Feasibility of continuous fever monitoring using wearable devices

Abstract

Elevated core temperature constitutes an important biomarker for COVID-19 infection; however, no standards currently exist to monitor fever using wearable peripheral temperature sensors. Evidence that sensors could be used to develop fever monitoring capabilities would enable large-scale health-monitoring research and provide high-temporal resolution data on fever responses across heterogeneous populations. We launched the TemPredict study in March of 2020 to capture continuous physiological data, including peripheral temperature, from a commercially available wearable device during the novel coronavirus pandemic. We coupled these data with symptom reports and COVID-19 diagnosis data. Here we report findings from the first 50 subjects who reported COVID-19 infections. These cases provide the first evidence that illness-associated elevations in peripheral temperature are observable using wearable devices and correlate with self-reported fever. Our analyses support the hypothesis that wearable sensors can detect illnesses in the absence of symptom recognition. Finally, these data support the hypothesis that prediction of illness onset is possible using continuously generated physiological data collected by wearable sensors. Our findings should encourage further research into the role of wearable sensors in public health efforts aimed at illness detection, and underscore the importance of integrating temperature sensors into commercially available wearables.

Deep learning-based detection of COVID-19 using wearables data

“…Tracking biometric data from wearable devices is a promising method for detecting COVID-19 5–9 and other respiratory viral infections. 10 Wearable devices contain a myriad of different sensors that collect distinct data types such as heart rate, steps, and sleep, which can potentially be used to track viral infections over time and proactively detect their onset using statistical methods like cumulative sum (CUSUM), RHR-Diff, and HROS-AD, as in our previous work.…”

Quantified Flu: an individual-centered approach to gaining sickness-related insights from wearable data

“…The goal of this work was to address two main questions: (1) As personal science practitioners, can we provide ourselves a way to generate self-expertise through building practical self-knowledge; and (2) Can methods of co-creation adapted from existing peer-production systems successfully support the development of collective knowledge in a community that is mostly concerned with individual discovery? By taking this perspective, this work is in contrast to the plethora of population level studies that are typically performed to evaluate the usefulness of wearable technology for the prediction of illness [20], [24]- [27].…”

“…Anecdotal reports from self-trackers suggested that wearables may provide evidence of COVID-19 infection [23]. During the first year of the COVID-19 pandemic, a small number of studies appeared, highlighting that wearable devices, often along with self-reported symptoms, might indeed be used for the early detection of COVID-19 infections and to assess physiological symptoms [24]- [27]. The majority of these studies take a crowdsourcing-based approach -in which participants are invited to contribute by providing their own wearable data along with regular symptom reports and COVID-19 test results -as the main way of engaging individuals.…”

Predicting Covid-19: wearable technology and the politics of solutionism

“…available since about 2017, became a flashpoint in the articulations between technology and public health during the pandemic. Some researchers are employing the Ring in attempts to continuously track whether a wearer is developing fever-like symptomsand, in turn, developing COVID-19 (Smarr et al 2020). In news reporting and commentary, the mere existence of this research has led to the repeated assertion that Oura Rings can predict COVID-19 symptoms in individuals (Fowler 2020).…”

“…A press release from May 28, 2020, which was heavily cited in the subsequent reporting, claimed 'the RNI has created a digital platform that can detect COVID-19 related symptoms up to three days before they show up'; but, again, there are no publicly available findings for researchers to actually assess this claim, as the studies are still ongoing and as of January 2021, the project's website gives no indication its studies or datasets have been formally peer reviewed and published (WVU Medicine 2020). While an unrelated study of Oura's capacity to detect temperature fluctuations (and, thus, fever) was published in December 2020 (Smarr et al 2020), it was very careful to hedge its results, suggesting (quite obviously) 'people are different, and so are physiological systems' (p. 7). While some researchers have centred Oura in their studies, in other words, they are relatively careful to indicate Oura in-andof-itself cannot offer much of a solution.…”