🌱 Foundations

Everything in this course rests on a single observation — accuracy tells you how often a model is right, but never when it is about to be wrong. In a clinic, those are completely different questions. A model with 95% accuracy that fails silently on the 5% is far more dangerous than one that flags its own uncertain cases for review.

Part 1 builds that intuition before introducing a single equation. You will see the two ways clinical AI fails, learn to separate uncertainty that more data can fix from uncertainty that it cannot, and see how radiologists have always communicated confidence as part of their diagnostic output — the exact standard we want our models to meet.