Fitness Trackers Inaccuracy
|Fitness Trackers Inaccuracy
|Accuracy of Fitness Trackers Data Can Depend on Users Age, Gender and Skin Tone
|Identifying, Ethnicity, Behavioral, Demographic, Medical and Health, Physical Characteristics, Computer Device
|Fitbit Inc., Apple, Other fitness trackers
|Fitness trackers users
|High Risk Groups
|Females, Elderly, Ethnic Minority
Fitness trackers can help users learn about their health, activity, recognize patterns, and reflect on their behavior, but the data these devices provide was found to be not always true.
The reason for the data inaccuracy in fitness tracking devices and apps, such as Fitbit or Apple Watch, is that they often display not the information they know, but the information they assume.
For example, in case of step counting, devices don’t specifically count each step; they approximate using what’s called an “accelerometer”. Accelerometers use electromagnetic sensors to pick up on motion, and the fitness trackers interpret that information using an algorithm that trains the devices to recognize what counts as a step.
However, the algorithms used are usually based on data from studies that enroll college-age men. So for example, for women the information about their step count isn't accurate, which can be seen as Distortion. The same is true for older adults who move more slowly, those who walk with a limp, or those who have Parkinson’s disease.
One laboratory study has shown, that 50 Percent of the time that fitness trackers undercounted steps.
In case of heart rate measurement, studies have shown skin tone may influence the data accuracy. To measure heart rate, most trackers use a technique, which measures blood volume by shining a beam of green LED light into the wrist. These green LED sensors have to penetrate the skin in order to measure blood volume, but several studies suggest that green light is more likely to be absorbed by more melanated skin. Potentially this is why users with dark skin who have tried Fitbits and other trackers have complained that the devices give strange readings or don’t work at all.Distortion
And considering the devices’ uncertain accuracy across demographics, it can also be seen as Exclusion, since the users don't expect their age, gender or skin tone to influence the accuracy of the metrics.