Investigating the accuracy of Garmin PPG sensors on differing skin types based on the Fitzpatrick scale: cross-sectional comparison study

Abstract

Background: Commercial wearable devices, which are often capable of estimating heart rate via photoplethysmography (PPG), are increasingly used in health promotion. In recent years, researchers have investigated whether the accuracy of PPG-measured heart rate varies based on skin pigmentation, focusing particularly on the accuracy of such devices among users with darker skin tones. As such, manufacturers of wearable devices have implemented strategies to improve accuracy. Given the ever-changing nature of the wearable device industry and the important health implications of providing accurate heart rate estimates for all individuals no matter their skin color, studies exploring the impact of pigmentation on PPG accuracy must be regularly replicated.

Objective: We aimed to contrast heart rate readings collected via PPG using the Garmin Forerunner 45 in comparison with an electrocardiogram (ECG) during various levels of physical activity across a diverse group of participants representing a range of skin tones.

Methods: Heart rate data were collected from adult participants (18-64 years of age) at a single study session using the Garmin Forerunner 45 PPG-equipped smartwatch and the Polar H10 ECG chest strap. Skin tone was self-reported via the Fitzpatrick scale. Each participant completed two 10 min bouts of moderate-intensity walking or jogging separated by a 10 min bout of light walking.

Results: A series of mixed ANOVAs indicated no significant interaction between Fitzpatrick score and phase of the activity bout (i.e., rest at the start, first intensity ramp-up phase, first steady-state phase, active rest, second ramp-up phase, and second steady-state phase). Similarly, there was no significant main effect for the Fitzpatrick score, although there was a significant main effect for phase, which was driven by greater ECG-recorded heart rate relative to PPG during the first ramp-up phase.

Conclusion: Our findings support prior research demonstrating no significant impact of skin tone on PPG-measured heart rate, with significant differences between PPG- and ECG-measured heart rate emerging during dynamic changes in activity intensity. As commercial heart rate monitoring technology and software continue to evolve, it will be vital to replicate studies investigating the impact of skin tone due to the rapidity with which widely used wearable technologies advance.

Keywords: equity; exercise; heart rate; physical activity; wearables.

Figure 1

Bland–Altman plots contrasting differences in ECG vs. PPG by average across both devices. The lines are plotted for average difference and 95% confidence limits around the mean difference.

Figure 2

Scatter plot showing the relationship between participant Fitzpatrick scores and the difference between ECG and PPG heart rate values during the second ramp phase.