Does your health monitor have a device bias? Harvard Health Blog


In recent years, there has been a real explosion in the number and type of health monitors available in smartphones and fitness apps.

Your smartphone will likely track the number of steps you take, how far and fast you walk, and the number of stairs you climb each day. Some phones record sleep, your heart rate, how much energy you burn, and even “walking health” (how many times are your feet on the floor? How do you even step up?). Of course, non-wearable devices and fitness tools are available, such as devices that measure your heart rhythm, blood pressure or oxygen levels. The accuracy of these devices varies – in some cases, your skin tone can make a difference.

In general, how accurate are health monitors?

I know from my experience with hospital monitors that they are not always accurate. False alarms from EKG monitors often send medical staff quickly to patient rooms, only to find the patient feeling well and surprised by the uproar. Particularly common false alarm is dangerous and unstable heart rhythm on the continuous cardiac monitoring device, which could be due to movement from the patient brushing his teeth.

High risk devices with the possibility of monitoring, such as Defibrillators And the Defibrillators, Widely used by their makers and Checked by the Food and Drug Administration, So its accuracy and reliability are generally good.

But what about home health monitors that are intended for consumer use and have not been extensively tested by the Food and Drug Administration? Have you ever stepped back just a few minutes to see if your phone balance agrees? Or climb several stairs to see if you’re getting full credit for not taking the elevator?

Consumer hardware accuracy depends in part on What or what Are being watched. For example, one study evaluated the Accuracy of heart rate monitors and energy expenditure calculators In phones and health applications. Accuracy was very high for heart rate (often in the range of 95%), but much less accurate with respect to energy expenditure. Resolution can also vary by Who is the Are being watched.

Device bias: what it is and why it happens

While there is no perfect health tool, some users get more reliable results than others. For example, if you wear nail polish, a pulse oximeter – a device that is attached to the tip of a finger to measure oxygen in the blood through the skin – may not work well, because the coating interferes with the proper function of the light sensor. In this case, there is a simple solution: remove the polish.

But in other cases, the solution is not simple. We are increasingly aware that some medical devices are less accurate depending on a person’s skin tone, a phenomenon called device bias.

  • Pulse oximeter. Although it is generally considered to be highly accurate and commonly trusted in healthcare settings, its accuracy tends to be so. Less in people of color. This is because the device relies on shining light through the skin to reveal the color of blood, which varies according to the level of oxygen. The amount of pigment in the skin may change the way the light behaves as it travels to the blood vessels, resulting in inaccurate results. The The U.S. Food and Drug Administration (FDA) has issued an alert About this and other limitations of using a pulse oximeter.
  • Measurement of bilirubin in newborns. Bilirubin is the product that breaks down red blood cells. Newborns are screened for high levels As this can cause permanent brain damage. When detected, light therapy (light therapy) can help the child get rid of excess bilirubin, which prevents brain damage. The examination includes examining the skin and eyes of the newborn for jaundice (yellowing due to elevated bilirubin) and a light meter test to detect elevated bilirubin levels. But The accuracy of this test is lower in black newborns. This is especially important because jaundice is more difficult to spot in dark-skinned infants, and dangerously high bilirubin levels are more common in this population.
  • Heart rate monitors in smartphones. to me At least one studySmartphone applications may be less accurate in people of color. Again, this is because the higher the number of skin pigment, the more light sensors that detect pulses in the blood flow reflect the heartbeat.

Why does device bias matter

Sometimes a measurement error does not have immediate health consequences. The error rate of 5% to 10% when measuring heart rate may be of little effect. (In fact, one might ask why would anyone need a heart rate monitor when you could just count your pulse by 15 seconds and hit it by 4!)

But pulse oximeter readings are used to help determine whether a person needs to be admitted to the hospital, who needs to be admitted to the intensive care unit, and who needs additional testing. If the oxygen level is consistently overestimated in people of color, they may be more likely to be treated compared to others whose readings are more accurate. This may exacerbate pre-existing inequalities in health care.

These examples add to the growing list of An inherent bias in health care, And the Other cases Failure to include diverse individuals has dire consequences. When you’re using a health device, it makes sense to wonder if it has been tested on people like you. It is also reasonable to expect people who develop medical devices and consumer health devices to broaden the demographics of test subjects, to ensure that results are reliable for all users before they are put on the market.

Sometimes there is a change in technology, such as using an Different type of light sensor, It can make health related devices work more accurately for a larger group of people.

Or, there may not be an easy solution, and user characteristics will have to be incorporated into the correct interpretation of the results. For example, the device can provide the user with a choice of skin tone to match the skin tone. Then based on comprehensive data from pre-testing for people with different skin colors, the device can adjust the results appropriately.

The bottom line

The push to monitor our bodies, our health, and our life experiences continues to gain momentum. So we need to test and validate the health related devices to ensure they work with diverse individuals before declaring them suitable for the general public. Until then, device bias won’t disappear: Objects are different, and technology has its limits. The key is to know it exists, fix what can be fixed, and interpret the results accordingly.

Follow me on Twitter Embed a Tweet


Like it? Share with your friends!


What's Your Reaction?

hate hate
confused confused
fail fail
fun fun
geeky geeky
love love
lol lol
omg omg
win win


Your email address will not be published. Required fields are marked *