Does the smart health device people use today have an element of device bias?

4 minutes, 14 seconds Read

In recent years, there has been a veritable explosion in the kinds of health monitoring devices available in both fitness apps and smartphones. Yet, the element of biases in these devices is hard to observe for many.

As a matter of fact, anybody’s smartphone is most likely to be tracking the number of steps they are taking, how fast they are walking and how far they have walked, how many stairs they climbed, how many times they did it daily.

Some of the phones are logging in sleep times (i.e. when a person slept), heart-beat rate, the amount of energy they are burning, and how often are the feet on the ground as well as the evenness of the steps (Gait Health).

Non-phone wearables and fitness gadgets are undoubtedly available, especially those devices that measure the human heart’s rhythm, blood pressure, or oxygen levels. The accuracy of almost each device present is different and at times, the skin tone of any human being can be the differentiating factor.

How accurate are the health monitors, generally speaking?

One of the top cardiologist in Dubai shares one of their experiences regarding hospital monitoring devices. They revealed that most of these devices are not always accurate. False alarms coming from EKG monitors often send medical staff hurrying into patient rooms, only to find out that the patients were feeling fine which often surprises them about the fuss created by the machine.

One particularly common false alarm annoying medical staff and physicians alike is a dangerous and unstable heart rhythm on a continuous heart monitor, which can also arise due to the arm and hand motion when patients are brushing their teeth, scrubbing their own feet, combing their hair and the like.

High-risk devices having monitoring capability, like defibrillators and pacemakers, are extensively tested by their manufacturers and are assessed (as well as scrutinized) by the Food and Drug Administration (FDA). Such devices are highly accurate and are also quite reliable.

However, the role and quality of home health monitoring devices comes into questions because they are intended for consumer use. They are not extensively tested by the Food and Drug Administration (FDA).

Also, did people using these devices ever count their steps for a few minutes just to see if the tally of the phone agrees to the manual tally of the device’s user. How about climbing a couple of stair steps to see if they are receiving full credit for not using the elevator?

Legitimate questions asked, right?

The accuracy of consumer devices depends in part on what is monitored. For instance, a study assessed the accuracy of heart beat rate monitors and energy expenditure calculators in phones and health apps.

For the heart beat rate, the accuracy was quite high (usually in the range of 95%) but much less accurate for energy expenditure. Accuracy also differs based on who is being monitored (i.e. the kind of person being monitored).

What is device bias and why does it happen?

No health gadget is perfect and yet some users get more reliable results in comparison to others. For instance, those who are wearing nail polish, a pulse oximeter (a device clinging on to the fingertip to measure blood oxygen through the skin) may not work well on their fingertips because the nail polish interferes with its light sensor. 

In such a situation, there is a simple solution: Removing the nail polish.

In other cases, solutions are not easy. Also, physicians are recognizing that certain medical devices are less accurate due to a person’s skin color, a phenomenon known as device bias.

Pulse oximeters have often been considered as highly accurate and are relied upon in healthcare settings, they have a low accuracy in people of color. Why? Because the device depends on shining light through the skin to detect the color of blood which differs with the oxygen level.

The amount of pigment in the skin can alter the way the light behaves as it travels to blood vessels, leading to wrong results. Regarding this, an alert was released by the FDA and also issued other limitations of usage of pulse oximeters.

Measuring bilirubin in newborns becomes difficult in newborns of color. Bilirubin is a breakdown product of red blood cells and newborns are often screened for high levels of this because this can cause permanent brain damage.

When such is detected, phototherapy (light treatments) can help babies remove excess bilirubin which thus prevents brain damage. The screening involves examining a newborn’s skin and eyes for jaundice (a yellowing hue due to elevated levels of bilirubin) and a light meter test to detect its levels.

Accuracy of this test is lower in Black newborn infants because jaundice is difficult to detect in infants with darker skin and dangerously high bilirubin levels are common in this ethnic group.

Heart rate monitors in smartphones also produce inaccurate results for people of color. Here, the issue is again due to skin pigment causing trouble for light sensors having difficulties in detecting pulsations in blood flow reflecting heartbeats.



Syed Hassan is a cybersecurity expert at HostNoc. HostNoc is a premium IT solution provider that offers dedicated servers, web hosting, and many other IT services and products so businesses can fulfill their business needs.

Similar Posts