About
About this site
This portal hosts a free, illustrated, hands-on R course for people who want to learn to work with electronic health record (EHR) data.
Who made it
A revision of Jaewon Kim’s R Guide by the IHC/EHR Training Team. The lessons are a revision of the original guide, reorganised into six parts: R foundations, the supervised workflow, more supervised methods, unsupervised learning, other kinds of learning, and choosing and comparing methods, with capstone projects. The lesson source files are the single source of truth; this site is built from them.
Synthetic data, educational use
For education only. All data in this course is synthetic (fabricated). Nothing here is clinical advice, and nothing here shows that any model is medically valid.
The course dataset has 600 fabricated examples. The labels are deliberately fully known, unlike many real EHR exports. Readers should never enter or upload health information on this site, and real patient data must not be added to the course files. A model that ranks invented labels well has not shown disease detection, calibration, equity or clinical usefulness.
Rights
The course is a revision of another author’s work. No images from the original tutorial are used on this site. Public release depends on the rights to the derived text.