Back to Projects

KidneyCare Clinical Assistant

Clinical decision support system for nephrologists to manage lab reports, follow-ups, and treatment recommendations.

KidneyCare Clinical Assistant - Image 1
1 / 11

Project Overview

KidneyCare Clinical Assistant is a real-world clinical decision support system developed under academic and medical supervision. It helps nephrologists manage patient records, enter and validate lab results, track historical trends, and generate treatment and medication recommendations based on hospital-defined clinical logic. The system is designed to handle real clinical constraints such as missing, outdated, or conflicting lab data, and ensures all recommendations are structured, reviewable, and safe for physician decision-making.

Problem It Solves

Nephrologists must interpret multiple lab values across time while managing follow-up visits and treatment decisions. Manual analysis of reports, especially when lab data is missing or outdated, increases cognitive load and risk of oversight. There was a need for a system that centralizes patient history, validates lab relevance, and supports consistent, guideline-based decision-making.

Tools & Technologies Used

Next.jsNode.jsSupabase (PostgreSQL)Role-based Access ControlRule-based Clinical Logic Engine

Skills Involved

Backend System DesignHealthcare Software EngineeringRule-based Decision SystemsDatabase Modeling for Clinical DataCollaboration with Medical Professionals

Challenges

Designing medical logic that is safe, explainable, and aligned with real hospital workflows was the biggest challenge. The system had to correctly handle edge cases such as missing tests, expired lab validity, and partial reports, while still providing useful recommendations. Translating clinical reasoning into deterministic software logic required close iteration with nephrology instructors and careful validation.

Learnings

This project provided hands-on experience in building safety-critical software. I learned how clinical decision support differs from typical applications, the importance of explainability in medical systems, and how to convert domain expertise into structured logic. It also strengthened my ability to collaborate with non-technical domain experts and design systems meant for real clinical use rather than demos.