Prognostic model for early warning of threatening influenza waves

Abstract

The goal of the TeCoMed project is to send early warnings against forthcoming waves or even epidemics of infectious diseases, especially of influenza to interested practitioners, pharmacists etc. in the German federal state of Mecklenburg-Western Pomerania. The forecast of these waves is based on written confirmations of unfitness for work of the main German health insurance company. Since influenza waves are difficult to predict because of their cyclic but no regular behaviour, statistical methods based on the computation of mean values are not helpful. Instead, we have developed a prognostic model that makes use of similar former courses. Our method combines Case-based Reasoning with Temporal Abstraction to decide wether early warning is appropriate. In this paper, we present this method.