Using digital traces to build prospective and real-time county-level early warning systems to anticipate COVID-19 outbreaks in the United States (preprint)

The ongoing COVID-19 pandemic continues to affect communities around the world. To date, almost 6 million people have died as a consequence of COVID-19, and more than one-quarter of a billion people are estimated to have been infected worldwide. The design of appropriate and timely mitigation strategies to curb the effects of this and future disease outbreaks requires close monitoring of their spatio-temporal trajectories. We present machine learning methods to anticipate sharp increases in COVID-19 activity in US counties in real-time. Our methods leverage Internet-based digital traces -- e.g., disease-related Internet search activity from the general population and clinicians, disease-relevant Twitter micro-blogs, and outbreak trajectories from neighboring locations -- to monitor potential changes in population-level health trends. Motivated by the need for finer spatial-resolution epidemiological insights to improve local decision-making, we build upon previous retrospective research efforts originally conceived at the state level and in the early months of the pandemic. Our methods -- tested in real-time and in an out-of-sample manner on a subset of 97 counties distributed across the US -- frequently anticipated sharp increases in COVID-19 activity 1-6 weeks before the onset of local outbreaks (defined as the time when the effective reproduction number $R_t$ becomes larger than 1 consistently). Given the continued emergence of COVID-19 variants of concern -- such as the most recent one, Omicron -- and the fact that multiple countries have not had full access to vaccines, the framework we present, while conceived for the county-level in the US, could be helpful in countries where similar data sources are available.

Self-testing and vaccination against COVID-19 to minimize school closure (preprint)

Schools were largely closed in 2020-2021 to counter COVID-19 spread, impacting students education and well-being. With highly contagious variants expanding in Europe while vaccine hesitancy persists, safe options to maintain schools open are urgently needed. We developed an agent-based model of SARS-CoV-2 transmission in school. We used empirical contact data measured in a primary and a secondary school in France, and field estimates for adherence to screening from 683 schools during the spring 2021 wave. Examining different screening protocols, we performed a cost-benefit analysis for varying epidemic conditions and vaccination scenarios. In a partially immunized school population, weekly screening would reduce the number of cases on average by 24% in the primary and 53% in the secondary school compared to symptom-based testing alone, if R=1.3 and 50% adhered to screening. This adherence was met in primary schools (53% (95% confidence interval 21-85%)), but insufficient participation was recorded in secondary schools (10% (1-38%) in middle schools, 6% (2-12%) in high schools). Regular screening would also reduce by 90% the number of student-days lost compared to reactive class closure. No difference was predicted when fully vaccinating teachers, due to their limited number and mixing. Partially vaccinating adolescents would still require regular screening for additional control (20% case reduction with 50% vaccinated students). In the upcoming fall, COVID-19 epidemic will likely continue to pose a risk to the safe opening of schools. Increasing vaccination coverage in adolescents and implementing regular testing while largely incentivizing adherence are essential steps to keep schools open.

A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models (preprint)

We present a timely and novel methodology that combines disease estimates from mechanistic models with digital traces, via interpretable machine-learning methodologies, to reliably forecast COVID-19 activity in Chinese provinces in real-time. Specifically, our method is able to produce stable and accurate forecasts 2 days ahead of current time, and uses as inputs (a) official health reports from Chinese Center Disease for Control and Prevention (China CDC), (b) COVID-19-related internet search activity from Baidu, (c) news media activity reported by Media Cloud, and (d) daily forecasts of COVID-19 activity from GLEAM, an agent-based mechanistic model. Our machine-learning methodology uses a clustering technique that enables the exploitation of geo-spatial synchronicities of COVID-19 activity across Chinese provinces, and a data augmentation technique to deal with the small number of historical disease activity observations, characteristic of emerging outbreaks. Our model's predictive power outperforms a collection of baseline models in 27 out of the 32 Chinese provinces, and could be easily extended to other geographies currently affected by the COVID-19 outbreak to help decision makers.

The Role of Environmental Factors on Transmission Rates of the COVID-19 Outbreak: An Initial Assessment in Two Spatial Scales. (preprint)

A novel coronavirus (SARS-CoV-2) was identified in Wuhan, Hubei Province, China, in December 2019 and has caused over 240,000 cases of COVID-19 worldwide as of March 19, 2020. Previous studies have supported an epidemiological hypothesis that cold and dry environments facilitate the survival and spread of droplet-mediated viral diseases, and warm and humid environments see attenuated viral transmission (e.g., influenza). However, the role of temperature and humidity in transmission of COVID-19 has not yet been established. Here, we examine the spatial variability of the basic reproductive numbers of COVID-19 across provinces and cities in China and show that environmental variables alone cannot explain this variability. Our findings suggest that changes in weather alone (i.e., increase of temperature and humidity as spring and summer months arrive in the Northern Hemisphere) will not necessarily lead to declines in case count without the implementation of extensive public health interventions.

The role of absolute humidity on transmission rates of the COVID-19 outbreak (preprint)

A novel coronavirus (COVID-19) was identified in Wuhan, Hubei Province, China, in December 2019 and has caused over 40,000 cases worldwide to date. Previous studies have supported an epidemiological hypothesis that cold and dry (low absolute humidity) environments facilitate the survival and spread of droplet-mediated viral diseases, and warm and humid (high absolute humidity) environments see attenuated viral transmission (i.e., influenza). However, the role of absolute humidity in transmission of COVID-19 has not yet been established. Here, we examine province-level variability of the basic reproductive numbers of COVID-19 across China and find that changes in weather alone (i.e., increase of temperature and humidity as spring and summer months arrive in the North Hemisphere) will not necessarily lead to declines in COVID-19 case counts without the implementation of extensive public health interventions.