Klasifikasi Chronic Kidney Disease Menggunakan K-Nearest Neighbor dengan Pelabelan Berbasis Glomerular Filtration Rate

M. Wahyu Ramadhan; Mhd. Ikhsan Rifki

doi:10.56427/jcbd.v5i3.1103

Authors

M. Wahyu Ramadhan Universitas Islam Negeri Sumatera Utara
Mhd. Ikhsan Rifki Universitas Islam Negeri Sumatera Utara

DOI:

https://doi.org/10.56427/jcbd.v5i3.1103

Keywords:

Chronic Kidney Disease, Confusion Matrix, Glomerular Filtration Rate, K-Nearest Neighbor, Klasifikasi

Abstract

Chronic Kidney Disease (CKD) merupakan kondisi penurunan fungsi ginjal yang dapat berlangsung tanpa gejala yang jelas pada tahap awal. Penelitian ini bertujuan mengevaluasi algoritma K-Nearest Neighbor (KNN) dalam mengklasifikasikan CKD berdasarkan label operasional yang dibentuk dari ambang Glomerular Filtration Rate (GFR). Data sekunder berupa 4.000 observasi diperoleh dari dataset Chronic Kidney Disease pada platform Kaggle. Label CKD ditetapkan untuk GFR <60 mL/min/1,73 m² dan NonCKD untuk GFR ≥60 mL/min/1,73 m². Untuk menghindari target leakage, GFR dan kreatinin tidak digunakan sebagai prediktor sehingga model hanya memanfaatkan tekanan darah, blood urea nitrogen (BUN), darah dalam urin, dan riwayat penyakit ginjal keluarga. Tahapan penelitian meliputi transformasi data kategorikal, pembagian data secara stratifikasi dengan proporsi 80:20, standardisasi menggunakan StandardScaler dalam Pipeline, pemilihan nilai K melalui 10-fold cross-validation pada data pelatihan, dan evaluasi pada data pengujian. Nilai K=13 menghasilkan rata-rata akurasi validasi 98,47% dengan standar deviasi 0,57%. Pada data pengujian, model memperoleh accuracy 99,12%, precision 98,72%, recall 99,78%, dan F1-score 99,25%. Hasil tersebut menunjukkan bahwa KNN memiliki performa klasifikasi yang tinggi pada dataset dan definisi target yang digunakan. Namun, performa tersebut merepresentasikan klasifikasi label berbasis ambang GFR dan tidak secara langsung menunjukkan kemampuan diagnosis klinis CKD.

Downloads

Download data is not yet available.

References

[1] P. S. Hidayangsih, D. H. Tjandrarini, N. E. W. Sukoco, N. Sitorus, I. Dharmayanti, and F. Ahmadi, “Chronic kidney disease in Indonesia: Evidence from a national health survey,” Osong Public Health Res. Perspect., vol. 14, no. 1, pp. 23–30, 2023, doi: https://doi.org/10.24171/j.phrp.2022.0290.

[2] Kidney Disease: Improving Global Outcomes (KDIGO) CKD Work Group, “KDIGO 2024 clinical practice guideline for the evaluation and management of chronic kidney disease,” Kidney Int., vol. 105, no. 4S, pp. S117–S314, 2024, doi: https://doi.org/10.1016/j.kint.2023.10.018.

[3] M. Gokiladevi, S. Santhoshkumar, and V. Varadarajan, “Machine learning algorithm selection for chronic kidney disease diagnosis and classification,” Malaysian J. Comput. Sci., Spec. Issue 1, pp. 102–115, 2022, doi: https://doi.org/10.22452/mjcs.sp2022no1.8.

[4] E. M. Senan et al., “Diagnosis of chronic kidney disease using effective classification algorithms and recursive feature elimination techniques,” J. Healthc. Eng., vol. 2021, Art. no. 1004767, 2021, doi: https://doi.org/10.1155/2021/1004767.

[5] F. Sanmarchi, C. Fanconi, D. Golinelli, D. Gori, T. Hernandez-Boussard, and A. Capodici, “Predict, diagnose, and treat chronic kidney disease with machine learning: A systematic literature review,” J. Nephrol., vol. 36, no. 4, pp. 1101–1117, 2023, doi: https://doi.org/10.1007/s40620-023-01573-4.

[6] S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, Art. no. 100804, 2023, doi: https://doi.org/10.1016/j.patter.2023.100804.

[7] A. Moscovich and S. Rosset, “On the cross-validation bias due to unsupervised preprocessing,” J. R. Stat. Soc. Ser. B Stat. Methodol., vol. 84, no. 4, pp. 1474–1502, 2022, doi: https://doi.org/10.1111/rssb.12537.

[8] V. Wulandari, W. J. Sari, Z. Alfian, L. Legito, and T. Arifianto, “Implementasi algoritma Naïve Bayes Classifier dan K-Nearest Neighbor untuk klasifikasi penyakit ginjal kronik,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, pp. 710–718, 2024, doi: https://doi.org/10.57152/malcom.v4i2.1229.

[9] Q. Bai, C. Su, W. Tang, and Y. Li, “Machine learning to predict end stage kidney disease in chronic kidney disease,” Sci. Rep., vol. 12, no. 1, Art. no. 8377, 2022, doi: https://doi.org/10.1038/s41598-022-12316-z.

[10] R. K. Halder et al., “ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application,” J. Pathol. Inform., vol. 15, Art. no. 100371, 2024, doi: https://doi.org/10.1016/j.jpi.2024.100371.

[11] Q. Pan and M. Tong, “Artificial intelligence in predicting chronic kidney disease prognosis: A systematic review and meta-analysis,” Ren. Fail., vol. 46, no. 2, Art. no. 2435483, 2024, doi: https://doi.org/10.1080/0886022X.2024.2435483.

[12] M. A. Islam, M. Z. H. Majumder, and M. A. Hussein, “Chronic kidney disease prediction based on machine learning algorithms,” J. Pathol. Inform., vol. 14, Art. no. 100189, 2023, doi: https://doi.org/10.1016/j.jpi.2023.100189.

[13] V. Sangeetha and S. Swetha, “Predictive modeling of chronic kidney disease using machine learning: A biostatistical perspective,” JP J. Biostat., vol. 26, no. 2, pp. 229–237, 2026, doi: https://doi.org/10.17654/0973514326012.

[14] A. Levin et al., “Executive summary of the KDIGO 2024 clinical practice guideline for the evaluation and management of chronic kidney disease: Known knowns and known unknowns,” Kidney Int., vol. 105, no. 4, pp. 684–701, 2024, doi: https://doi.org/10.1016/j.kint.2023.10.016.

[15] N. Alturki et al., “Improving prediction of chronic kidney disease using KNN imputed SMOTE features and TrioNet model,” Comput. Model. Eng. Sci., vol. 139, no. 3, pp. 3513–3534, 2024, doi: https://doi.org/10.32604/cmes.2023.045868.