NHS - best in the world

[GhostofTarbera]

My Russian friend flys home to Moscow if she needs to see a doctor, as can’t believe how rubbish it is here


Sent from my iPhone using Contractor UK Forum

[GhostofTarbera]

Glad it worked out ok for you.

I've got a similar (less serious) issue. Have done my back in and lost the feeling in my left leg.

Doctor: "We can't refer you for an MRI until you've had the problem for at least 8 weeks. Go home, take some painkillers and do some exercises"

Me: "That's exactly what they told my brother who is now crippled after red flag symptoms were ignored. F**k this, thank God I've got BUPA, now please give me a referral"

Me to, but get referral within an hour from video doctor


Sent from my iPhone using Contractor UK Forum

[Big Blue Plymouth]

Outside of the UK, NHS trained GPs are quite highly valued. But delayed diagnosis is also an issue. My insurance allows me to go directly to specialists without referral.

Any loss of feeling due to back problems needs to be seen rather more expeditiously than 8 weeks, I would have thought. Or have did he spot your arms have fallen off?

He said it would be 8 weeks before they'd consider an MRI scan.

My brother had cauda equina syndrome that was left untreated for weeks until he finally got a GP to refer him to a specialist who immediately ordered an MRI.. He was on the operating table the next day and he's now permanently disabled.

I don't want to end up in the same place.

[sasguru]

This does seem a common complaint the diagnosis is slow or less than competent but once you get to the experts they know what they are doing.

We do however have a chance to get in on the ground floor with AI cancer detection

Google shows how AI might detect lung cancer faster and more reliably - MIT Technology Review

The Cutting-Edge Of AI Cancer Detection

Could artificial intelligence be the future of cancer diagnosis?

AI cancer detectors | Technology | The Guardian


This removes the need for expert staff and could be part of a health screening. Lets hope the Government get on to it.

It doesn't. AI while useful is not a panacea. In particular you wouldnt want to be one of the many false positives or false negatives that most ML models come up with.

[sasguru]

Bottom of seven high-income countries: Australia, Canada, Denmark, Ireland, New Zealand and Norway being the others. Last time I looked there were around 200 countries in the world, so the headline description of it as a "global league table" is disingenuous clickbait at best

Here's the actual study, for those who'd like to have a stab at interpreting the significance of its findings themselves rather than relying on a journalist whose other recent headlines include "Coffee can help you lose weight, study finds" and "Eating breakfast to lose weight ‘could have the opposite effect’".

(And yes, I know the subs write the headlines, but still.)

This is one of several studies that shows that UK survival rates are not as good as those in comparable countries, especially Europe.
This is mainly due to later diagnosis.

[vetran]

It doesn't. AI while useful is not a panacea. In particular you wouldnt want to be one of the many false positives or false negatives that most ML models come up with.

As usual you are wrong, currently its as good at the task soon it will be better than a human, at least for lung cancer. With more scan data and training it will get better.

Artificial intelligence diagnoses lung cancer - BBC News

It was more effective than the radiologists when examining a single CT scan and was equally effective when doctors had multiple scans to go on.
The results, in Nature Medicine, showed the AI could boost cancer detection by 5% while also cutting false-positives (people falsely diagnosed with cancer) by 11%.

so actually a machine is 5% less likely to miss cancer and 11% less likely to give a false positive. I suspect once it becomes mainstream it will be faster & cheaper. In which case you could probably do best of three in one go (multiple scans from different directions) which could then be followed by a human opinion. The more scans we take the better chance anyone has to detect it.

It won't come in hung over etc. So yes if it performs better in the lab its more likely to perform better in real life.

[vetran]

This is one of several studies that shows that UK survival rates are not as good as those in comparable countries, especially Europe.
This is mainly due to later diagnosis.

so cheaper & faster early screening would help?

[sasguru]

As usual you are wrong

I'm building deep learning models for medical diagnosis using various modalities of medical imaging. You?
While effective, we've probably hit the limit of what they can do. You still have to run biopsies and all other tests on flagged and unflagged patients who have symptoms.
Early screening using AI is being used, but the gains so far are marginal, because the bottleneck is in the testing. Screening just provides an indication of who to test and its not foolproof by any means.

[sasguru]

so cheaper & faster early screening would help?

It could help, if the rest of the process caught up with it.
Ai says you *might* have lung cancer.
Unlike other rich countries, NHS maybe can't make an appt within 60 days due to lack of staff to conduct biopsies etc.
This is what's happening at the mo.

How do I know? I'm working for a non-Uk pharma in the oncology therapy area.

[d000hg]

Britain sits at bottom of global league table for cancer survival rates

Britain sits at bottom of global league table for cancer survival rates | The Independent



Sent from my iPhone using Contractor UK Forum

A global league for some countries, was as far as I got before the pay-wall popped up.