'Doctor, I'm worried about this patient's observations.' We find them bolt upright, gripping the rails, wheezing with each gasp. RR & BP up, sats down. Classic APO - we got here just in time. Yet an AI for detecting deterioration might have missed this. Our paper explains why...
@robertskmiles Define "health"
Sometimes good medicine is the conversation that ends with, "I think the best thing is to do is to do nothing."
I suspect LLMs are fine tuned away from from those, for a variety of reasons.
@DrLKVaughan Google have had their LLM sit and adapted MRCGP and more recently take histories from real patients. https://t.co/A4WSpffgOV
I agree, the current benchmarks aren't great. It's not feasible to do studies of this scale on all new LLMs. What do you think benchmarks should test?
Just one more example of how the UK is a formerly dynamic and growing economy behaving as if it is still a dynamic and growing economy, and then being surprised when things that used to work (and work for other countries that haven’t stagnated) no longer work here.
"Why are early career doctors angry?" asks @DAaronovitch on BBC Briefing Room.
Two consultants who qualified in 1979 and 1990 are on to explain.
Part of it? Feeling that consultants don't understand their struggles. Funnily enough, that didn't come up.
@DAaronovitch I'm a loyal listener, but this was disappointing. Goddard even admits on air he knows the consultant situation better. Here are 16 reasons we're angry, by the excellent @DevanSinha https://t.co/uTDzbWvJXA
Doctors pay dispute is only one, though totemic & overwhelming, of many serious issues affecting working conditions & unattractiveness of the NHS to doctors.
Once started listing issues to express problems doctors face:
XVI Theses on UK Postgraduate Doctors’ Discontent😬
Here's a chart of the marginal tax rate for someone with two kids. They pay 53% tax on every £ they earn between £60k and £80k. 62% on every £ they earn between £100k and £125k.
9% more if they've a student loan
(See all the detail in our calculator, pinned to my profile)
@somerset_mat@pash22@debzly@DrNickDalmon RE: mean scores. They aren't equivalent - they are statistically significantly different. Everyone agrees on this, including the original authors.
Please could you show me where you got the sense I was "admitting" to anything, so I could correct it?
@somerset_mat@pash22@debzly@DrNickDalmon Hi Mat
The paper hasn't been published because I have other things to do (like write my thesis), I submitted it to the BMJ but they made an editorial decision not to publish it but it was peer reviewed
I didn't get any funding to do this
1/2
In the UK's national frailty screening tool, harmful alcohol use is weighted 25x more heavily than dressing problems
This improves prediction. But does it capture frailty?
New commentary with @Krockdoc in @age_and_ageing
1/8
Thank you:
To the reviewers who genuinely improved this work
To @age_and_ageing & the editorial team who are incredibly helpful
And of course to @Krockdoc! It is an immense privilege to work with someone who literally wrote the book on frailty indices 8/8