Feasibility of continuous fever monitoring using wearable devices.
Level 4 - case-series / case-control
Prospective case series of 50 individuals with COVID-19 wearing a consumer device
PubMed 33318528 · doi:10.1038/s41598-020-78355-6
What was done
The TemPredict study tracked continuous physiological data, including peripheral temperature, from a commercially available wearable device during the COVID-19 pandemic. Sensor measurements were coupled with self-reported symptoms and COVID-19 diagnosis logs in the first 50 participants who reported COVID-19 infection.
What was found
The abstract reports no numerical data, sensitivity/specificity values, or effect sizes. Qualitatively, peripheral temperature elevations detected by the wearable device correlated with self-reported fever, and analyses supported the feasibility of detecting illness in the absence of recognized symptoms and predicting illness onset.
Why it matters
This study provides preliminary evidence that consumer-grade wearable temperature sensors can continuously monitor physiological signals to flag fever and early infection onset during a pandemic.
Limits
The sample size is small (n = 50) and restricted to individuals with self-reported COVID-19 diagnoses. The abstract provides no quantitative metrics regarding diagnostic accuracy, false positive rates, or temperature detection thresholds. Peripheral temperature is an indirect proxy for core body temperature and is sensitive to ambient environmental changes.
Cited by
- supports Wearable-based algorithms tracking parameters like respiratory rate and body temperature can detect COVID-19 infection before symptoms appear.