Self organising maps for the investigation of clinical data: A case study

Abstract

The clinical process often involves comparisons of how one set of measurements is related to previous, similar, data and the use of this information to take decisions concerning possible courses of action, often with insufficient data to make meaningful calculations of probabilities. Self-organising maps are useful devices for data visualisation. To illustrate how visualisation with self-organising maps might be used in the clinical process, this paper describes the investigation of an osteoporosis data set using this technique. The data set had previously been used to show that backpropagation neural networks were capable of distinguishing between patients who had suffered a fracture, and those who had not using measured bone mineral density values; illustrating the power of these networks to model relationships in data. However, we had realised that this was somewhat of an academic exercise given that in reality a non-fracture case might be a fracture case waiting to happen. We felt it would be more productive to examine the data itself rather than model an imposed classification. As part of this investigation, the data set was examined using self-organising maps. From the results of the investigation, we conclude that it is possible to create a map, a compressed data representation, using BMD values which may then be partitioned into low and high fracture risk areas. Using such a map may be a useful screening mechanism for detecting people at risk of osteoporotic fracture.