Deploying an Artificial Intelligence System for COVID-19 Testing at the Greek Border

Hamsa Bastani, Kimon Drakopoulos, Vishal Gupta

Abstract:

On July 1st, 2020, members of the European Union gradually lifted earlier COVID-19 restrictions on non-essential travel. In response, we designed and deployed “EVA” – a novel, self-learning artificial intelligence system – across all Greek borders to identify asymptomatic travelers infected with SARS-CoV-2 based on demographic characteristics and results from previously tested travelers. EVA allocates Greece’s limited testing resources to (i) limit the importation of new cases and (ii) provide real-time estimates of COVID-19 prevalence to inform border policies.

Counterfactual analysis shows that our system identified on average 1.85x as many asymptomatic, infected travelers as random surveillance testing, and up to 2-4x as many during peak travel. Moreover, for most countries, EVA identified atypically high prevalence 9-days earlier than machine learning systems based on publicly reported data. By adaptively adjusting border policies 9-days earlier, EVA prevented additional infected travelers from arriving.

Finally, using EVA’s unique cross-country, large-scale dataset on prevalence in asymptomatic populations, we show that commonly used public data on cases/deaths/testing have limited predictive value for the prevalence among asymptomatic travelers, and furthermore exhibit strong country-specific idiosyncrasies. As herd immunity is still likely more than a year away [1], and travel protocols for the summer of 2021 are still being discussed, our insights raise serious concerns about internationally proposed border control policies [2] that are both country-agnostic and solely based on public data. Instead, our work paves the way for leveraging AI and real-time data for public health goals, such as border control during a pandemic.