AI to assess the effectiveness of health policies

September 23, 2022

A few months after the emergence of a new coronavirus on the side of China, the whole world hopes for a treatment or a vaccine which will make it possible to fight against the pandemic of Covid-19. In the meantime, only health policies seem able to limit the spread of SARS-CoV-2. It is still necessary to be able to assess its effectiveness. This is the objective of a partnership between the Development Research Institute (IRD) and EDF R&D: modeling the impact of such policies at the local level.

Game Of Thrones, World War Z or the mythical Lord of the Rings. What these film productions have in common is the use of "Synthetic crowds". Animations carried out on computer, but which faithfully reproduce the reality of crowd phenomena. "This is an example of what multi-agent systems (SMA) can bring", explains Mathieu Schumann, engineer in EDF R&D. This branch ofartificial intelligence aims to reproduce the behavior of a set of agents – processes, robots or even human beings -, evolving in a certain environment, interacting with each other.

Many disciplines also exploit these technologies. So theenergy or telecommunications. And it is these ADMs that are today at the heart of a partnership concluded between EDF R&D and the Research Institute for Development (IRD). The two entities have agreed to combine their research resources to meet the challenges of fight the Covid-19 and provide local decision makers with a decision support tool in this unprecedented crisis situation. Whereas the classical epidemiology models make it possible to give a projection into the evolution of population compartments (compartments of the infected, cured, deceased, etc.), the use of modeling multi-agents makes it possible to take into account the heterogeneity of the population and the characteristics of individuals (age, occupations, etc.), on several territorial scales.

EDF and the Research Institute for Development (IRD) have decided to combine their research resources to meet the challenges of the fight against Covid-19. © EDF

“For almost 15 years, EDF's R&D has been developing skills in these multi-agent systems. This is how we develop solutions to simulate the daily life of people in the health home, a bit like in the video game The Sims, to better anticipate energy consumption ”, says Mathieu Schumann. But here, it is the IRD – and more precisely its Ummisco research unit based in Vietnam – which has developed with its partners a model allowing – in connection with epidemiological models – to assess the risks of spread of coronavirus locally.

Remember that the IRD is a reference in matter agent-based modeling. For fifteen years already, he has been developing a software suite open source modeling and simulation called GAMA Platform®. And from the start of the coronavirus crisis, the Institute designed, on this platform, a disease spread simulator and evaluation of health policies called COMOKIT – for Covid-19 Modeling Kit.

A first simulation of a model aimed at supporting the decisions of local authorities concerning the containment measures to be adopted when a municipality is affected by the Covid-19. © GAMA Platform®

The power of high performance computing

Among the input data of this simulator: statistical data such as the number of houses in the locality studied, the number of inhabitants per foyer, the age distribution of these inhabitants or the distribution of the working population. "All available information that can help generate a virtual population representative of the real population", explains Mathieu Schumann. "Then they are avatars digital which are modeled to run the simulation. We do not use any personal data. "

To obtain results quickly – in the coming days or weeks – the simulator uses the computing power available to EDF R&D. More specifically, the High Performance computer GAIA (40,000 computation cores 3,2 PFlops) which allows to launch calculations in parallel on many processors to simulate the interactions of thousands of agents. An essential asset for exploring a large set of parameters in a very short time. Which is of course sought in the context of the crisis we are experiencing.

The COMOKIT simulator was designed as a generic simulator, which can be adapted to any case of study. It will make it possible to explore multiple scenarios and thus define the most suitable containment perimeter, the impact of school closings, the duration most effective containment or the most effective measures to implement.

A Review phase is underway in Vietnam. The objective is to extend these simulations to other countries such as Cameroon or Senegal where the IRD is also present. And contacts have already been made with French communities which could be interested in these simulation models.

Subject realized in collaboration with EDF

This will also interest you

Coronavirus: can we delay a second wave of the epidemic? France is at the beginning of its confinement while in China, life gradually returns to normal. But the country must now anticipate a second wave of the coronavirus epidemic. An English study has simulated several deconfinement scenarios to limit this second wave. Can we delay its arrival? Video response!