms and Clinical DataInform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 2024
- Implementasi Optimasi Hyperparameter GridSearchCV Pada Sistem Prediksi Serangan Jantung Menggunakan SVMTeknologi, 2023
- Klasifikasi Penyakit Stroke Menggunakan Algoritma K-Nearest Neighbor (KNN)ROUTERS: Jurnal Sistem dan Teknologi Informasi, 2022
- Implementasi Algoritma Naïve Bayes Classifier (NBC) untuk Klasifikasi Penyakit Ginjal KronikJurnal Sistem Komputer dan Informatika (JSON), 2022
- Efficient Medical Diagnosis of Human Heart Diseases Using Machine Learning Techniques With and Without GridSearchCVIEEE Access, 2022
- Penurunan Intensitas Rasa Haus Pasien Penyakit Ginjal Kronik Yang Menjalani Hemodialisa Dengan Menghisap Es BatuNers Muda, 2021
- Optimasi Akurasi Metode Convolutional Neural Network untuk Identifikasi Jenis SampahJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 2021
- Faktor-Faktor yang Berhubungan dengan Kualitas Hidup Pasien Penyakit Ginjal Kronis yang Menjalani HemodialisisJurnal Farmasi dan Ilmu Kefarmasian Indonesia, 2021
- Optimization of K Value in KNN Algorithm for Spam and Ham Email ClassificationJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 2020
- Implementasi Data Mining untuk Deteksi Penyakit Ginjal Kronis (PGK) menggunakan K-Nearest Neighbor (KNN) dengan Backward EliminationJurnal Teknologi Informasi dan Ilmu Komputer, 2020