@DeryaTR_ But how does it handle a GP workflow where many patients don’t have anything actionable, most diseases are common ones and lifestyle and compliance are the main issues? Surely Microsoft can afford to conduct these studies?
Would be great to see this trialed though. The QoH would probably win on sensitivity agains physicians working in clinical practice, but picking out the individual cases it wins on doesn’t show us the full effect. The real question is this: how many patients would have improved outcomes thanks to the QoH finding their OMIs, at what cost in unnecessary cath lab activations, and what outcomes in those patients? Until such a trial is done we don’t know the clinical value of the QoH. Personally I suspect QoH would come out very well in such a trial.
Lessons from one of the first [and the largest] randomized trials of AI in medicine @NatureMedicine
A trial of >100,000 women undergoing mammography with or without AI support for interpretation, by Kristina Lång @lunduniversity
Most importantly, can it [AI] improve patient outcomes?
https://t.co/B1j8bvphcB
For me SHAM-PVI-AF means, that a cardioversion makes sense in patients on the waiting list for PVI, as it controls symptoms for up to 6 months.
Didn’t we know this before?!
👉🏻Not “PVI vs sham,” but “PVI vs an effective rhythm-control strategy such as ECV” study on the short term effects on symptoms/QoL
@PrashSanders@drjohnm@EJSMD
Agree. Binary freedom from 30 seconds of recurrent AF is a terrible endpoint. Particularly when patients have more advanced disease.
Imagine if the coronary stent trials had a Kaplan Meier curve for first episode of chest discomfort post stent.
Or if the hypertension trials evaluated time to first systolic BP > 140 mmHg
Hi everyone
If you got a message from me asking you to vote for me to host a podcast it’s a phishing scam from when my account was hacked. Delete it and set account security. Sorry!
This is the question of the future for monitoring to detect AF:
How certain am I that the patient doesn’t have an actionable AF burden?
Not: does the patient have AF?
@SharpeShark Not anymore! I finally got my account back when the hackers started the Maye Musk posting, after a week of productivity boosts from no scrolling on X.
I've had my account hacked for the past week, resulting in a boost in productivity from reduced scrolling, and also a brief stint as a Maye Musk impersonator. And maybe some phishing attempts or nuisance messages to some of the people I know? Sorry!
I still think the whole workflow with an individualized model that suggests things to a physician should be tested! Maybe it’s better but maybe not. And certified for sure. Maybe in that case one need only certify the concept or the bare bones of it if the person vidence is robust enough, but for sure it needs to be certified as a decision aid.