# Credits & Origin

NephroScreen is a **solo project**. The design, data analysis, machine-learning
pipeline, API, web interface, deployment, and write-up are entirely my own work.

An earlier version of the core analysis was submitted for a university Machine
Learning course. This repository is a **complete independent rebuild and
extension** of that idea, adding:

- An installable package with a leakage-safe, train-only preprocessing pipeline.
- A **FastAPI** service and a **professional web frontend** for live screening.
- **Serving-oriented ML work**: model persistence, a recall-tuned decision
  threshold, rule-based clinical indicators, calibration and SHAP analysis, and
  an automated test suite.
- Containerisation and free-tier cloud deployment.

**Author:** Sadiq Mansoor
**Dataset:** UCI Machine Learning Repository — Chronic Kidney Disease (ID 336).