Heart disease risk calculator

The brief

A clinic wants a quick screening aid that flags patients who should be referred to a cardiologist. Build a risk model from routine clinical measurements, make sure it is well-calibrated, and present it as a calculator a doctor could understand. Good looks like: good sensitivity at a sensible threshold, calibrated probabilities, and clear reasons for each estimate.

What you will build

1. Explore the clinical features and missing values
2. Train simple and ensemble models
3. Check calibration and choose a screening threshold
4. Explain each estimate
5. Build a calculator page with a clear medical disclaimer

Free, open data to build it with

• Heart Disease ↗ UCI Machine Learning Repository
• CDC Diabetes Health Indicators ↗ UCI Machine Learning Repository

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.