Medical AI can detect the racial identity of patients from x-rays. This is extremely concerning, and raises urgent questions about how we test medical AI systems.
AI has the worst superpower… medical racism.
2020 and 2021 on the blog, for some reason with more emojis than strictly necessary
For those who don't know, I was on parental leave for almost all of 2020. Not only did this mean almost no research time, but it meant no blogging time as well. Of course, there were plenty of benefits! 😍👶😍👶😍👶😍👶😍👶😍👶😍👶😍👶😍 I still got 5 blog posts done this year, which I'm pretty amazed about given … Continue reading 2020 and 2021 on the blog, for some reason with more emojis than strictly necessary
Docs are ROCs: a simple fix for a “methodologically indefensible” practice in medical AI studies.
The way we currently report human performance systematically underestimates it, making AI look better than it is.
It’s complicated. A deep dive into the Viz/Medicare AI reimbursement model.
CMS will reimburse an AI stroke detection model through Medicare/Medicaid. It is so darn complicated that it deserves a much deeper look.
The medical AI floodgates open, at a cost of $1000 per patient.
AI is finally getting paid, apparently at a rate of $1000 per patient. What?
CT scanning is just awful for diagnosing Covid-19
Reports that CT scanning may be better than PCR testing for covid-19 are flawed and almost certainly wrong.
Who wants to be a clinical AI informaticist?
We need AI-trained radiologists in every practice. Become one by applying for the first Clinical AI Fellowship in Australia!
The FDA has approved AI-based PET/MRI “denoising”. How safe is this technology?
Super-resolution promises to be one of the most impactful medical imaging AI technologies, but only if it is safe.
This week we saw the FDA approve the first MRI super-resolution product, from the same company that received approval for a similar PET product last year. This news seems as good a reason as any to talk about the safety concerns myself and many other people have with these systems.
Improving Medical AI Safety by Addressing Hidden Stratification
Medical AI testing is unsafe, but addressing hidden stratification may be a way to prevent harm, without upending the current regulatory environment.
AI competitions don’t produce useful models
Ai competitions are fun, community building, talent scouting, brand promoting, and attention grabbing. But competitions are not intended to develop useful models.
