Video-based heart rate monitoring across a range of skin pigmentations during an acute hypoxic challenge

Abstract

The robust monitoring of heart rate from the video-photoplethysmogram (video-PPG) during challenging conditions requires new analysis techniques. The work reported here extends current research in this area by applying a motion tolerant algorithm to extract high quality video-PPGs from a cohort of subjects undergoing marked heart rate changes during a hypoxic challenge, and exhibiting a full range of skin pigmentation types. High uptimes in reported video-based heart rate (HRvid) were targeted, while retaining high accuracy in the results. Ten healthy volunteers were studied during a double desaturation hypoxic challenge. Video-PPGs were generated from the acquired video image stream and processed to generate heart rate. HRvid was compared to the pulse rate posted by a reference pulse oximeter device (HRp). Agreement between video-based heart rate and that provided by the pulse oximeter was as follows: Bias = − 0.21 bpm, RMSD = 2.15 bpm, least squares fit gradient = 1.00 (Pearson R = 0.99, p < 0.0001), with a 98.78% reporting uptime. The difference between the HRvid and HRp exceeded 5 and 10 bpm, for 3.59 and 0.35% of the reporting time respectively, and at no point did these differences exceed 25 bpm. Excellent agreement was found between the HRvid and HRp in a study covering the whole range of skin pigmentation types (Fitzpatrick scales I–VI), using standard room lighting and with moderate subject motion. Although promising, further work should include a larger cohort with multiple subjects per Fitzpatrick class combined with a more rigorous motion and lighting protocol.

Sources of Inaccuracy in Photoplethysmography for Continuous Cardiovascular Monitoring

“…However, the authors also mentioned that the lack of environmental control leads to increased humidity and possibly increased vasodilation [ 41 ]. In addition to these examples, numerous other studies that stratify results against Fitzpatrick classification identify the same trend; errors in determining heartrate from wearable PPG devices that use primarily green light as their source is increased in individuals with dark skin tones due to the high absorption caused by increased amounts of epidermal melanin [ 42 , 43 , 44 , 45 ]. Lastly, Bent et al published an experimental analysis of error observed in optical heart rate sensors manufactured by Apple (Apple Watch 4), Fitbit (Fitbit Charge 2), Garmin (Garmin Vivosmart 3), Xiaomi (Xiaomi Miband 3), Empatica (Empatica E4), and Biovotion (Biovation Everion) as a function of skin tone [ 46 ].…”

Cardiovascular assessment by imaging photoplethysmography – a review

“…A couple of works considered the impact of skin pigmentation [51][52][53][54]. Those works show the tendency of higher values in the Fitzpatrick scale to degrade the results but proper methods might be able to compensate for the skin tone.…”

Synthetic Data for Multi-Parameter Camera-Based Physiological Sensing

“…Perhaps the most obvious appearance characteristic when measuring the blood volume pulse optically is skin type. Previous work has found systematic biases in the performance of non-contact photoplethymography measurement algorithms with skin type [40], [22]. Specifically, performance is over signficantly poorer for darker skin types.…”