Real-time detection of COVID-19 epicenters within the United States using a network of smart thermometers

Abstract

Containing outbreaks of infectious disease requires rapid identification of transmission hotspots, as the COVID-19 pandemic demonstrates. Focusing limited public health resources on transmission hotspots can contain spread, thus reducing morbidity and mortality, but rapid data on community-level disease dynamics is often unavailable. Here, we demonstrate an approach to identify anomalously elevated levels of influenza-like illness (ILI) in real-time, at the scale of US counties. Leveraging data from a geospatial network of thermometers encompassing more than one million users across the US, we identify anomalies by generating accurate, county-specific forecasts of seasonal ILI from a point prior to a potential outbreak and comparing real-time data to these expectations. Anomalies are strongly correlated with COVID-19 case counts and may provide an early-warning system to locate outbreak epicenters.

The Affordable Care Act and the COVID-19 Pandemic: A Regression Discontinuity Analysis

“…5 To disentangle these two explanations, we turn to data on fever readings from smart thermometers distributed by Kinsa, Inc. We use two variables in our analysis: the percent of active users reporting feverish readings ("percent ill") and the number of active users (individuals who have used their thermometer over the course of the past year). The former variable is our proxy for the true intensity of Covid-19, as fever is a common symptom of the disease, and as Kinsa has provided evidence that its data are predictive of Covid-19 outbreaks (Chamberlain et al 2020). The latter variable allows us to check that the distribution of thermometers is continuous across the Medicaid expansion boundary, and therefore, that there should not be di¤erences in thermometer usage by individuals on di¤erent sides of the boundary apart from di¤erential prevailing rates of fever-inducing illnesses such as Covid-19.…”

Internet of Things for Current COVID-19 and Future Pandemics: an Exploratory Study

“…Although the privacy of data is still a significant issue for expanding these devices, it is predicted that healthcare providers will spend $20 billion annually until 2023 on wearable IoT devices to monitor more patients [30]. IoT wearable devices cover a wide range of different smart wearable tools such as Smart Themormeters [31,32], Smart Helmets [33], Smart Glasses [34], IoT-Q-Band [35], EasyBand [36], and Proximity Trace [37]. Table 2 shows all wearable devices regarding their classification with examples.…”

“…Also, since the use of infrared thermometers for capturing body temperature can possibly spread the virus more due to the closeness of patients and healthcare providers, using smart thermometers is highly recommended [42]. According to [82], Kinsa's thermometers have been widely used in homes, and the producer is now able to predict the most suspicious areas (contaminated with COVID-19) in each state of the USA based on the recorded temperature of people [31,[83][84][85]. Other smart thermometers such as Tempdrop, Ran's Night, iFever, and iSense (shown in Fig.…”

Contact tracing apps for the COVID-19 pandemic: a systematic literature review of challenges and future directions for neo-liberal societies

“…Based on the outcome of this SLR and our findings, we present the following future considerations and directions for contact tracing apps and related technologies in the fight against COVID-19 and future pandemic outbreaks that are worth investigating and implementing to encourage willingness and mass adoption by the wider population: Adopting less-invasive and privacy-preserving technologies— For future considerations, the use of less-invasive technologies such as Artificial Intelligence (AI) and Machine Learning (ML) has been proposed to help analyse the level of infection by the SARS-CoV-2 virus by identifying hotspots, tracing, and monitoring infected persons as described in primary studies [ 42 , 78 , 102 – 109 ]. Other methods described in the primary study [ 110 , 111 ], propose the use of thermal-based imaging using the Internet of Medical Things (IoMT) and other Internet of Things (IoT) devices [ 112 , 113 ] to trace and track positive cases and help control the spread of COVID-19 infection and future infectious disease outbreaks. The use of a privacy-preserving contact tracing scheme in blockchain-based medical applications has also been proposed [ 114 , 115 ].…”