Skin tone, confidence, and data quality of heart rate sensing in WearOS smartwatches
Abstract
Smartwatches can collect heart rate data unobtrusively and continuously, making them a promising tool for conducting long term studies, monitoring chronic conditions, and providing timely intervention. Healthcare applications, however, require us to understand the reliability of collected readings, both in terms of quality and quantity. The accuracy of optical heart rate (HR) measurements has been studied extensively in recent years, identifying several common causes of errors. For example, previous research has demonstrated that inaccurate HR readings occur more frequently in dark skin as compared to light skin due to melanin absorption. Smartwatches therefore implement a confidence mechanism to estimate reliability of HR readings. We study the effect of skin tone on the reliability of confidence estimation of seven consumer-grade WearOS smartwatches. We find that some watches systematically underestimate the reliability of HR readings taken from dark skin, despite no substantial difference in actual error. This results in significantly fewer data points for people with darker skin tones, which can bias downstream applications. We also report a wide variation in how watches implement the same WearOS API for HR collection, with implications for researchers that intend to use them for studies.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Some WearOS smartwatches underestimated heart rate by 10-15 bpm in darker-skinned users during moderate to vigorous exercise, compared with near-baseline error in lighter-skinned participants.
“Ray et al. (2021) observed that some WearOS smartwatches underestimated heart rate by 10-15 bpm in darker-skinned users during moderate to vigorous exercise, compared with near-baseline error in lighter-skinned participants [1].”
From Photoplethysmography in Diverse Skin Tones: Evaluating Bias in Smartwatch Health Monitoring (2025) · cites this paper as [1]
PPG technology typically relies on green light wavelengths, which are particularly affected by melanin's higher absorption.
“Photoplethysmography (PPG) technology typically relies on green light wavelengths, which are particularly affected by melanin’s higher absorption [1].”
From Photoplethysmography in Diverse Skin Tones: Evaluating Bias in Smartwatch Health Monitoring (2025) · cites this paper as [1]
Four of the ten included studies found no difference in heart rate accuracy between participants of different skin tones.
“Four studies noted no effect of user skin tone on accuracy.”
From Accuracy of heart rate measurement with wrist-worn wearable devices in various skin tones: a systematic review (2023) · cites this paper as [14]
In three of the included studies, skin tone was the primary variable considered in the accuracy of wrist-worn heart rate monitors.
“In three of the included studies, skin tone was the primary variable considered in the accuracy of wrist-worn heart rate monitors [1, 2, 14].”
From Accuracy of heart rate measurement with wrist-worn wearable devices in various skin tones: a systematic review (2023) · cites this paper as [14]
Ray et al. found that various WearOS watches systematically underestimate the reliability of HR readings taken from dark skin, despite no substantial differences in error, leading to significantly fewer recorded data points in patients with dark skin.
“Ray et al. found that various WearOS watches systematically underestimate the reliability of HR readings taken from dark skin, despite no substantial differences in error, leading to significantly fewer recorded data points in patients with dark skin [14].”
From Accuracy of heart rate measurement with wrist-worn wearable devices in various skin tones: a systematic review (2023) · cites this paper as [14]
The citation lists haven’t been fetched yet
References 29 · Cited by 23
- Authors
- Ray, I., Liaqat, D., Gabel, M., & de Lara, E.
- Affiliations
- University of Toronto (CA)
- University of Toronto,Toronto,Canada
- ORCID
- Liaqat, Daniyal
- Venue
- 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)
- Publisher
- IEEE
- Published
- 2021-03-22
- Pages
- 213-219
- OpenAlex
- W3172785686
- Cited by
- 23
- References
- 29
- Citations by year
- 2026: 1 · 2025: 9 · 2024: 3 · 2023: 2 · 2022: 5 · 2021: 3
- FWCI
- 6.16
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) (publishedVersion)
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- heartbeat detection, smartwatches, skin tone, melanin absorption, confidence estimation, data quality, dark skin, consumer-grade wearable devices, measurement bias
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
