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

111–120 of 124 posts

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

#111

Post by godelski »

PascLeRasc wrote: post #21

I'm a student EMT and our instructor told us not to rely on a pulse ox reading if our patient has dark skin, or if they were in a fire, or are a lifelong smoker, or if they have any nail polish or dirt/grease on their fingertips. We just look for the 94-100% range and would only take action if we get a reading around 87% or lower, or see a sudden drop during treatment. There are a few alternatives designs that aim to…

Just so you have some extra information (I actually build a heart rate monitor and pulse oximiter) skin color and transparency makes a big difference, same with the color of the LEDs. I'm pretty pale and one of my friends is pretty tan, my signal was much stronger than his. The IR (infrared) ones work better as they are able to penetrate the skin better and there are clearer absorption lines from oxidized blood. I also tested different locations to place the device, I did notice most are fingertip or wrist (fitbits and smart watches), but found I got substantially stronger signals by placing the device near the upper forearm (god did this help in debugging). This was true for everyone I tested (unfortunately only white people) and helped smooth out the data a little, but it was still noticeable.

On how these devices work, it is typically two LEDs the produce light that bounces through the skin, some light is absorbed by blood (different absorption by different oxidation and density) then the reflected light is captured by a photodiode. All of this is on one surface, they are very basic. The density changes rapidly and that's how you capture the pulse (easy to get btw) and the oxidation is based on absolute levels (THIS IS THE PROBLEM!!!!). After building one I learned to not take these things too seriously, especially fingertip and wrist mounted ones.

I encourage others to build them. You can do most of it in a weekend if you have some soldering experience (best if you can do surface mount soldering), some programming, and are comfortable doing data analysis. And no, I do not expect my device to be on par with the ones in hospitals, but I was quickly able to match readings from a finger based device that I bought from the local drug store.

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

#112

Post by skwb »

jennyyang wrote: post #72
jrajav wrote: post #26

Earlier quoted context omitted.

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…

Medicine is very rarely about absolutes, it's mostly about how things get better or worse. When I was in the hospital, no one looked at the absolute values of my blood work, they cared to see if it dropped based on the treatment they saw. Also, doctors are already aware about how oximeters may be inaccurate. It doesn't mean that they still can't be useful.

Yeah, if we had such cut and dry "rules" about medicine, then we could automate a lot of what doctors do. Medicine is as much about the art as it is the science. You come to understand the limitations of different measuring techniques, and learn to know when you need to rely on each for more accurate representations.

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

#113

Post by sangnoir »

DoofusOfDeath wrote: post #106
sangnoir wrote: post #101

Earlier quoted context omitted.

The article also mentions that nonwhite people have a higher rate of their trouble with breathing being dismissed as due to anxiety compared to white people... It's possible there is a layer of biases, and at each step, there's a risk of not getting timely medical intervention resulting in poorer outcomes.

Right. I wasn't trying to imply that the oxymeter bias explained the entire difference in outcome rates. I'm just curious if it matters enough to warrant further study.

I am agreeing with you, and speculating that the oxymeter is a small tip of the iceberg, and a multitude of "small" biases that add up to terrible outcomes.

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

#114

Post by JamesBarney »

sangnoir wrote: post #99
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.

> In other words, they're looking for patients going from 98 to 75, not 98 to 95 The problem is that that '95' might really be a '90' - surely a drop from 98 to 90 is a cause for concern. If that information is being hidden, it needs to be fixed, regardless of other, more subjective fallback methods.

The difference of 5% is only common in the 60-70% on some clips. In the 90%-100% level the different is up to 2%-3% on the worst pulse ox's, and usually around 1%.

For reference I have two pulse oximeters at home and they routinely give me results that differ by 2-3%.

Seems like an issue we should fix, but I don't know what impact this would have in a clinical setting given that they use multiple criteria and the devices are known to be inaccurate.

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

#115

Post by zamfi »

Teknoman117 wrote: post #97
zamfi wrote: post #71

Earlier quoted context omitted.

Frustratingly, this kind of dismissal perpetuates injustices. First, let's be clear: > Doctors know that these pulse ox meters aren't very accurate and use them accordingly Some doctors know... > 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. Sometimes , perhaps even often , they're used for this. It's one use case of…

I'd hardly call it injustice. Anything based on light is going to be variable depending on skin tone (or, as other have mentioned, darkened skin for any reason). The only thing you could claim injustice for would be if there was no other mechanism for measuring blood oxygen other than something that was known to not work properly for people of color.

A lot of other folks made this point, but I’m replying here because your response was the most considered.

No one — myself including — is saying that physics is biased, or that this tool is inherently biased. The headline is misleading, it’s really talking about the interpretation of the number that’s biased, not the physics. The number is just a number.

The bias comes through the typical institutional use of this tool, as described in the article: the “normal” regions are based on “normal” for lightly pigmented people, so heavily pigmented people are by default not in the “normal” range. Do some doctors realize this? Of course they do. But as programmers we all know the power of defaults some doctors won’t realize this, or will forget, or will realize it but it will still affect them.

Other policies (like the Medicaid one described in the article) also ignore these differences.

It’s not the physics that’s biased. It’s the institutional and individual assumptions around the tool.

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

#116

Post by dllthomas »

slowmovintarget wrote: post #93
zamfi wrote: post #71

Earlier quoted context omitted.

Frustratingly, this kind of dismissal perpetuates injustices. First, let's be clear: > Doctors know that these pulse ox meters aren't very accurate and use them accordingly Some doctors know... > 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. Sometimes , perhaps even often , they're used for this. It's one use case of…

This IS NOT BIAS ! This is physics! As someone else pointed out, this isn't only about melanin in the skin. Darkened skin for any reason will cause this (burns, smoking, dirt, etc...). Medical personnel are trained to account for this partial accuracy. The other fact is that there are newer techniques being worked on to improve the technology.

When a measurement device is, in some settings, consistently off in one direction... that's one of the most central definitions of bias.

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

#117

Post by dafoex »

Sorry if I'm not demonstrating adequate sympathy, but all I can thing of from reading this headline is "oh dear, a person with a genetic adaptation that prevents some wavelengths of light from penetrating to deeper layers of the skin will find it hard to make some wavelengths of light penetrate to deeper layers of the skin"

As a nonmedical person, this seems blindingly obvious - to the point I could reference the "floor is made of floor" meme - so it would surprise me to learn that professionals haven't considered this downfall of the technology when taking their readings. Judging by the discussion here, I don't think I'm going to be surprised today.

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

#118

Post by 0xdeadb00f »

I believe if we were given the race of the developers this bias would become clear - nothing against the developers or their race, I'm not implying the developers are racist in any way.

What I am saying is that systems developed by a team with a majority of single race is bound to have biases purely because of the lack in opinion diversity while testing the system.

But I could be completely wrong...

Edit: I pressed send by accident, I never meant to actually post this comment but I'm leaving it up anyways.

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

#119

Post by btach »

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…

Many quick, practical decisions are made on patient assessment and clinical judgement, not just numbers. None of us that I know of has ever come across a perfect pulse ox. "Treat the patient, not the numbers" as the saying goes. When they don't match up, I like to do things like use a different finger/hand (or ear lobe or forehead).

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

#120

Post by spoopyskelly »

x86_64Ubuntu wrote: post #35
jrajav wrote: post #26

Earlier quoted context omitted.

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…

This thread because it has race as a secondary theme will be rife with such statements dismissing the premise.

Bullshit should be dismissed, regardless of race.
Post reply on HN