Learning from Large-Scale Wearable Device Data for Predicting the Epidemic Trend of COVID-19

Abstract

The pandemics of COVID-19 triggered out an alarm on the public health surveillance. The popularity of wearable devices enables a new perspective for the precaution of the infectious diseases. In this study, we propose a framework, which is based on the heart rate and sleep data collected from the wearable devices, to predict the epidemic trend of COVID-19 in different countries and cities. On top of a physiological anomaly detection algorithm defined based on wearable device data, an online neural network prediction modelling methodology combining both detected physiological anomaly rate and historical COVID-19 infection rate is explored. 4 models are trained separately according to geographical segmentation, i.e., North China, Central China, South China, and South-Central Europe. The de-identified sensor data from about 1.3 million wearable device users are used for verification. Experiment results indicate that the prediction models can be utilized to alert the outbreak of COVID-19 in advance, which sheds light on a health surveillance system with wearable device.

Wearable sensor data and self-reported symptoms for COVID-19 detection

“…This work builds on our earlier retrospective analysis demonstrating the potential for consumer sensors to identify individuals with influenza-like illness, which has subsequently been replicated in a similar analysis of over 1.3 million wearable users in China for predicting COVID-19 8,9 . In response to the COVID-19 pandemic, a number of prospective studies, led by device manufacturers and/or academic institutions, including DETECT, have accelerated deployment to allow interested individuals to voluntarily share their sensor and clinical data to help address the global crisis [10][11][12][13][14] .…”

Pre-symptomatic detection of COVID-19 from smartwatch data

“…Wearable sensors have also been used to detect atrial fibrillation 6 . Other recent studies have shown that elevated heart rate measurements from smartwatches can be used in epidemiological studies to track the spread of respiratory viruses 7,8 .…”

Applications of artificial intelligence in battling against covid-19: A literature review

“…Wearable devices: In [400] , a framework is proposed that collects data about heart rate and sleep data collected from wearable devices to predict the pandemic trend. In this approach, an online neural network algorithm is proposed to build the required model.…”