AWS releases Simulator and Machine Learning Toolkit for Predicting COVID-19 Spread

Amazon Web Services (AWS) ,the world famous on-demand cloud computing platform recently published a new simulator and machine learning toolkit to anticipate and mitigate the spread of COVID-19. This toolkit is comprised of a disease progression simulator and several machine learning (ML) models to test the impact of various intervention strategies to accurately capture many of the complexities of the virus in the world.
There have been a number of breakthroughs in understanding COVID-19, such as how soon an exposed person will develop symptoms and how many people on average will contract the disease after contact with an exposed individual. Researchers around the world currently develop epidemiology models and simulators using available datasets from agencies and institutions, as well as historical data from similar diseases such as influenza, SARS and MERS.
As COVID-19 remains a relatively unknown disease, plenty of challenges are emerging when building these kinds of models. Learning parameters that influence variations in disease which spread across multiple countries or populations, being able to combine various intervention strategies (such as school closures and stay-at-home orders) are crucial challenges. Also, with no historic data about COVID-19, researchers face numerous what-if scenarios by incorporating trends from diseases similar to COVID-19.
First, the machine learning models in AWS’ suite bootstrap the system by estimating the disease progression and comparing the outcomes to historical data. Next, the data scientists can run the simulator with learned (using supervised learning) parameters to play out what-if scenarios for various interventions and use templates for the state level in the U.S., India, and countries in Europe.
aws suit_01
Image from aws blogs
AWS’ suite provides several notebooks in their open-source toolset to run what-if scenarios at the state level in the US, India, and countries in Europe. The suit uses Delphi Epidata API from Carnegie Mellon University to access various datasets, including but not limited to the Johns Hopkins Center for Systems Science and Engineering, survey trends from Google search and Facebook, and historical data for H1N1 from 2009 to 2010.
AWS’ simulator can assign a probability distribution to disease variables for each individual parameterized by a mean, standard deviation, and lower and upper limits.
“For example, you can set parameters such as individuals will develop symptoms within 2–5 days after exposure, with the majority of the population developing symptoms in 2–3 days. Similarly, you can set parameters for the recovery period, such as within 14–21 days after exposure. The stochasticity allows for variation in the population at the individual level to mimic real-world scenarios.”  AWS explains in a blog post.
Image from aws blogs
AWS suit uses finite state machine to model the disease progression for each individual in a population. This finite state machine is similar to the simulation model in COVID-19 Projections Using Machine Learning, with additional states for infection transmission by asymptomatic individuals. The default state machine is extensible in the sense that you can add any disease progression state to the model as long as the state transitions are well-defined from and to the new state. For example, users can add a state for having tested positive.
This disease simulation can also capture population dynamics. The transition from one state to the next for an individual is influenced by the states of the others in the population. For example, a person transitions from a “Susceptible” to “Exposed” state based on factors such as whether the person is vulnerable due to pre-exiting health issues or interventions such as social distancing.

“Our solution first tries to understand the approximate time to peak and expected case rates of the daily COVID-19 cases for the target entity (state/country) by analysis of the disease incidence patterns. Next, it selects the best (optimal) parameters using optimization techniques on a simulation model. Finally, it generates the projections of daily and cumulative confirmed cases, starting from the beginning of the outbreak until a specified length of time in the future.” said AWS in their blog post.

To get started, AWS has provided a few sample simulations at state and country levels in the covid19_simulator.ipynb notebook in https://github.com/aws-samples/covid19-simulation which you can run on Amazon SageMaker or a local environment.

Rising Invation Batteries …..Read more>>


Leave a Reply

Your email address will not be published. Required fields are marked *