Wearable Tech for Cardiac Monitoring May Give Spotty, Inaccurate Data Depending on Skin Tones

Daniel Koerber, MD

New data from a systematic review of data from nearly a dozen studies suggest patients of Hispanic or African ancestry may benefit less from wearable technology than their White counterparts.

Presented at the American College of Cardiology’s annual 71st Scientific Session (ACC.22), the University of Alberta-led study suggests wearable devices with abilities to measure heart rate and arrhythmia were significantly more accurate for measurements of heart rate and detecting arrhythmia when used in patients with lighter skin tones, which investigators suggest indicates the need for further refinement of this technology.

“People need to be aware that there are some limitations for people with darker skin tones when using these devices, and the results should be taken with a grain of salt,” said Daniel Koerber, MD, resident physician at the University of Alberta in Edmonton, Canada, and the study’s co-lead author, in a statement. “Algorithms are often developed in homogeneous white populations, which may lead to results that are not as generalizable as we would like. Ongoing research and development of these devices should emphasize the inclusion of populations of all skin tones so that the developed algorithms can best accommodate for variations in innate skin light absorption.”

With cardiovascular disease representing the leading cause of death in the US, cardiology often finds itself in the spotlight of mainstream media and with the attention of the general public. In recent years, the public have become enamored with the potential of wearable devices to improve remote patient monitoring and, by extension, management of cardiovascular disease. Yet, as many in the field will attest, the jury is out on whether these devices are truly ready to be leveraged as an avenue for improving care in real-world settings.

With this in mind, Koerber and a team of colleagues designed the current study as a systematic review of data from studies assessing heart rate and rhythm data for consumer wearable technology according to participant race or skin tone from the Embase, MEDLINE, CINAHL, and Cochrane database. Searching from database inception through July 28, 2021, investigators identified 622 articles and, from this group, 10 studies meeting inclusion criteria were selected for further analysis.

For the purpose of analysis, skin tone was expressed using the Fitzpatrick score, which provides numerical classification for human skin color ranging from 1-6. From the 10 studies selected for inclusion, the total patient population was 469. Of the 10 studies included, 6 studies, with a population of 293, reported frequency-weighted Fitzpatrick scores. The mean score among participants in these studies was 3.5.

Upon analysis, results indicated 40% of studies reported a significant reduction in accuracy of heart rate measurements using wearable device among individuals with higher Fitzpatrick scores than those with lower scores and compared to gold standard measurements, such as those performed using an ECG or chest strap monitoring.

Investigators noted a single study reported wearable devices recorded significantly fewer data points for individuals with darker skin tones, but did not report a discrepancy in accuracy of heart rate measurements. Investigators also pointed out only 1 study assessed ECG changes and noted a significant reduction in RR interval measurement in individuals with darker skin tones compared with ECG data (r=.98; P <.05).

“There are a lot of claims that these devices can detect heart rhythm issues like tachycardia, bradycardia and even atrial fibrillation,” Koerber said. “We want to be able to inform health care providers about whether these are reliable sources for collecting data in all patients, regardless of skin tone.”

This study, “The Effect of Skin Tone on Accuracy of Heart Rate Measurement in Wearable Devices: A Systematic Review,” was presented at ACC.22.