DEFENDER: Detecting and Forecasting Epidemics using Novel Data-analytics for Enhanced Response

Abstract

In recent years social and news media have increasingly been used to explain patterns in disease activity and progression. Social media data, principally from the Twitter network, has been shown to correlate well with official disease case counts. This fact has been exploited to provide advance warning of outbreak detection, tracking of disease levels and the ability to predict the likelihood of individuals developing symptoms.In this paper we introduce DEFENDER, a software system that integrates data from social and news media and incorporates algorithms for outbreak detection, situational awareness, syndromic case tracking and forecasting. As part of this system we have developed a technique for creating a location network for any country or region based purely on Twitter data. We also present a disease count tracking approach which leverages counts from multiple symptoms, which was found to improve the tracking of diseases by 37 percent over a model that used only previous case data. Finally we attempt to forecast future levels of symptom activity based on observed user movement on Twitter, finding a moderate gain of 5 percent over a time series forecasting model.

Digital surveillance in Latin American diseases outbreaks: information extraction from a novel Spanish corpus

“…Optimizer: Stochastic Gradient Descent (SGD) and Adam [29], each one with different learning rates: [0.001, 0.05, 0.01, 0.1]. Mini batch size: [8,16,32]. Recurrent neuronal network layers: Embeddings: we analyzed seven different combinations of embeddings using the Spanish Billion Word Corpus (SBWC) 18 [30] and Wikipedia dumps (retrieved from the Flair library 19 ) through stacked embeddings.…”

“…Finally, examples of fully automated systems include the European Commission's Medical Information System (MedISys), 9 Pattern-based Understanding and Learning System (PULS), 10 SENTINEL, 11 DEFENDER [16] and the Global Rapid Identification Tool System (GRITS) [17]. 12 It is worth noting the Epidemic Intelligence from Open Sources (EIOS) initiative [17], a collaboration of WHO, the European Union, and several organizations, that pulls together many existing aggregator systems, as those aforementioned, with the aim to unify health approaches to digital surveillance from public sources.…”

“…This decision was taken based on the Gazetters' information 15. The thesis is written in Spanish 16. GeoNames WebServices.…”