What do you get when you cross machine learning and standard epidemiology with the latest data on the spread of the coronavirus?

According to a team of MIT researchers, you get a means of determining the efficacy of current quarantine measures while also being able to predict how the virus will or will not spread.

As a recent article at MIT News explains the technique, “(m)ost models used to predict the spread of a disease follow what is known as the SEIR model, which groups people into ‘susceptible,’ ‘exposed,’ ‘infected,’ and ‘recovered.’”

For this project, MIT’s Raj Dandekar, a PhD candidate studying civil and environmental engineering, and George Barbastathis, professor of mechanical engineering, 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.

What they found, the article says, is that places like South Korea, where the government was quick to implement strong quarantine measures, saw the virus spread plateau more quickly. Conversely, they say, “in places that were slower to implement government interventions, like Italy and the United States, the ‘effective reproduction number’ of Covid-19 remains greater than one, meaning the virus has continued to spread exponentially.”

Moreover, the algorithm shows that with the current quarantine measures in place, the plateau for both Italy and the United States should have arrived somewhere between April 15-20, a prediction similar to other projections like that of the Institute for Health Metrics and Evaluation.

“Our model shows that quarantine restrictions are successful in getting the effective reproduction number from larger than one to smaller than one,” said Barbastathis. “That corresponds to the point where we can flatten the curve and start seeing fewer infections.”

For the project, Dandekar and Barbastathis modeled the spread of the virus in Wuhan, China, Italy, South Korea and the United States after the 500th case was recorded in each area. 

Using the data from each of country, the team “took the standard SEIR model and augmented it with a neural network that learns how infected individuals under quarantine impact the rate of infection. They trained the neural network through 500 iterations so it could then teach itself how to predict patterns in the infection spread.”

With this model, they were able to draw a direct correlation between quarantine measures and a reduction in the effective reproduction number of the virus.

“The neural network is learning what we are calling the ‘quarantine control strength function,’” explained Dandekar. 

Looking ahead, the algorithm suggest that the infection count will reach 600,000 in the United States before the rate of infection starts to stagnate.

“This is a really crucial moment of time,” said Barbastathis, noting relaxing quarantine measure too soon could resurgence of the virus, as appears to have happened in Singapore.