How can data and AI help us tackle contact research efficiently and effectively?

Contact research is seen as one of the most important interventions that contribute to curbing the spread of the coronavirus. This requires a huge human effort, which can be supported and relieved by reliable and effective technological support. Combining existing data sources can provide a faster and better understanding of outbreaks at local level, while at the same time protecting privacy. Technologies such as crowd computing can reduce the time a health professional spends on contact research. And insight into ‘dark data’ shows us what essential data we lack to conduct contact research in a reliable and efficient way.

Navigating the Transition Phase

The COVID-19 emergency put a spotlight on two core aspects of decision-making in times of emergency: the central role of data and the need for expert knowledge and judgment. During the containment phase, the government enforced policies like the intelligent lockdown based on the advice of epidemiologists and behavioural scientists. The advice was informed by data about reported infections, hospitalisations, and mortality; data that was often incomplete or reported with delays. This uncertainty heavily impaired the effectiveness of standard epidemiological models, so the sensibility and expertise of scientists played a key role, and interventions –like closing cinemas and hairdressers – were applied country-wide.

Using traffic and transport technology to support contact research

In the past decade, sensing in traffic and transport has taken a massive leap. Whether it is the use of chipcard data, floating car data, social data, surveys, GPS, Wifi, Bluetooth, 3D cameras, emotion detection, or Lidar, we have a far better picture of the operations in transportation systems. We believe that these data provide an important source of information for understanding, predicting and preventing the spreading of the coronavirus. This could be achieved via looking at travel patterns and locations where many people come together, or by using advanced sensing techniques to enhance the functionality of apps. In addition to data, we can use advanced simulation modelling to identify the impact of strategies on virus spreading in for example public transport, taxis or demand responsive transport.