Predicting estimated glomerular filtration rate (eGFR) for chronic kidney disease risk assessment using machine learning techniques: A case study of Khu Mueang Hospital

Abstract

Chronic Kidney Disease (CKD) is a significant health problem affecting populations worldwide. Analyzing and predicting the estimated glomerular filtration rate (eGFR) is essential for planning patient care at various stages, including primary prevention, secondary prevention, and tertiary prevention. In this study, we experimented with various machine learning models, including Linear Regression, Random Forest, Decision Tree, Gradient Boosting Machine (GBM), XGBoost, and LightGBM, to identify the factors influencing eGFR. We selected the most effective model based on performance metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R².The results demonstrated that the most effective model was Random Forest, with an MAE of 0.146688, an MSE of 0.260079, and an R2 of 0.999688, indicating the highest accuracy across all metrics. The R² value, being close to 1, reflects the model's ability to explain the variability in the data effectively. Furthermore, the Random Forest model was refined using Grid Search, resulting in optimal parameters. This model proved to be highly effective in predicting eGFR for patisnts with chronic kidney disease (CKD) with a low MSE and a high R² score, showcasing its capability for accurate outcome predictions. It can be utilized to assess the risk of CKD effectively, aiding in the planning and prevention of chronic kidney disease more efficiently.

References

B. P. Ghosh, T. Imam, N. Anjum, M. T. Mia, C. U. Siddiqua, K. Shaharia, Sharif, M. A. I. Mamun, M. Z. Hossain, Md Atikul, and I. Mamun, "Advancing Chronic Kidney Disease Prediction: Comparative Analysis of Machine Learning Algorithms and a Hybrid Model," Journal of Computer Science and Technology, pp. 989-993, Jul. 2024

C. Mbah, A. Johnson, L. Williams, and D. Smith, "Association between Chronic Kidney Disease and Cardiovascular Risk Factors in Diverse Populations," Journal of Nephrology Research, vol. 15, no. 2, pp. 123-134, 2023

D. Vanathi, S. M. Ramesh, K. Tamizharasu, S. N, and K. P, "A Machine Learning Perspective for Predicting Chronic Kidney Disease," Proceedings, pp. 989-993, Jul. 2024.

D. Xie et al., “Global burden and influencing factors of chronic kidney disease due to type 2 diabetes in adults aged 20-59 years, 1990-2019,” Dental Science Reports, vol. 13, no. 1, pp. 20234-20, Nov. 2023

E. Mahbub, R. K. Sarker, M. Hasan, and F. Ahmed, "Application of Machine Learning in Predicting Chronic Kidney Disease: A Comprehensive Study," Healthcare Informatics Research, vol. 28, no. 4, pp. 315-325, Dec. 2022

M. Tonelli, V. Nkunu, C. Varghese, A. K. Abu-Alfa, M. N. Alrukhaimi, L. Fox, J. Gill, D. C. H. Harris, F. F. Hou, P. J. O’Connell, H. U. Rashid, A. Niang, S. Ossareh, V. Tesar, E. Zakharova, and C.-W. Yang, “Framework for establishing integrated kidney care programs in low- and middle-income countries,” Kidney International Supplements, vol. 10, no. 1, pp. e19–e23, 2020.

M. Rane, M. Derkar, D. Kabra, and T. J. Desai, "Chronic Kidney Disease Prediction Using Machine Learning," International Journal for Research in Applied Science and Engineering Technology (IJRASET), vol. 12, no. 6, pp. 65-70, Jun. 2024

M. Forné, S. L. Pérez-García, J. M. Betriu, and L. Fernandez, "Cardiovascular Risk Assessment in Patients with Chronic Kidney Disease: A Compre hensive Review," Nephrology Dialysis Transplantation, vol. 34, no. 12, pp. 1915-1923, Dec. 2019.

N. A. Kikvadze and G. Gorgadze, “The role of environmental factors in the development of chronic kidney disease (CKD) – Literature Review,” Junior Researchers, vol. 7, no. 1, pp. 1-8, Jun. 2023.

T. Bai, Y. Zhang, L. Wang, and J. Liu, "Machine Learning Models for Predicting the Progression of Chronic Kidney Disease," Journal of Medical Systems, vol. 46, no. 11, pp. 1-10, Nov. 2022.

T. R. Noviandy, G. M. Idroes, M. Syukri, and R. Idroes, "Interpretable Machine Learning for Chronic Kidney Disease Diagnosis: A Gaussian Processes Approach," Indonesian Journal of Case Reports, vol. 2, no. 1, pp. 24-32, Jun. 2024.

U. O. Pontes, T. L. M. Amaral, C. A. Amaral, and G. T. R. Monteiro, "Prevalence and factors associated with chronic kidney disease in diabetic and hyper tensive patients," Environmental Health Perspectives, 2023

กมลทิพย์ วิจิตรสุนทรกุล, “แนวทางการดูแลและจัดการ ผู้ป่วยโรคไตเรื้อรัง,” กรมควบคุมโรค, กระทรวงสาธารณสุข, สืบค้นเมื่อ 30 กันยายน 2566. [ออนไลน์]. เข้าถึงได้จาก: https://ddc.moph.go.th/uploads/pulish/13088202209050 25852.pdf