Data from a plurality of sensors representing a patient's condition, includingthe measurement signals and also secondary parameters derived from themeasurement signals, are displayed in a simple way by mapping them from themulti-dimensional measurement space to a two-dimensional visualisation space.This can be achieved using a mapping which preserves the topography of thedata points, for instance by ensuring that the inter-point distances in thevisualisation space match as closely as possible the corresponding inter-pointdistances in the measurement space. Such a mapping, for instance Sammon'smapping is achieved by a suitably trained artificial neural network. Theparameters are normalised before the mapping process and the normalisation andmapping are such that mapped points from a patient whose condition is normalappear in the centre of the visualisation space, whereas points from a patientwhose condition is abnormal appear at the edge of the visualisation space. Theartificial neural network may be trained using data points from a singlepatient or from a group of patients, and data may be thinned out using a pre-clustering algorithm.
