From symptoms to syndromes: a new paper by an international scientific team on influenza-like illness web-based surveillance

The availability of novel data streams has recently led to the emergence of non-traditional approaches for ILI (influenza-like illness) surveillance. These new models can complement and alleviate the issues of the traditional practice for surveillance, that is usually carried out by sentinel general practitioners who compile weekly reports based on the number of ILI clinical cases observed among visited patients.

In Europe, a participatory web-based surveillance system called Influenzanet (now active in 10 countries) represents a powerful tool for monitoring seasonal influenza epidemics thanks to aid of self-selected volunteers from the general population who monitor and report their health status through Internet-based surveys, thus allowing a real-time estimate of the level of influenza circulating in the population.

In a new work, out in PLOS – Computational Biology, an international team of scientists, including ISI Foundation researchers Ciro Cattuto, Kyriaki Kalimeri, Yamir Moreno, Daniela Paolotti and Daniela Perrotta, proposes an unsupervised probabilistic framework that combines time series analysis of self-reported symptoms collected by the Influenzanet platforms and performs an algorithmic detection of groups of symptoms, called syndromes. The aim of this study, that refers to data collected over six influenza seasons (from 2011-2012 to 2016-2017), is to show that participatory web-based surveillance systems are capable of detecting the temporal trends of influenza-like illness even without relying on a specific case definition, just basing on the available information of the previous years.

Unsupervised extraction of epidemic syndromes from participatory influenza surveillance self-reported symptoms”, Kyriaki Kalimeri, Matteo Delfino, Ciro Cattuto, Daniela Perrotta, Vittoria Colizza, Caroline Guerrisi, Clement Turbelin, Jim Duggan, John Edmunds, Chinelo Obi, Richard Pebody, Ana O. Franco, Yamir Moreno, Sandro Meloni, Carl Koppeschaar, Charlotte Kjelsø, Ricardo Mexia, Daniela Paolotti. PLOS – Computational Biology, April 8th, 2019. Link