{"id":478,"date":"2020-10-30T23:03:02","date_gmt":"2020-10-30T23:03:02","guid":{"rendered":"https:\/\/machine-learning.webcloning.com\/2020\/10\/30\/introducing-the-covid-19-simulator-and-machine-learning-toolkit-for-predicting-covid-19-spread\/"},"modified":"2020-10-30T23:03:02","modified_gmt":"2020-10-30T23:03:02","slug":"introducing-the-covid-19-simulator-and-machine-learning-toolkit-for-predicting-covid-19-spread","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2020\/10\/30\/introducing-the-covid-19-simulator-and-machine-learning-toolkit-for-predicting-covid-19-spread\/","title":{"rendered":"Introducing the COVID-19 Simulator and Machine Learning Toolkit for Predicting COVID-19 Spread"},"content":{"rendered":"
\n

There have been 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. The wider research community is actively working on accurately predicting the percent population who are exposed, recovered, or have built immunity. Researchers currently build epidemiology models and simulators using available data from agencies and institutions, as well as historical data from similar diseases such as influenza, SARS, and MERS. It\u2019s an uphill task for any model to accurately capture all the complexities of the real world. Challenges in building these models include learning parameters that influence variations in disease spread across multiple countries or populations, being able to combine various intervention strategies (such as school closures and stay-at-home orders), and running what-if scenarios by incorporating trends from diseases similar to COVID-19. COVID-19 remains a relatively unknown disease with no historic data to predict trends.<\/p>\n

We are now open-sourcing a toolset for researchers and data scientists to better model and understand the progression of COVID-19 in a given community over time. This toolset is comprised of a disease progression simulator and several machine learning (ML) models to test the impact of various interventions. First, the ML models help bootstrap the system by estimating the disease progression and comparing the outcomes to historical data. Next, you can run the simulator with learned parameters to play out what-if scenarios for various interventions. In the following diagram, we illustrate the interactions among the extensible building blocks in the toolset.<\/p>\n

\"\"<\/p>\n

In this post, we describe in detail how our disease simulation works, how simulation parameters are learned using supervised learning, and predict the incidence of disease given an intervention score.<\/p>\n

Historical trends for infectious diseases<\/h2>\n

We provide several notebooks in our open-source toolset to run what-if scenarios at the state level in the US, India, and countries in Europe. In these notebooks, we use various data sources that frequently publish the number of new cases. For example, for the US, we use the Delphi Epidata<\/a> API from Carnegie Mellon University (CMU) to access various datasets, including but not limited to the Johns Hopkins Center for Systems Science and Engineering (JHU-CSSE), survey trends from Google search and Facebook, and historical data for H1N1 in 2009\u20132010.<\/p>\n

We can use our notebook, covid19_data_exploration.ipynb<\/code>, to overlay historical data from previous pandemics with COVID-19. For example, the following graphs compare COVID-19 to seasonal flu and the H1N1 pandemic in California, Texas, and Illinois.<\/p>\n

The first graph shows the 7-day average of the number of incidences in California during seasonal flu, H1N1, and COVID-19.<\/p>\n

\"\"<\/p>\n

Although COVID-19 cases peaked in summer for most states in the US, there are exceptions. In Illinois, the most cases occurred early in the year, similar to the H1N1 peak in spring.<\/p>\n

\"\"<\/p>\n

On the other hand, in other states such as Texas, we observe a potential peak aligning with the H1N1 peak in fall.<\/p>\n

\"\"<\/p>\n

The trends differ greatly across states and countries. Therefore, we provide notebooks that enable you to run what-if scenarios by learning from existing data and projecting into the future using anticipated peaks.\u00a0<\/strong><\/p>\n

Results from running what-if scenarios<\/h2>\n

The notebook covid19_simulator.ipynb<\/code> has a comprehensive list of regions and countries across the world to run what-if scenarios. In this section, we discuss various what-if scenarios for France, Italy, the US, and Maharashtra, India. First, we use ML to predict the disease trends, including peaks and waves based on parameters specified by the user (for example, we use 3 months of COVID-19 case data to bootstrap and follow the H1N1 trend or create a second or third wave after 6 months from the first wave). Next, we play out intervention scenarios such as mild intervention or strict intervention and discuss the results.<\/p>\n

France<\/h3>\n

For France, we considered the what-if scenario of having a stricter intervention and a second wave in 6 months but with a higher peak than the first wave, as expected in H1N1-like trends. The following graphs compare the daily number of cases and cumulative number of cases. Our projection in this scenario (orange line) closely matches with the actual curve (blue line).<\/p>\n

\"\"<\/p>\n

Italy<\/h3>\n

For Italy, we consider the scenario of having a mild intervention policy versus a stricter intervention policy and a second wave in 6 months with a higher peak, as expected in H1N1-like trends. The first set of graphs shows the number of daily cases and total cases with a mild intervention policy.<\/p>\n

\"\"<\/p>\n

The following graphs compare daily and total case numbers with a stricter intervention policy.<\/p>\n

\"\"<\/p>\n

During the first wave, the milder intervention projection initially matches better, and stricter interventions result in a decline. Therefore, in this what-if scenario, we can see how our model captures varying interventions. However, although the trend with the second wave matches our predictions, using the assumption of a second wave in 6 months doesn\u2019t align with the new trend. Therefore, the best projection for Italy\u2019s what-if scenario should shift the second wave to where we usually expect H1N1 would have been\u2014specifically, in fall.<\/p>\n

US<\/h3>\n

For our US scenario, we considered having another wave in 3 months while keeping a stricter level of interventions. Overall, the US aligns better with stricter intervention scores based on the invention scoring mechanism provided by the Oxford Coronavirus Government Response Tracker<\/a>, which we use for all the examples in this post and notebook. In this what-if scenario, we start observing a trend for another wave that aligns with H1N1-like trends in fall.<\/p>\n

\"\"<\/p>\n

Maharashtra, India<\/h3>\n

Our Maharashtra, India, scenario considers having another wave in 6 months while keeping the same level of intervention policies. The graph on the left shows the actual (blue) and estimated (orange) number of cases. The graph the right is the cumulative number of cases. In this scenario, we can see the impact of experiencing a second wave is similar to the first one.<\/p>\n

\"\"<\/p>\n

Disease simulator<\/h2>\n

We model the disease progression for each individual in a population using a finite state machine, and then report out the aggregate state of the population. We assign a probability distribution to the disease parameters for each individual, parametrized by a mean, standard deviation, and lower and upper limits. For example, you can set parameters such as individuals will develop symptoms within 2\u20135 days after exposure, with the majority of the population developing symptoms in 2\u20133 days. Similarly, you can set parameters for the recovery period, such as within 14\u201321 days after exposure. The stochasticity allows for variation in the population at the individual level to mimic real-world scenarios.<\/p>\n

Our finite state machine is similar to the simulation model in COVID-19 Projections Using Machine Learning<\/a>, with additional states for infection transmission by asymptomatic individuals, as shown in the following diagram. 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, you can add the state for having tested positive.<\/p>\n

\"\"<\/p>\n

Our 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. Theoretically, our simulation model iterates each individual\u2019s state within an automata network [4]. The state transition probabilities are driven by two types of factors:<\/p>\n