DESIGN AND IMPLEMENTATION OF AN AI-BASED SYSTEM FOR KIDNEY DISEASE PREDICTION

Main Article Content

Oyinkansola E. Sojirin
Boluwatife C. Mustapha
Alfred A. Udosen
Christiana J. Daramola

Abstract

Chronic Kidney Disease (CKD) is a considerable public health problem in Nigeria, and most hospital record systems have limited predictive ability for timely clinical intervention. In Nigeria, chronic kidney disease (CKD) is a major public health problem, and hospital record systems have limited predictive power for timely clinical intervention. The objective of this study is to design and implement NephroTrack, an AI-based web system to predict CKD. A three-tiered architecture was implemented: a React.js and Tailwind CSS front end that interfaces with a REST API back end running on Node.js and Express.js, and a standalone Python FastAPI machine learning service deployed together with the managed PostgreSQL database on Render. The system can support 3 user roles and include a 51-featured CKD risk prediction form with colour-coded risk classifications and PDF report export, patient registration, clinical visit recording, and laboratory result tracking. After hyperparameter tuning using 216 combinations with 5-fold cross-validation, the Random Forest algorithm yielded the highest performance metrics: accuracy, 91.87%; recall, 99.34%; F1-Score, 95.73%; and AUC-ROC, 74.97%, revealing the effectiveness of using AI for early detection of CKD in resource-limited healthcare contexts in Nigeria.

Article Details

Section

Articles

References

[1] World Health Organization, "Reducing the burden of noncommunicable diseases through promotion of kidney health," WHO, Geneva, 2025.

[2] T. K. M. Jawad, A. Verma, F. Amsaad, and L. Ashraf, "AI-driven predictive analytics approach for early prognosis of chronic kidney disease using ensemble learning and explainable AI," arXiv, 2024. doi:10.48550/arXiv.2406.06728

[3] J. Ma, J. Wang, L. Lu, Y. Sun, M. Feng, F. Zhang, P. Shen, Z. Jiang, S. Hong, and L. Zhang, "Development and validation of a dynamic kidney failure prediction model based on deep learning: A real-world study with external validation," arXiv, 2025. doi:10.48550/arXiv.2501.16388

[4] N. Nguycharoen, "Explainable machine learning system for predicting chronic kidney disease in high-risk cardiovascular patients," arXiv, April 2024. arXiv:2404.11148

[5] A. E. Babatope, I. P. Adewunmi, D. O. Ajisafe, K. O. Adepoju, and A. R. Babatope, "Accessing the factors militating against the effective implementation of electronic health records (EHR) in Nigeria," Scientific Reports, Dec. 2024. doi:10.1038/s41598-024-83009-y

[6] A. Rajkomar, J. Dean, and I. Kohane, "Machine learning in medicine," New England Journal of Medicine, vol. 380, no. 14, Apr. 2019. doi:10.1056/NEJMra1814259

[7] L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

[8] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794, 2016.

[9] C. Cortes and V. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.

[10] S. Paulo, "Artificial intelligence in global health: An unfair future for health in sub-Saharan Africa," Health and Social Care in the Community, Feb. 2025. doi:10.1093/haschl/qxaf023

[11] K. Takkavatakarn, W. Oh, E. Cheng, G. N. Nadkarni, and L. Chan, "Machine learning models to predict end-stage kidney disease in chronic kidney disease stage 4," BMC Nephrology, Dec. 2023. doi:10.1186/s12882-023-03424-7

[12] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Upper Saddle River, NJ: Prentice Hall, 2020.

[13] A. Esteva, K. Chou, S. Yeung, N. Naik, A. Madani, A. Mottaghi, Y. Liu, E. Topol, J. Dean, and R. Socher, "Deep learning-enabled medical computer vision," npj Digital Medicine, Jan. 2021. doi:10.1038/s41746-020-00376-2

[14] Q. An, S. Rahman, J. Zhou, and J. J. Kang, "A comprehensive review of machine learning in the healthcare industry: Classification, restrictions, opportunities and challenges," Sensors, Apr. 2023. doi:10.3390/s23094178

[15] S. A. Omokanye, A. I. Wegbom, R. Adio, and C. O. Adebayo, "SWOT analysis of health information management practice in Nigeria," unpublished, Feb. 2025.