Wouter van Amsterdam Profile picture
machine learning, causal inference, health care
May 23 18 tweets 3 min read
Great to see the TRIPOD+AI reporting guideline published!

It does medical research a great service, but prognosis models intended to support treatment decisions need more, so we wrote a rapid response in the BMJ: bmj.com/content/385/bm…
Image TRIPOD+AI ensures that researchers report sufficient information for readers to verify whether a published prediction model is fit for purpose, doing the field a tremendous service by improving standards and reducing research waste
Jul 21, 2021 14 tweets 5 min read
Better outcome predictions lead to better treatment decisions, right?

Turns out it’s not that simple. In fact, accurate outcome predictions can in some cases lead to WORSE clinical decisions.

Blog with numerical example here: vanamsterdam.github.io/posts/goodpred…
Thread here 👇:
(1/) For a certain type of cancer there are two treatments: A and B. From randomized trials it is known that A leads to better overall survival. There is no known variation in treatment effect among patient subgroups.
(2/)