Chronic Kidney Disease Risk Prediction Model

I built a machine learning system that predicts whether a patient is likely to have chronic kidney disease based on their medical test results. Since this kind of prediction can directly affect patient care, I focused heavily on building the pipeline correctly — handling missing data without introducing bias, and making sure the model was tested in a way that wouldn't give falsely optimistic results. I then compared six different prediction models against each other to find the most reliable one, and the model identified every actual case correctly in testing, which matters most in a medical context where missing a real case is far more costly than a false alarm.

This shows my ability to handle sensitive, high-stakes data carefully — a skill that transfers to any business problem where wrong predictions are expensive (finance, healthcare, fraud detection).