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

51–60 of 180 posts

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

#51

Post by proto-n »

jl6 wrote: post #30

> Models trained on low-pass filtered images maintained high performance even for highly degraded images. More strikingly, models that were trained on high-pass filtered images maintained performance well beyond the point that the degraded images contained no recognisable structures; to the human coauthors and radiologists it was not clear that the image was an x-ray at all. What voodoo have they unearthed?

I tend to not believe unbelievable results in machine learning. It's too easy to unintenionally cause some kind of information leakage. I haven't read the paper in detail though, so their experimentation setup could be foolproof, this is not a critique of this paper specifically.

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

#52

Post by krona »

bb123 wrote: post #10

One idea is that there is some difference in the x-rays themselves that could potentially be explained by racial disparities in access to (and quality of) healthcare. Maybe white people tend to visit hospitals with newer, better equipment or better trained radiographers and the model is picking up on differences in the exposures from that.

> We also showed that the ability of deep models to predict race was generalised across different clinical environments, medical imaging modalities, and patient populations, suggesting that these models do not rely on local idiosyncratic differences in how imaging studies are conducted for patients with different racial identities.

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

#54

Post by amarshall »

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.

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

#55

Post by airza »

jcranberry wrote: post #36
airza wrote: post #27

Earlier quoted context omitted.

The article is pretty fascinating and I recommend that you actually read it. For example: >"We found that deep learning models effectively predicted patient race even when the bone density information was removed for both MXR (AUC value for Black patients: 0·960 [CI 0·958–0·963]) and CXP (AUC value for Black patients: 0·945 [CI 0·94–0·949]) datasets. The average pixel thresholds for different tissues did not produce…

So just from the silhouette of a skeleton, if I understand that correctly?

Even after being munged into a nearly-uniform gray by high pass the effect seems pretty robust.

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

#56

Post by oaktrout »

bb123 wrote: post #8
mensetmanusman wrote: post #4

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

Perhaps there is some quality of the x rays themselves that is different? Maybe white people tend to visit hospitals with newer, better equipment or better trained radiographers and the model is picking up on differences in the exposures from that.

From the paper "Race prediction performance was also robust across models trained on single equipment and single hospital location on the chest x-ray and mammogram datasets"

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

#57

Post by andrewmcwatters »

scandox wrote: post #22
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…

Quoted post unavailable.

The reality is more humbling: humanity is vast and knowledge is not uniformly dispersed.

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

#58

Post by aulin »

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."

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?

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

#59

Post by Beltiras »

tomp wrote: post #17

If you’re interested in “hard to describe features that can be learned with enough expiration”, look up chick sexing https://en.wikipedia.org/wiki/Chick_sexing#Vent_sexing

Interesting field. You have to breed a couple of males to maintain the species. If you were to pick those from the mis-sexed group I suppose natural selection would reduce the classifying feature over time. I wonder if poultry farms pick a couple of the male-classified birds to maintain a stock of well identifiable males and kill all the mis-classified males.

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

#60

Post by rmbyrro »

scandox wrote: post #22
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…

Quoted post unavailable.

Why's that?

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

Post reply on HN