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

Pulse oximeters give biased results for people with darker skin

bostonreview.net

Post reply on HN
Print view View original

51–60 of 124 posts

Re: Pulse oximeters give biased results for people with darker skin

#51

Post by IndPhysiker »

simion314 wrote: post #12
PaulHoule wrote: post #6

If I understand it, they looked at 3 pulse ox meters. The expensive one from the company that was sponsoring the study read about one point (out of 100) lower on blacks which is inaccurate but not outrageous. One of the off-brand meters was completely wrong (e.g. dangerous) for blacks, the other one was in between.

They look at a few studies too and asked around companies if they handled the issues mentioned in those studies, the most positive result was that some models from one company are now better)probably some of the others are not). IMO seems that the certifications for this devices, especially for the ones used by medical stuff to decide things need to be better tested. Other interesting point that I did not consider is…

Nonin created the first of these back in the '90s, so I pulled one of their spec sheets from 2016 (https://www.nonin.com/wp-content/uploads/2018/09/NoninConnec...) which explicitly mentions the pigmentation issue along with nail polish, poor circulation, and breathing issues. From that, this isn't exactly a new or unknown thing since commercial products have been working around this for some time. I wasn't able to find an industry standard for testing on these, so maybe the article should cite that as an opportunity to improve a product or add a new method?

Re: Pulse oximeters give biased results for people with darker skin

#52

Post by detaro »

ravenstine wrote: post #41
exikyut wrote: post #36

Earlier quoted context omitted.

Oh, THAT'S why entrance barriers at supermarkets only occasionally fail, but fail consistently on a given day... Wait. Would this happen to PIR-based systems?

I'm not sure. It seems at least possible with supermarket doors because those supposedly use a low-power microwave beam. With PIR, it still relies on a deflection of a beam, so I think it would be a problem with that as well, but I'm just guessing.

PIR doesn't have a "beam", it detects temperature changes (i.e. you, a warm object, moving around). Clothes could play a role, not sure if the color though.

Re: Pulse oximeters give biased results for people with darker skin

#53

Post by klyrs »

oneplane wrote: post #22

And darker coloured textiles are less visible on people with darker skin. Grass is green and bananas tend to be curved. I get that it is interesting to research optically measuring systems to 'search for bias' and I'm sure there are going to be biases in varying degrees, but that doesn't mean it's always for the same reason or with the same result. There are very real problems of course, take the example with the pho…

If you have stairs leading up to the porch of your house, they aren't there to prevent people with disabilities from entering. They're there because it's a cheap and convenient solution.

If the building is commercial, not residential, you'll find yourself on the business end of an ADA complaint. Not because of malice, but because of neglect.

Re: Pulse oximeters give biased results for people with darker skin

#54

Post by treis »

jrajav wrote: post #26
treis wrote: post #13

This really isn't a big deal. Doctors know that these pulse ox meters aren't very accurate and use them accordingly. Nobody's changing their plan because you have a pulse ox of 93 instead of 95. They're there to quickly measure big changes that indicate a problem. In other words, they're looking for patients going from 98 to 75, not 98 to 95.

What's the point of casually dismissing this article's premise? Whether the conclusions are fully sound or not isn't the goal of this article, this is journalistic not academic. The goal is to raise awareness of a potential bias, and I think it achieves that (assuming the facts all check out). For one, according to the article the discrepancy was found to be up to 8 points in some cases, not 3. And it seems reasonabl…

>What's the point of casually dismissing this article's premise?

Because it should be casually dismissed. This person doesn't know what they're talking about, refused to listen to the people who told them they didn't know what they are talking about, and wrote an article full of nonsense.

Re: Pulse oximeters give biased results for people with darker skin

#55

Post by vr46 »

vinay427 wrote: post #20
vr46 wrote: post #2

Quelle surprise - garbage in, garbage out. I'll bet my Apple Watch doesn't have these issues.

The Apple Watch doesn't have a pulse oximeter (EDIT: it does have one that is not approved and therefore is disabled), so it would be difficult for it to have this issue. You might be thinking of optical HR measurement, for which sensors have also been shown to have skin color biases in some cases. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7010823/

Ah yeah, maybe. I've had the watch and previously a Vivoactive HR and they never seemed to have any trouble with my skin colour when measured against other measurement methods.

Re: Pulse oximeters give biased results for people with darker skin

#57

Post by vr46 »

ChrisLomont wrote: post #10
vr46 wrote: post #2

Quelle surprise - garbage in, garbage out. I'll bet my Apple Watch doesn't have these issues.

>I'll bet my Apple Watch doesn't have these issues. I bet they do. They certainly did a while back, and I've found nothing saying this has been fixed. https://bossip.com/1137485/race-matters-new-apple-watch-malf...

Mildly interesting, but that looks exceedingly anecdotal.

Re: Pulse oximeters give biased results for people with darker skin

#58

Post by vr46 »

vinay427 wrote: post #49
ceejayoz wrote: post #23

Earlier quoted context omitted.

> The Apple Watch doesn't have a pulse oximeter Yes, it does. The FDA blocked its use. https://www.city-journal.org/fda-blocks-apple-watch-blood-ox... https://www.cultofmac.com/320322/apple-watch-sensors-are-cap...

Noted and thanks for the information, but as far as I can tell my point stands if the feature is completely inaccessible. I don't really understand what the GP comment was referring to regarding Apple Watch pulse oximetry accuracy. Other consumer devices such as my smartphone and watch have working pulse oximeter sensors built-in that are presumably FDA approved (or not FDA banned anyway), so it doesn't bode well for…

I have a lot of confidence in Apple even if they are less than 100% all the time. They put a vast amount of effort into catering for diverse users, their iOS accessibility, for example. So I would bet that the Watch sensors are solid. Or will be, as the feature appears to be coming soon: https://9to5mac.com/2020/03/08/apple-watch-blood-oxygen-satu...

Re: Pulse oximeters give biased results for people with darker skin

#59

Post by newacct583 »

oneplane wrote: post #22

And darker coloured textiles are less visible on people with darker skin. Grass is green and bananas tend to be curved. I get that it is interesting to research optically measuring systems to 'search for bias' and I'm sure there are going to be biases in varying degrees, but that doesn't mean it's always for the same reason or with the same result. There are very real problems of course, take the example with the pho…

> And darker coloured textiles are less visible on people with darker skin. Grass is green and bananas tend to be curved.

The point isn't that people have different skin. It's not even that this one common device works better for some people than others. It's that the practice of medicine, having grown up around this cheap and effective device, turns out to be discriminatory in ways that we wouldn't naively expect.

That's worth talking about, because it's a problem that should be fixed.

> apply Hanlon's razor when in doubt - it's not always malice like people often assume

Nowhere in the article is "malice" alleged. You added that part yourself, precisely because the bias described has infected you too. Reflexively arguing that "black people get bad O2 readings" is an argument that shouldn't be made in journalism isn't helpful to anyone, most especially the patients needing better care.

Re: Pulse oximeters give biased results for people with darker skin

#60

Post by travisporter »

controversy wrote: post #4
return1 wrote: post #3

Can’t they just be wrong , do they need to be biased? Has the english language run out of words except the ones ending in -ist?

While I get being touchy about such a term, I think bias is the proper term here. https://en.m.wikipedia.org/wiki/Bias_(statistics)

"Pulse oximeters give less accurate results for people with darker skin" would have conveyed exactly the same information, but probably would have yielded fewer clicks
Post reply on HN