Newswise — The onset of the COVID-19 pandemic in March 2020 forced governments around the world to take action to prevent its spread among the population and thereby reduce the death toll from the virus. A few months later, as mobility restrictions and lockdowns were gradually lifted, states moved to launch tracking apps that citizens could download to their cellphones to find out if nearby contacts were infected with COVID. However, for these apps to be truly effective, they require a large number of people to install them on their devices, and they also involve certain privacy risks.
Today, an IMDEA Networks research team led by Elisa Cabana (postdoctoral researcher) and Nikolaos Laoutaris (research professor), in collaboration with Andra Lutu (Teléfonica Research) and Enrique Frías-Martínez (Camilo José Cela University), conducted a study in which they propose a method that uses mobile network data to detect possible hospitalizations due to COVID-19 and obtain the corresponding epidemic risk maps. The paper “Improving epidemic risk maps using mobility information from mobile network data” will be published at the ACM SIGSPATIAL conference in November 2022.
Cabana explains that the main advantage of the proposed solution is that, unlike Contact Tracing, “the data is already available at the operator and the progress is faster. You do not need to activate the GPS and download a application”. “When you have mobile data connected, your device connects to a cell tower that identifies your location radius. And that’s how you study spatiotemporal mobility of people,” she adds. Another advantage is that the method works with anonymized data and can be performed at the operator’s premises under its standard security arrangements.
According to Laoutaris, the method works like this: “You check the location of a phone late at night and if it’s not connected to the usual cell towers it was connected to in pre-pandemic times, you see if it was connected to a tower near a hospital that receives COVID patients. If so, the person with the cell phone is tagged as potentially hospitalized. The method also includes filters to eliminate false positives , such as people who live near or work in hospitals.
As shown in their study, data from mobile networks can be exploited to understand the dynamics of urban mobility and its impact on the spread of contagious diseases like cholera, and also to predict the risk of viruses like dengue, Zika or malaria, or other new ones that may emerge in the future.
The team applied their methods to an anonymised dataset of more than 2 million cell phones, collected by a mobile network provider located in London, UK, during the months of March and April 2020. They have concluded that this method gives 98.6% agreement. with public records of patients admitted to National Health Service (NHS) hospitals.
Phases of the data collection process
In a first phase, the research group describes the algorithm for detecting possible COVID hospitalizations from mobile network data, as well as the parameters involved. The second phase consists of validating these data by checking the cases reported by London hospitals to the National Health Service and comparing them with those obtained with the proposed method. Finally, in a third phase, they analyze the mobility profile of each person detected as hospitalized during the two weeks preceding their day of hospitalization. With this information, they obtain dynamic and detailed risk maps that evolve over time and thus more accurately capture the distribution, evolution and intensity of the disease.
Compared to census-based maps, their risk maps indicate that the areas most at risk are not necessarily the most densely populated and can change from day to day. Additionally, they observed that hospitalized people tend to have higher average mobility than non-hospitalized people.
Elisa Cabana points out that the most relevant result of her research is precisely the risk maps, since they not only allow visual analysis of the evolution of an epidemic, but can also be very beneficial for different sectors of society. “At the individual level, representing each area with a more or less intense color, which can vary over time, depending on a measure of risk, is useful because it can help people take additional protective measures, at each time and place. For emergency teams and decision-makers, it would help assess the level of stress in the healthcare system, as well as the severity and intensity of the spread, and the advantages or disadvantages of certain decisions (use of masks, quarantine, vaccination). “, she concludes.
E. Cabana, A. Lutu, E. Frias-Martinez, N. Laoutaris, “Improvement of epidemic risk maps using mobility information from mobile network data”, ACM SIGSPATIAL’22.(Extended summary, full versionat the SpatialEpi’22 workshop).