In DepthCOVID-19

AI systems aim to sniff out coronavirus outbreaks

See allHide authors and affiliations

Science  22 May 2020:
Vol. 368, Issue 6493, pp. 810-811
DOI: 10.1126/science.368.6493.810


The international alarm about the COVID-19 pandemic was sounded first not by a human, but by a computer program called HealthMap that uses artificial intelligence (AI) to scan social media, news reports, internet search queries, and other data for signs of disease outbreaks. Humans weren't far behind. Within 1 hour, an epidemiologist in New York City had independently issued a more detailed alert. But the early alarm underscores the potential of AI, or machine learning, to keep watch for contagion. As the COVID-19 pandemic continues to spread, AI researchers are teaming with tech companies to build automated systems that will mine social media, news reports, and public health data for signs of outbreaks and assess the current state of an epidemic—so-called now-casting. Those efforts cannot replace traditional health measures such as testing for the virus, epidemiologists caution, but they might help policymakers better deploy their precious health care resources.

View Full Text

Stay Connected to Science