Meta-Analysis of the Accuracy of Syndromic Surveillance

TL;DR

This paper conducts a meta-analysis of digital disease surveillance research over the past decade, highlighting how co-evolutionary learning networks and social media analytics have improved accuracy and methodological approaches.

Contribution

It provides the first comprehensive meta-analysis of co-evolutionary learning networks in digital disease surveillance, illustrating their development and impact over ten years.

Findings

Incorporation of social media analytics enhances surveillance accuracy.

Co-evolutionary learning networks demonstrate adaptive improvements.

Feedback loops improve system reliability and validity.

Abstract

We present the first meta-analysis of co-evolutionary learning networks for digital disease surveillance research over last 10 years. In doing so, we show the co-evolution and dynamical changes that occurred in academic research related to digital disease surveillance for improving accuracy, approach and results. Using dynamic network analysis, we are able to show the incorporation of social media-based analytics and algorithms which have been proposed and later improved by other researchers as co-evolutionary learning networks. This essentially demonstrates how we improve our research and increase accuracy through feedback loop for correcting the behaviour of an open system and perhaps infer learning patterns, reliability and validity using 10 years scientific research in digital disease surveillance.