Clinical Machine Learning
You will build a clinical prediction model that survives its own audit — and you will be able to take apart anyone else's, published or purchased, in writing.
17 lessons · 11.5 hours
Who it's for. Clinicians, researchers, and informatics engineers who will do the modelling themselves: the registrar with a research question and a dataset, the epidemiologist moving from regression to machine learning, the engineer who has to make a risk score work in a real hospital, the quality lead who has been asked to evaluate a purchased model and refuses to take the vendor's word for it.
The capstone. A clinical risk model built, validated, calibrated, subgroup-audited and reported to TRIPOD+AI standard — plus a scored appraisal of a vendor claim in the same clinical area.
Lessons open with membership. Join the network to work through this course at your own pace, keep your progress, and earn a certificate of completion when you finish.
Join the network