Implementasi model support vector machine sebagai sistem prediksi penyakit ginjal kronik berbasis data klinis

Rama Dian Syah; Diandra Hasna Widianto; Bhakti Gunawan; Hadyanto Caputra; Widya Silfianti; Rena Fuji Erin Setyawati

doi:10.35760/tr.2026.v31i1.218

Penulis

Rama Dian Syah Universitas Gunadarma Penulis
Diandra Hasna Widianto Universitas Gunadarma Penulis
Bhakti Gunawan Universitas Gunadarma Penulis
Hadyanto Caputra Universitas Gunadarma Penulis
Widya Silfianti Universitas Gunadarma Penulis
Rena Fuji Erin Setyawati Universitas Gunadarma Penulis

DOI:

https://doi.org/10.35760/tr.2026.v31i1.218

Kata Kunci:

Chronic Kidney Disease, GridSearchCV, machine learning, Support Vector Machine, web-based prediction system

Abstrak

Chronic Kidney Disease (CKD) is one of the global health problems with increasing prevalence and mortality rates, requiring accurate early detection methods to support timely treatment and prevention. Various previous studies have applied machine learning techniques for CKD prediction; however, most studies are still limited to basic model implementation without systematic parameter optimization or real-time web-based prediction system deployment. This study aims to develop a CKD prediction model using the Support Vector Machine (SVM) algorithm optimized through GridSearchCV to improve classification performance. The research was conducted based on the CRISP-DM framework using the CKD dataset from the UCI Machine Learning Repository. The preprocessing stage included categorical data transformation, missing value handling using median imputation, and feature standardization using StandardScaler. Parameter optimization was performed by testing several SVM parameter combinations using a 5-fold cross-validation approach. The results showed that the optimized SVM model achieved an accuracy of 98.75%, with high precision, recall, and F1-score values in CKD and non-CKD classification. These results indicate better performance compared to several previous studies using similar datasets with accuracy below 98%. Furthermore, the model was implemented in a web-based application using Gradio and Hugging Face Spaces to support real-time prediction. Initial validation by an internal medicine specialist indicated that the system predictions were consistent with medical interpretation, suggesting that the proposed model has potential as a decision-support tool for early CKD detection

Unduhan

Data unduhan tidak tersedia.

Referensi

[1] C. P. Kovesdy, “Epidemiology of chronic kidney disease: An update 2022,” Kidney Int. Suppl., vol. 12, no. 1, pp. 7–11, Apr. 2022, doi: 10.1016/j.kisu.2021.11.003.

[2] L. Deng et al., “Global, regional, and national burden of chronic kidney disease and its underlying etiologies from 1990 to 2021: A systematic analysis for the Global Burden of Disease Study 2021,” BMC Public Health, vol. 25, no. 1, Art. no. 636, Feb. 2025, doi: 10.1186/s12889-025-21851-z.

[3] N. M. Hustrini, E. Susalit, and J. I. Rotmans, “Prevalence and risk factors for chronic kidney disease in Indonesia: An analysis of the National Basic Health Survey 2018,” J. Glob. Health, vol. 12, Art. no. 04074, Oct. 2022, doi: 10.7189/jogh.12.04074.

[4] G. Kaur and V. Patney, “Progression of CKD and uremic symptoms,” in Approaches to Chronic Kidney Disease, J. McCauley, S. M. Hamrahian, and O. H. Maarouf, Eds. Cham: Springer Int. Publ., 2022, pp. 69–85, doi: 10.1007/978-3-030-83082-3_5.

[5] S. Wang et al., “Chronic kidney disease: Bridging conventional therapeutics and emerging molecular innovations,” Prog. Microbes Mol. Biol., vol. 8, no. 1, Aug. 2025, doi: 10.36877/pmmb.a0000468.

[6] R. M. Gama, K. Griffiths, R. P. Vincent, A. M. Peters, and K. Bramham, “Performance and pitfalls of the tools for measuring glomerular filtration rate to guide chronic kidney disease diagnosis and assessment,” J. Clin. Pathol., vol. 76, no. 7, pp. 442–449, Jul. 2023, doi: 10.1136/jcp-2023-208887.

[7] R. Hasan, I. Ahmed, M. Hasan, A. A. Abir, S. Md. R. Islam, and S. M. A. Ullah, “Prediction of chronic kidney disease – a machine learning-based approach,” in Proc. Int. Conf. Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), Raipur, India, Dec. 2023, pp. 1–7, doi: 10.1109/ICAIIHI57871.2023.10489799.

[8] T. Thangarasan, B. Jai Kumar, S. Jeelan, S. R. Reddy, and B. Manohar, “AI supported chronic kidney disease prediction using machine learning classification techniques,” in Proc. 2nd Int. Conf. New Frontiers in Communication, Automation, Management and Security (ICCAMS), Bangalore, India, Jul. 2025, pp. 1–6. doi: 10.1109/ICCAMS65118.2025.11234089.

[9] Md. S. Al Huda, E. Kanon, Md. S. K. Pappo, Md. A. Ali, and N. Ahmed, “NefroAI: An explainable and real-time framework for predicting chronic kidney disease using diverse machine learning models and different feature selection techniques,” IEEE Access, vol. 14, pp. 10939–10976, 2026, doi: 10.1109/ACCESS.2025.3649006.

[10] N. Bhaskar and M. Suchetha, “A computationally efficient correlational neural network for automated prediction of chronic kidney disease,” IRBM, vol. 42, no. 4, pp. 268–276, Aug. 2021, doi: 10.1016/j.irbm.2020.07.002.

[11] J. Wang, “A fusion kernel in SVM and improved evolutionary algorithm in feature selection for Parkinson’s disease detection,” in Proc. 3rd Int. Conf. Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023), D. A. Karras and S. X. Yang, Eds., SPIE, Jul. 2023, Art. no. 127172G, doi: 10.1117/12.2684724.

[12] X. Zhipeng, M. A. A. Aziz, and N. A. Razak, “Performance evaluation of support vector machine algorithm in object classification using different preprocessing methods,” in Proc. 2024 IEEE Int. Conf Automatic Control and Intelligent Systems (I2CACIS), Shah Alam, Malaysia, Jun. 2024, pp. 169–174, doi: 10.1109/I2CACIS61270.2024.10649625.

[13] L. Rubini, P. Soundarapandian, and P. Eswaran, “Chronic kidney disease,” UCI Machine Learning Repository, 2015, doi: 10.24432/C5G020.

[14] M. J. Nodeh, M. H. Calp, and İ. Şahin, “Analyzing and processing of supplier database based on the cross-industry standard process for data mining (CRISP-DM) algorithm,” in Artificial Intelligence and Applied Mathematics in Engineering Problems, D. Hemanth and U. Kose, Eds., Lecture Notes on Data Engineering and Communications Technologies, vol. 43. Cham, Switzerland: Springer, 2020, pp. 544 – 558, doi: 10.1007/978-3-030-36178-5_44.

[15] A. Purbasari, F. R. Rinawan, A. Zulianto, A. I. Susanti, and H. Komara, “CRISP-DM for data quality improvement to support machine learning of stunting prediction in infants and toddlers,” in Proc. 2021 8th Int. Conf. Adv. Informatics: Concepts, Theory Appl. (ICAICTA), Bandung, Indonesia, Sep. 2021, pp. 1–6, doi: 10.1109/ICAICTA53211.2021.9640294.

[16] B. Liu, Y. Lu, Y. Geng, Y. Pang, and Z. Zhu, “Current status and progress in research on postoperative acute kidney injury,” Chin. J. Clin. Res., vol. 37, no. 9, pp. 1438–1442, Sept. 2024, doi: 10.13429/j.cnki.cjcr.2024.09.025.

[17] A. M. Sharifnia, D. E. Kpormegbey, D. K. Thapa, and M. Cleary, “A primer of data cleaning in quantitative research: handling missing values and outliers,” J. Adv. Nurs., vol. 82, no. 1, pp. 970–975, Jan. 2026, doi: 10.1111/jan.16908.

[18] J. Sukhbaatar, B. Zagd, and N. Jambaljav, “Detection of point outliers in meteorological data (case study: Ulaanbaatar, Mongolia),” in Advances in Intelligent Information Hiding and Multimedia Signal Processing, J.-S. Pan, J. Li, K. H. Ryu, Z. Meng, and A. Klasnja-Milicevic, Eds., Smart Innovation, Systems and Technologies, vol. 212. Singapore: Springer, 2021, pp. 68–75, doi: 10.1007/978-981-33-6757-9_9.

[19] K. Kim and B. Jang, “The effect of data split on correlation errors with respect to independent validation data,” in Proc. 20th Int. Topical Meeting Nucl. Reactor Thermal Hydraulics (NURETH-20), Washington, D.C., USA, Aug. 2023, pp. 2764–2771, doi: 10.13182/NURETH20-41342.

[20] H. Nasir, A. Pandita, C. N. B. Nasir, and N. K. Ojha, “Significance of fairly distributed instances and optimal ratio for validation set in machine learning,” in International Conference on Innovation, Sustainability, and Applied Sciences (ICISAS 2023), C. Pon Selvan, N. Sehgal, S. Ruhela, and N. U. Rizvi, Eds., Signals and Communication Technology. Cham, Switzerland: Springer, 2025, pp. 641–647, doi: 10.1007/978-3-031-68952-9_83.

[21] A. Shmilovici, “Support vector machines,” in Machine Learning for Data Science Handbook, L. Rokach, O. Maimon, and E. Shmueli, Eds. Cham: Springer Int. Publ., 2023, pp. 93–110, doi: 10.1007/978-3-031-24628-9_6.

[22] M. A. Widyananda and I. Palupi, “Implementation of the spiral optimization algorithm in the support vector machine (SVM) classification method (case study: diabetes prediction),” in Proc. 2021 Int. Conf. Adv. Data Sci., E-learn. Inf. Sys. (ICADEIS), Bali, Indonesia, Oct. 2021, pp. 1–6, doi: 10.1109/ICADEIS52521.2021.9701953.

[23] P. Ansah et al., “Precision medicine in diabetes: A machine learning model for diabetic foot ulcer prediction using Keras TensorFlow,” in Proc. 2024 1st Int. Conf. Cogn., Green and Ubiquitous Comput. (IC-CGU), Bhubaneswar, India, Mar. 2024, pp. 1–6, doi: 10.1109/IC-CGU58078.2024.10530735.

[24] C. S. Hong and T. G. Oh, “TPR-TNR plot for confusion matrix,” Commun. Stat. Appl. Methods, vol. 28, no. 2, pp. 161–169, Mar. 2021, doi: 10.29220/CSAM.2021.28.2.161.

[25] K. N. Qodri, M. R. Fikri, and L. Ardi, “Analytical prediction for chronic kidney disease: A comparison of machine learning methods,” JKTi: Jurnal Keilmuan Teknologi Informasi, vol. 1, no. 1, pp. 15–22, Jul. 2025, doi: 10.61902/jkti.v1i1.1686.

[26] C. Paramita and W. Prasetyaningtyas, “Enhanced chronic kidney disease prediction using optimized support vector machine with hyperparameter tuning and SMOTE,” Rabit: Jurnal Teknologi dan Sistem Informasi Univrab, vol. 11, no. 1, pp. 964–978, Jan. 2026, doi: 10.36341/rabit.v11i1.7179.