Health Data Science / 2022 / Article / Tab 4

Review Article

Mobile Sensing in the COVID-19 Era: A Review

Table 4

Study characteristics of remote detection literature.

ReferenceData typePopulation scaleSensing durationDescription

Kumar and Alphonse [17]AudioIndividualJust in timeDetecting the symptoms of COVID-19 from crowd-sourced sound data
Laguarta et al. [18]AudioIndividualJust in timeDetecting asymptomatic COVID-19 from cough recording data
Xia et al. [19]AudioIndividualJust in timeDetecting respiratory and COVID-19 symptoms from crowd-sourced sound data
Han et al. [20]AudioIndividualJust in timeDetecting COVID-19 from the combination of self-reported symptoms and sounds
Brown et al. [21]AudioIndividualJust in timeDetecting COVID-19 from multiple respiratory sound data
Han et al. [22]AudioIndividualJust in timeExploring the realism and societal bias of detecting COVID-19 from sound data
Ismail et al. [23]AudioIndividualJust in timeEvaluating the signatures of COVID-19 from the vibrations of the vocal folds
Orlandic et al. [24]AudioIndividualJust in timeEnabling large-scale COVID-19 screening based on cough recordings
Teo [25]PhysiologicalIndividualJust in timeDetecting COVID-19 using smartphone built-in pulse oximeters
Jouffroy et al. [26]PhysiologicalIndividualJust in timeDetecting COVID-19 from early abnormalities of silent hypoxemia
Al-zubidi et al. [27]PhysiologicalIndividualJust in timeUsing machine learning approaches to classify influenza and COVID-19
Mishra et al. [28]PhysiologicalIndividualDaysDetecting the presymptomatic COVID-19 from instant smartwatch data streams
Wong et al. [29]PhysiologicalIndividualDaysUsing wearable biosensors to monitor the physical condition for early detection
Gadaleta et al. [30]PhysiologicalIndividualDaysDetecting the onset of COVID-19 from wearable sensors and self-reported symptoms
Rao and Vazquez [31]Self-reportIndividualJust in timeDetecting COVID-19 using mobile-based self-reported web surveys