Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

scientificamerican.com

Post reply on HN
Print view View original

21–30 of 162 posts

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

#21

Post by spywaregorilla »

drtgh wrote: post #12

My humble opinion; AI is supposed to be the acronym for artificial intelligence, but marketing has usurped it to refer to machine learning, which is nothing more than a neo-language for defining statistical equations in a semi-automated way. An attempt to dispense with mathematicians to develop models. What amount of energy is necessary for an event to be reflected in a statistic? You have a box of 2x2 meters with ba…

> My humble opinion; AI is supposed to be the acronym for artificial intelligence, but marketing has usurped it to refer to machine learning, which is nothing more than a neo-language for defining statistical equations in a semi-automated way.

Sure. Hardly controversial.

> An attempt to dispense with mathematicians to develop models.

What...? No. Definitely not.

> What amount of energy is necessary for an event to be reflected in a statistic? You have a box of 2x2 meters with balls of data, and a string with a diameter of 1 meter with which to surround the highest concentration of balls possible, and those that remain outside, there they stay. Statistics and lack of precision are concepts that go hand in hand (someones say even it is not an science).

I have no idea what this is saying. It sounds like you're shitting on statistics all of a sudden, which is weird, given that you seemed to favor mathematicians in the first part.

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

#22

Post by spywaregorilla »

blackbear_ wrote: post #17
tensor wrote: post #15

This is entirely unsurprising and has a very simple solution: keep adding more data. Our measurements of the accuracy of AI systems are only as good as the test data, and if the test data is too small, then the reported accuracies won't reflect the true accuracies of the model applied to wild data. Basically, we need an accurate measure of whether the test data set is statistically representative of wild data. In hea…

From the article: > Here’s why: As researchers feed data into AI models, the models are expected to become more accurate, or at least not get worse. However, our work and the work of others has identified the opposite, where the reported accuracy in published models decreases with increasing data set size.

That's not a contradiction per se. It's easier to get spurriously high test scores with smaller datasets. It does not clearly demonstrate that the models are actually getting worse.

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

#23

Post by johannes_ne »

baxtr wrote: post #16
johannes_ne wrote: post #8

I recently published a paper, where we explain how an FDA approved prediction model, build into a widely used cardiac monitor was developed with an incredibly biased method. https://doi.org/10.1097/ALN.0000000000004320 Basically, the training and validation data was engineered so an important range for one of the predictor variables was only present in one of the outcomes, making perfect prediction possible for these…

Sorry for asking, but how is this relevant to the article?

Fair question. The model we comment on both suffer from the problem described in the article but also a more severe problem:

The developers sampled obvious cases og hypotension and nonhypotension, and trained the model to distinguish those. And also validated it on data that was similarly dichotomous. In reality the outcome is often between these two scenarios.

But worse, they also introduce a more severe problem where as range of an important predictor is only available in the hypotension outcome.

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

#24

Post by junipertea »

kbenson wrote: post #13
ericmcer wrote: post #9

Earlier quoted context omitted.

That scenario sounds like it lends itself more to AI automation than a Dr. House type one.

I don't know, compassion and understanding and nuanced understanding of individual desires when talking to someone is not what I associate AI with in my mind, but being able to assess sociological and cultural taboos and try to what a patient actually wants rather then what they might initially express seems like something I good doctor would get to through explorative conversation.

Maybe removing a human from the equation would lead to more honest outcome? E.g. people google all sorts of issues more earnestly than they would describe it to the doctors. The bottleneck would be properly understanding what the user intends, which might be out of reach.

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

#25

Post by dm319 »

kbenson wrote: post #13
ericmcer wrote: post #9

Earlier quoted context omitted.

That scenario sounds like it lends itself more to AI automation than a Dr. House type one.

I don't know, compassion and understanding and nuanced understanding of individual desires when talking to someone is not what I associate AI with in my mind, but being able to assess sociological and cultural taboos and try to what a patient actually wants rather then what they might initially express seems like something I good doctor would get to through explorative conversation.

My experience of chatting with an internet chat-bot when trying to get some help with a product gives me little confidence we are close here.

Edit: wording

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

#26

Post by charcircuit »

drtgh wrote: post #12

My humble opinion; AI is supposed to be the acronym for artificial intelligence, but marketing has usurped it to refer to machine learning, which is nothing more than a neo-language for defining statistical equations in a semi-automated way. An attempt to dispense with mathematicians to develop models. What amount of energy is necessary for an event to be reflected in a statistic? You have a box of 2x2 meters with ba…

>which is nothing more than a neo-language for defining statistical equations in a semi-automated way.

That's why it's called artificial intelligence.

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

#27

Post by ckemere »

bpodgursky wrote: post #10
deltree7 wrote: post #6

Yet. One thing media consistently gets wrong is the rate of innovation that is happening. Media also doesn't have access to state-of-the-art models, only from the trigger-happy startups too eager to release half-baked version. It's akin to downloading Image Generation tools from the App Store and concluding that's state of the art

It baffles me that people can watch the trendline of "Job X can be automated in 40 years" (5 years ago) "Job X can be automated in 10 years" (2 years ago) "Job X can be automated in 5 years" (1 week ago) And feel comfortable poking holes in the AI models, pointing out where it fails. Obviously? But nobody 3 years ago thought that graphic design or creative writing was on death's row either. You have to spend a modicu…

There's also the timeline that:

"Radiology will be automatized in 5 years" (10 years ago) "Radiology will be automatized in 5 years" (5 years ago) "Radiology will be automatized in 5 years" (last year)

or

"Full self driving will arrive within 5 years" (5 years ago) "Full self driving is still a ways off" (last year)

Assuming you're referring to generative models, I don't think that anyone (knowledgable) thinks that graphic design or creative writing are on death's door. They might change with new tools, but skilled practitioners are still required. That's basically the point of the article.

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

#28

Post by dm319 »

tensor wrote: post #15

This is entirely unsurprising and has a very simple solution: keep adding more data. Our measurements of the accuracy of AI systems are only as good as the test data, and if the test data is too small, then the reported accuracies won't reflect the true accuracies of the model applied to wild data. Basically, we need an accurate measure of whether the test data set is statistically representative of wild data. In hea…

I think this is a key point - the training set is very important, because biases, over-curation, or wrong contexts will mean the model may perform very poorly for particular scenarios or demographics.

I can't find the reference now of a radiology AI system which had a good diagnosis rate of finding a pneumothorax on a chest x ray (air in the lining of the lung). This can be quite a serious condition, but is easy to miss. Turns out that the training set had a lot of 'treated' pneumothorax. The outcome was correct - they did indeed have a pneumothorax, but they also had a chest drain in, which was helping the prediction.

Similar to asking what the demographic of training set is, is what the recorded outcome was. How was the diagnosis made. There is often no 'gold standard' of diagnosis, and some are made with varying degrees of confidence. Even a post-mortem can't find everything...

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

#29

Post by ben_w »

drtgh wrote: post #12

My humble opinion; AI is supposed to be the acronym for artificial intelligence, but marketing has usurped it to refer to machine learning, which is nothing more than a neo-language for defining statistical equations in a semi-automated way. An attempt to dispense with mathematicians to develop models. What amount of energy is necessary for an event to be reflected in a statistic? You have a box of 2x2 meters with ba…

> Statistics and lack of precision are concepts that go hand in hand (someones say even it is not an science).

Statistics is the mathematics of being precise about your level of imprecision. It's fairly fundamental to all science, and has been for a while now.

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

#30

Post by jerpint »

tomrod wrote: post #20

Technical (Honest) Solution: two holdouts 1. Involved in the build process 2. Never touched until paper metrics are being written, only run once Realistically, unlikely to occur however due to the incentives causing publication bias.

Third (better) option: have a regulating body have a separate, undisclosed test set. If you can't beat it, you can't deploy your model. If you can beat it, you still need to have your models peer reviewed and scrutinized
Post reply on HN