AI models that predict disease are not as accurate as reports might suggest • Hacker News Board

Re: AI models that predict disease are not as accurate as reports might suggest

#101

Post by naijaboiler » Sat, Oct 22, 2022, 1:50 AM UTC

fasthands9 wrote: post #60

It is still unclear to me exactly what data they were looking at/referring to in this article. If you take into account bloodwork, family history, demographics, etc. then it seems like you are still only getting a few dozen data points. At this scale it seems like traditional statistics or human checks for abnormalities are going to be about as good. Although I personally know very little (apologies for conjecturing)…

Look simple rule based algos can be just as effective. The hard part is not diagnosis. It's getting the human to comply with treatment

Re: AI models that predict disease are not as accurate as reports might suggest

#102

Post by bsder » Sat, Oct 22, 2022, 1:50 AM UTC

srvmshr wrote: post #34

I worked in healthcare ML solutions, as part of my PhD & also as consultant to a telemedicine company. My experience in dealing with data (we had sufficient, and somewhat well labeled) & methods made me realize that a lot of the prediction human doctors make are multimodal - and that is something deep learning will struggle for the time being. For example, say in detection of a disease X , physicians factor in blood…

> We humans are incredibly good at elimination of factors & differential diagnosis.

I don't automatically buy this.

Didn't heart attack care in the ER get dramatically better when people started following checklists? That suggests that human doctors aren't that great at even getting the basics correct.

In addition, most doctors are below average. So, maybe the best doctors are better than the AI. However, I may not have access to that doctor and the AI may be better than all the doctors I have access to.

Re: AI models that predict disease are not as accurate as reports might suggest

#103

Post by potatoman22 » Sat, Oct 22, 2022, 1:54 AM UTC

dirheist wrote: post #41

planetsprite wrote: post #19

The solution to failures of AI in heathcare is transparency of data. OpenAI's models work because they have virtually unlimited data to train on. The scale of training data for doctor bots is one millionth the size. Different countries, organizations, universities need to be as open as possible sharing and collaborating, realizing improvements in medicine benefits all of humanity with almost no downsides.

There should be a standardization committee tasked with standardizing the collection of anonymized, semi-synthetic medical data from hospitals/hospital networks. It seems like so much research is just locked up in the IMS systems the hospitals use for their patients and that never see the light of day.

I read about this researcher using GANs to create synthetic patient data, cool stuff. She had a problem she couldn't solve though: how do you validate that your synthetic patients look real?

Re: AI models that predict disease are not as accurate as reports might suggest

#104

Post by medler » Sat, Oct 22, 2022, 1:55 AM UTC

srvmshr wrote: post #52

majormajor wrote: post #50

Earlier quoted context omitted.

My view on this is framed a bit differently but probably a similar ultimate perspective: I think it's probably going to be a long time before models only using quantifiable measurements can even meet the performance of top doctors. I can't recommend enough that someone experiencing issues doctor-shop if they haven't gotten a well-explained diagnosis from their current doctor. But I'm very curious how good one has to…

> But I'm very curious how good one has to be in order to be better than a below-average doctor, or a 50th-percentile doctor, or a 75th. In dermatology, on which I was working, models were better (at detecting skin cancers) than 52% of the GPs, going by just images. In a famous Nature paper by Esteva et al., the TPR was at 74% for detecting Melanomas. There is a catch which probably got underreported (The skin cancer…

Interesting, could you explain more about the clinical markings? Was this mentioned in the paper itself or was it later commentary?

Re: AI models that predict disease are not as accurate as reports might suggest

#105

Post by potatoman22 » Sat, Oct 22, 2022, 1:59 AM UTC

rscho wrote: post #47

Surprise, surprise. People hugely overestimate the data retrieval capabilities of healthcare systems. And if you really put clinical 'AI' systems to the test in day-to-day settings (which is in fact never done), results would be much, much worse. Shit data in, shit prediction out.

Look up prospective validation or clinical impact trials. These are validated in day-to-day settings somewhat often, though not as often as they should be.

Re: AI models that predict disease are not as accurate as reports might suggest

#106

Post by dontreact » Sat, Oct 22, 2022, 2:20 AM UTC

Sweeping generalizations about AI models as a class of objects seem deeply uninformative to me. Perhaps I would even go so far as to say misleading. These days any undergrad can go on GitHub and have a model that does some diagnosis and I don’t understand why we have to group that together with multi-year efforts from groups of PhD’s and MDs working together to produce products.

There’s obviously way more of the first than the second and so if you analyze this group as a whole it’s easy to draw the wrong conclusion about what AI as a technique is capable of.

I can’t give too many details on specific examples I’m working on at Google but an example I’m not working on would be Caption Health who have an amazing AI-based ultrasound guidance product that has great prospective evidence, and several big fans in the clinical community.

There are also several success stories using AI on pathology in order to target clinical trials.

Can you imagine if someone made sweeping statements about webpages as if they were a coherent group of objects that you could sample from and deduce properties? “The information on websites is typically not as accurate as those websites claim”

Re: AI models that predict disease are not as accurate as reports might suggest

#107

Post by hfbff » Sat, Oct 22, 2022, 2:25 AM UTC

srvmshr wrote: post #34

I worked in healthcare ML solutions, as part of my PhD & also as consultant to a telemedicine company. My experience in dealing with data (we had sufficient, and somewhat well labeled) & methods made me realize that a lot of the prediction human doctors make are multimodal - and that is something deep learning will struggle for the time being. For example, say in detection of a disease X , physicians factor in blood…

Thanks for sharing. My belief is that we need to figure out a way to make humans interact with prediction models in a virtuous way. Prediction models suck at "connecting the dots" or considering multiple sources of information (for example: multiple models predicting different outcomes). Until we get true general artificial intelligence, I think the way to go forward is to try to quantify those unknowns through confidence intervals (conformal prediction seems to be quite nice for many models) plus some multiple hypothesis testing to handle the multiple outcomes / multiple models.

This needs to be then implemented on a real flow where humans and prediction models interact (for example: approve these things automatically, send these other test for humans to revise)

Re: AI models that predict disease are not as accurate as reports might suggest

#108

Post by lostlogin » Sat, Oct 22, 2022, 2:26 AM UTC

p1necone wrote: post #92

lostlogin wrote: post #32

Earlier quoted context omitted.

I work in radiology with MRI as a tech. We use AI slightly differently to the examples here, but it’s changing a lot of what we do. It’s more about enhancing images than directly about diagnosing. The image is denoised ‘intelligently’ in k-space and then the resolution is doubled via another AI process in the image domain (or maybe the resolution is quadrupled, as it depends on how you measure it. Our pixel count dou…

AI denoising may be making information that actually is in the image easier to spot, but AI upscaling is just inventing detail that doesn't actually exist in the source image, which seems rather dangerous for this use case.

I disagree.

It’s ‘only’ converting each pixel into 4, so the starting point is not going to change a lot. Also keep in mind that interpolating has been part of image reconstructions for 20+ years. MR suffers from slow acquisition times so we cheat and image resolution is rarely symmetrical in pixel dimensions when you compare x, y and z directions.

Previously we just made pixels square (made up data) then doubled the pixel count (more made up data). It was that dumb.

I’ve tried acquiring an image and up scaling it 2x. Then acquiring the same image at double the resolution and not upscaling.

It’s hard to compare as the longer acquisition is often hampered by patient movement.

When I set up a scan with the AI I’d estimate it as adding about about 30% signal. I make up a scan that will look good. Then turn the AI on, then shorten the scan or increase the resolution such that it’s 30% ish down on signal, then I press go.

We are seeing things we didn’t previously, particularly with cartilage injuries.

Re: AI models that predict disease are not as accurate as reports might suggest

#109

Post by steveBK123 » Sat, Oct 22, 2022, 2:56 AM UTC

medler wrote: post #104

srvmshr wrote: post #52

Earlier quoted context omitted.

> But I'm very curious how good one has to be in order to be better than a below-average doctor, or a 50th-percentile doctor, or a 75th. In dermatology, on which I was working, models were better (at detecting skin cancers) than 52% of the GPs, going by just images. In a famous Nature paper by Esteva et al., the TPR was at 74% for detecting Melanomas. There is a catch which probably got underreported (The skin cancer…

Interesting, could you explain more about the clinical markings? Was this mentioned in the paper itself or was it later commentary?

I remember a similar New Yorker article ~5 years ago about medical imaging ML/AI where they realized it's good hit rate was actually a data artifact from training. Something along the lines that essentially all the positives had secondary scans and so there was a set of known positives which had say run through the same machine/lab and had similar label color & text markings in the margin of the imaging.

When they went back and tested with clean images that didn't basically have the "im a positive cuz I have this label over here in the margins", the hit rate dropped below that of humans.

It was an article with anecdotes about some of the hospice cats that seemingly are able to detect when a patient is about to die. Entirely possible as they have a sense of smell and patient tumors likely giving out detectable odors.

Nonetheless, the ML model & the cat were similarly inscrutable.

Re: AI models that predict disease are not as accurate as reports might suggest

#110

Post by steveBK123 » Sat, Oct 22, 2022, 3:02 AM UTC

hfbff wrote: post #107

srvmshr wrote: post #34

I worked in healthcare ML solutions, as part of my PhD & also as consultant to a telemedicine company. My experience in dealing with data (we had sufficient, and somewhat well labeled) & methods made me realize that a lot of the prediction human doctors make are multimodal - and that is something deep learning will struggle for the time being. For example, say in detection of a disease X , physicians factor in blood…

Thanks for sharing. My belief is that we need to figure out a way to make humans interact with prediction models in a virtuous way. Prediction models suck at "connecting the dots" or considering multiple sources of information (for example: multiple models predicting different outcomes). Until we get true general artificial intelligence, I think the way to go forward is to try to quantify those unknowns through confi…

Personally knowing the hit rate of these ML models & their non-explanatory nature, weighed against their low cost.. I'd argue they should be used as a default automated second opinion to radiologist opinion.

Recently went through a pet cancer death so though medical imaging, diagnostic testing, specialist escalation and second opinion workflows are pretty fresh in my mind. There is a shortage of specialists, backlog for appointments and many astonishingly bad practitioners out there.