Prof. Dr. Paul Lukowicz, head of the Research Department Embedded Intelligence at DFKI: "Artificial intelligence can not only help to detect the outbreak and spread of epidemics at an early stage through pattern recognition, but can also contribute to efficient control. The underlying data are crucial for this. The fact that this data can be collected with due consideration for data protection and made available for crisis management has been researched in groundbreaking EU research projects and proven in many years of practical use.
The system essentially comprises the following core components:
- The recording of health and analysis parameters
Health parameters that users voluntarily provide can be anonymised, aggregated and used to represent or analyse the exact spatial distribution of an infection. The parameters to be queried are defined by leading European epidemiologists of the influenza monitoring network "lnfluenzaNet" and can be adapted to the current situation of the users over time in order to always collect relevant data. These are not associated with personal data.
The experience in this respect comes, among other things, from the EU-funded research project CIMPLEX. In this various tools were developed under the direction of DFKI to investigate and influence the spread of disease and other infection phenomena in complex social systems.
- Decentralized, anonymous contact tracing
By means of so-called "Bluetooth Handshakes" an anonymous contact tracing is realized without sending data to a server. The privacy of the user is thus always protected. This technology forms an important basis for the interruption of infection chains by warning users in good time if they have been in contact with a positively diagnosed person.
As an early adopter, the consortium is in the process of adapting the system to the European PEPP-PT contact tracing standard which is currently under development. This standard aims at a decentralized, anonymous and logbook-based contact tracing, which is in full compliance with the Data Protection Ordinance (DSGVO). It also ensures international compatibility so that chains of infection can be traced across national borders.
- Targeted communication
Messages and notices can be sent location-specific, as so-called "location-based messages". These are only received in certain geographical areas. The shape and size of the message target areas can be selected as desired: From single blocks of houses, public places up to complete countries, every scenario is possible. In the context of a pandemic, the population can thus be provided with targeted information and tips – nationwide, locally by regional administrations or by event organizers. In this way, users can be specifically notified if there are particular risks of infection in certain areas.
- Optional anonymised analysis of mobility patterns
The crowd sensing technology was developed within the framework of the EU research project SOCIONICAL, in which 14 European universities and research centres investigated the interplay of technology and social interaction. It was originally developed and used to analyze the behavior of crowd movements at major events and to prevent catastrophes, such as the 2010 Love Parade in Duisburg. These analyses are based on anonymous, aggregated movement data sent with the consent of smartphone users.
At major events such as the 2012 Olympic Games in London or Rock am Ring Festival, the technology has already been successfully used to prevent potential disasters. In a crisis, this technology can be used to analyse mobility patterns and draw conclusions about possible ways in which the epidemic could spread.
"With our system, we are aiming for a holistic platform for citizen participation, data analysis and official information, which combines the results of successful research projects and proven technologies. In the context of the current COVID 19 crisis, these can make an important contribution to combating the pandemic," says Dr. Tobias Franke, scientist in the Embedded Intelligence Research Department at the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern and founder of SIS Software GmbH. "The components can be used individually as well as integrated in combination with other features.
In addition to the DFKI spin-off SIS Software GmbH, founded in 2012, and the DFKI, the team includes the business consultancy PricewaterhouseCoopers (PwC), the concert promoter Eventim, the European influenza tracking network lnfluenzaNet, in which leading epidemiologists are organized, and the start-up Coneno.