This figure shows the model prediction of the infected case
count for the United States following its current model with
quarantine control and the exponential explosion in the infected
case count if the quarantine measures were relaxed. On the other
hand, switching to stronger quarantine measures as implemented in
Wuhan, Italy, and South Korea might lead to a plateau in the
infected case count sooner. Image courtesy of the researchers.
A machine learning algorithm combines data on the disease’s
spread with a neural network, to help predict when infections will
slow down in each country.
The research described in this article has been published on a
preprint server but has not yet been peer-reviewed by scientific or
medical experts.
Every day for the past few weeks, charts and graphs plotting the
projected apex of Covid-19 infections have been splashed across
newspapers and cable news. Many of these models have been built
using data from studies on previous outbreaks like SARS or MERS.
Now, a team of engineers at MIT hasdeveloped
a modelthat uses data from the Covid-19 pandemic in
conjunction with a neural network to determine the efficacy of
quarantine measures and better predict the spread of the virus.
“Our model is the first which uses data from the
coronavirus itself and integrates two fields: machine learning and
standard epidemiology,†explains Raj Dandekar, a PhD candidate
studying civil and environmental engineering. Together with George
Barbastathis, professor of mechanical engineering, Dandekar has
spent the past few months developing the model as part of the final
project in class 2.168 (Learning Machines).
Most models used to predict the spread of a disease follow what
is known as the SEIR model, which groups people into
“susceptible,†“exposed,†“infected,â€Â
and “recovered.†Dandekar and Barbastathis enhanced the
SEIR model by training a neural network to capture the number of
infected individuals who are under quarantine, and therefore no
longer spreading the infection to others.
Mary Beth Gallagher | Department of Mechanical Engineering
April 16, 2020
MIT News