Nice explainer from Georgia Tech about their re-opening model

Georgia Tech professors explain how they model school re-opening in this Youtube video. They did a great job simplifying the materials for a general audience.

You'll find that the Gatech model has the same stylized findings as the Cornell model. (However, these professors recommend starting the semester fully online, unlike the Cornell team.) I've already reviewed the key learnings in this prior post - the professors confirm the following:

1. It's super important to suppress imported cases at the start to the lowest possible through entry testing.
2. Then, they prescribe comprehensive testing to nip any community spread. (I've called for broad-based testing from the very start but CDC continues to not recommend it.) Cornell, unlike many other schools, also recognized that random samples are not enough. The Georgia Tech professors explain this nicely - they are using testing as a mitigation tool. (Sampling is a measurement tool.)
3. The testing needs to be extremely aggressive. The model concludes that everyone should be tested at least once a week. This is the same frequency as in the Cornell model.
4. Georgia Tech "cannot" mandate testing thus the comprehensive testing will be voluntary. Like Cornell, Georgia Tech has bottomless faith in its student body and larger community because based on some survey results, the professor said they expect "over 95 percent" compliance.
5. People testing positive will be isolated from the community.
6. They hope there will be close to 100% compliance on mask wearing.
7. Unlike Cornell, they are less invested in contact tracing. They hope that testing and isolation will be sufficient.

You can see that the results of this model - like any model - are based on a host of assumptions, many of which on human behavior. After a week or two of re-opening, the assumptions are already looking shaky. Commenters on Twitter are reporting testing compliance of less than 33% at Georgia Tech, and some Cornell students are said to have moved into dorms without having completed entry testing. (Note: these are unverified.)

As a fellow modeler, all I can say is: innocence lost!

***

There are a few new things I learned from the video:

1. These colleges are spending a fortune on testing, conducting thousands of tests per day, at roughly $10 a day. I get the sense that this price is possible only because Georgia Tech has academic staff with relevant skills, and if they must buy test kits from commercial vendors, the cost would be even higher.
   
   
2. They admit that the goal of testing once a week may not be feasible initially, and once every two weeks is more likely. They explain some of the regulatory and operational hurdles of getting the testing program up and running.
   
   
3. The current estimate for R0 has gone up to 3 (at least for the state of Georgia). This virus is highly contagious. They show that if the virus is allowed to spread through the community (i.e. what the herd immunity advocates want), there will be potentially dozens of deaths among faculty, staff and students.
   
   
4. A calculation of optimal class size shows how daunting it is to operate in-class instruction. In a classroom of 25 students, there is about 50 percent chance that at least one of them is infectious. (R0 of 3 means the first infectious person will transmit the virus to three others.)
   
   
5. For me, the gem of the slides was toward the end (at 43:57). They present recent evidence of pre-symptomatic transmission (work done by a team from UT Austin and others). Of course, we've been talking about silent transmission for a while (the latter part of this link) but somehow to this day, CDC continues to say that only people with symptoms should get tested. The evidence concerns a concept called "negative serial intervals". Imagine a transmission chain: person A transmits the virus to person B, who transmits it to person C. We can measure the time interval between A and B, and between B and C. A negative interval is when B gets sick before A does. This seems impossible.   But that's because we forget the pre-symptomatic carriers. Person A infects B while not showing symptoms; person B shows symptoms quickly after infection. Person A eventually develops symptoms. So the presence of negative serial intervals is proof of pre-symptomatic transmission. (The same dynamic describes asymptomatic transmission, except person A never exhibits symptoms, so without broad-based testing, person A would not be observed.)
   
   
6. Note that the above analysis is made possible by a robust testing and tracing program. If we don't know who's infected and we don't know with whom the infected have been in contact, we can't estimate the serial intervals. The data show person B getting sick before person A; to reverse this order, the researchers must have learned that A got infected first - for example, A attended a campus party, B has stayed in her off-campus apartment, except the one time she invited A over for a dinner.