DESIGN AND IMPLEMENTATION OF AN AI-BASED SYSTEM FOR KIDNEY DISEASE PREDICTION
Main Article Content
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
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.
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.