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

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.