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

AI recognition of patient race in medical imaging: a modelling study

thelancet.com

Post reply on HN
Print view View original

71–80 of 180 posts

Re: AI recognition of patient race in medical imaging: a modelling study

#71

Post by codefreeordie »

aulin wrote: post #58
matthewdgreen wrote: post #42

Earlier quoted context omitted.

"This issue creates an enormous risk for all model deployments in medical imaging: if an AI model relies on its ability to detect racial identity to make medical decisions, but in doing so produced race-specific errors, clinical radiologists (who do not typically have access to racial demographic information) would not be able to tell, thereby possibly leading to errors in health-care decision processes."

ok, maybe it's an US specific thing, why wouldn't a clinical radiologist have all the information he can gather about his patient including race to help the diagnosis?

Because in the US we are required to pretend that there is no such thing as race and no such thing as gender, and all people are exactly and precisely the same and there can be no differences.

Re: AI recognition of patient race in medical imaging: a modelling study

#72

Post by scandox »

rmbyrro wrote: post #60
scandox wrote: post #22

Earlier quoted context omitted.

Quoted post unavailable.

Why's that? Does Google have a filter that leaves all good science out of its indexes?

I object more concretely to the word "simply". Everyone who has some sort of agenda and doesn't actually read stuff starts with the word "simply". I'm tired of "simply" - meaning "listen to me and stop reading the actual content".

Re: AI recognition of patient race in medical imaging: a modelling study

#73

Post by orangepurple »

emddudley wrote: post #15
mensetmanusman wrote: post #4

What does this mean in terms of race being a social construct/concept?

There is no scientific, consistent way to define race. The groups we put people into is fairly arbitrary. They don't correlate to appearance, genetics, country of origin, etc. An interesting question in the U.S. is "who is considered white?" There was a Supreme Court case in which someone who was literally from the Caucasus was ruled not white. This is why it's sociological, not scientific. https://www.sceneonradio.o…

Alloco 2007 looked at random locations of single nucleotide polymorphisms(SNPs) and found that, using random SNPs, you still get very good correspondence between self-identification and best fit genetic cluster. Using as few as 100 randomly selected SNPs, they found a roughly 97% correspondence between self-reported ancestry and best-fit genetic cluster.

https://pubmed.ncbi.nlm.nih.gov/17349058/

Re: AI recognition of patient race in medical imaging: a modelling study

#74

Post by inglor_cz »

nerdponx wrote: post #31
hellohowareu wrote: post #5

Simply go to google image and search: "skeletal racial differences". subspecies are found across species-- they happen based on geographic dispersion and geographic isolation, which humans underwent for tens and hundreds of thousands of years. Welcome to the sciences of anatomy, anthropology, and forensics. other differences: - slow twitch vs fast twitch muscle - teeth shape - shapes and colors of various parts - gen…

Then problem is that human experts sometimes can't tell the difference while the model can.

AI is also able to determine your sex from your retinal scan with very good levels of certainty (provided that your retina is healthy; its ability to tell sexes apart drops in diseased retinas). [0]

Which came as a surprise to the ophthalmologists, because they aren't aware of any significant differences between male and female retinas.

[0] https://www.researchgate.net/publication/351558516_Predictin...

Re: AI recognition of patient race in medical imaging: a modelling study

#75

Post by ibejoeb »

matthewdgreen wrote: post #42
aulin wrote: post #18

Earlier quoted context omitted.

what's this enormous risk they're talking about? racial bias in x-ray reading? race can be a risk factor in plenty of diseases, why should we actively try to remove this information from medical images?

"This issue creates an enormous risk for all model deployments in medical imaging: if an AI model relies on its ability to detect racial identity to make medical decisions, but in doing so produced race-specific errors, clinical radiologists (who do not typically have access to racial demographic information) would not be able to tell, thereby possibly leading to errors in health-care decision processes."

Typically? It's coded in the standard. There's a DICOM tag for it.

https://dicom.innolitics.com/ciods/procedure-log/patient/001...

Re: AI recognition of patient race in medical imaging: a modelling study

#76

Post by codefreeordie »

amarshall wrote: post #54
tejohnso wrote: post #26

"This issue creates an enormous risk for all model deployments in medical imaging: if an AI model relies on its ability to detect racial identity to make medical decisions, but in doing so produced race-specific errors, clinical radiologists would not be able to tell, thereby possibly leading to errors in health-care decision processes." Why would a model rely on its ability to detect racial identity to make decision…

Just because the model relies on race in some way doesn’t mean that we know it relies on it. I.e., the model is, unbeknownst to us, biased on race in inaccurate ways.

Presumably the model would actually be biased on race in accurate ways, if it found the correlation itself

Re: AI recognition of patient race in medical imaging: a modelling study

#77

Post by kerblang »

> Importantly, if used, such models would lead to more patients who are Black and female being *incorrectly* identified as healthy

I think this is the point a lot of people are missing; they think, "So what if 'black' correlates to unhealthy and the model notices? It's just seeing the truth!"

However, I'm still wondering how this incorrectness works; can anyone explain?

Edit: Clue: The AI is predicting self-reported race, and the authors indicated that self-reported race correlates poorly to actual genetic differences.

Re: AI recognition of patient race in medical imaging: a modelling study

#78

Post by fullstackchris »

_8j50 wrote: post #32
mensetmanusman wrote: post #4

What does this mean in terms of race being a social construct/concept?

Still is? The AI is correlating biological features with self reported race. There are biological differences between people who have different ancestors. Finns are different from brits. The spanish are different from russians. Nigerians look different than somalians. The Japanese look differnet than filipinos. Race picks specific and arbitrary differences , for example hispanic is a different race in US society but…

Race as an entire concept to me has always been stupid at best. Sure, there are vast swaths of biological similarities (typically, though not necessarily) according to general geographic regions of the globe, but the real mistake was trying to give this vague concept a label. Can anybody give a definition of what "white" or "black" REALLY means? It's an impossible task. If we're talking just visually about skin color, congratulations, that represents citizens of some 100+ odd countries on the planet and just as many (if not many more!) cultures and languages. But leave it to humans to try and over optimize and try to denote evermore meaningless abstractions...

Let the social "culture war" rage on. The only war I see going on in the west (U.S. mostly) is a _lack_ of culture.

Re: AI recognition of patient race in medical imaging: a modelling study

#79

Post by orangepurple »

cdot2 wrote: post #23
omgJustTest wrote: post #9

Given the complexity of datasets, and what is known about the quality of medical scanners, is it possible that underserved communities (ie higher noise scanners) serve a specific community that is heavily skewed in race distributions?

"our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images" It doesn't seem like noise in the images is a factor

Imaging artifacts may persist despite corruption

Re: AI recognition of patient race in medical imaging: a modelling study

#80

Post by KaiserPro »

aulin wrote: post #18
tech-historian wrote: post #2

The interpretation part hit home: "The results from our study emphasise that the ability of AI deep learning models to predict self-reported race is itself not the issue of importance. However, our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images, often when clinical experts cannot, creates an enormous risk for all model deployments in medical imaging.…

what's this enormous risk they're talking about? racial bias in x-ray reading? race can be a risk factor in plenty of diseases, why should we actively try to remove this information from medical images?

> racial bias in x-ray reading?

no, it implies there is a signal in the dataset that could be something other than clinical. This means that until they can pinpoint the cause, or the thing the AI is detecting, all the other things it predicts are suspect.

ie if the AI thinks the subject is west african, then it might be more inclined to diagnose something related to sickle cell.

Or north western european woman in her mid 60s vs a japanese woman might get widly different bone density readings for the same level of "blob" (most medical imaging is divining the meaning of blobs and smears )

Post reply on HN