Neuroempiricism describes a strategy to store and process data analogous to the human brain and to derive an adaptive representation by modelling the biological processes. Technical systems often copy biological evolutionary “developments” from nature. The neuroempirical principle is an approach to realise features of biological information processing for technical approaches or solutions.

It is a challenge to model spatial problems in healthcare like the dissemination of a viral infection. The characteristics of the infection are changing in time and often further complicated by unpredictable events such as mutation of the virus. These factors have to be accounted for in the computer based framework of the model. Artificial Neural Networks (ANN) can be used as a mathematical and informatics module embedded in a Decision Support System for risk assessment and the distribution of related medical services. This article describes the application of Neuroempiricism for modelling complex dynamic systems in healthcare informatics which results in a new extended network typology derived from a biological network. The new model extends directed weighted graphs to a topological non-equivalent network model that is able to represent biological axo-axonal junctions. The new network topology creates a data structure for computational decision support concepts. The Biological Neural Network (BNN) provides an extension of the ANN so that both fuzzy and crisp data can be processed in a unified network typology.