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.
Similar content being viewed by others
References
Parkkari J, Kannus P, Niemi S et al. Increasing age-adjusted incidence of hip fractures in Finland: The number and incidence of fractures in 1970–1991 and prediction for the future. Calcif Tissue Int 1994; 55: 342–345
Obrant K. Increasing age-adjusted risk of fragility fractures: A sign of increasing osteoporosis in successive generations? Calcif Tissue Int 1989; 44: 157–167
Cooper C, Campion G, Melton LJ III. Hip fractures in the elderly: a worldwide projection. Osteoporosis Int 1992; 2: 285–289
Schneider EL, Guralnik JM. The aging of America: impact on health care costs. JAMA 1990; 263: 2335–2340
Melton LJ III, O'Fallon WM, Riggs BL. Secular trends in the incidence of hip fractures. Calcif Tissue Int 1987; 41: 57–64
Randell A, Sambrook PN, Nguyen TV et al. Direct clinical and welfare costs of osteoporotic fractures in elderly men and women. Osteoporosis Int 1995; 5: 427–432
Johnston CC, Melton LJ III. Bone densitometry. Osteoporosis: Etiology, Diagnosis and Management, 2nd edn. Riggs BL, Melton LJ III (eds.). Lippincott-Raven, 1995; 275–297
Cross SS, Harrison RF, Kennedy RL. Introduction to neural networks. Lancet 1995; 346: 1075–1079
World Health Organisation. Assessment of fracture risk and its application to screening for postmenopausal osteoporosis. WHO Technical Report Series 843, 1994
Kohonen T. Self-Organization and Associative Memory, 3rd edn. Springer-Verlag, 1989
Kohonen T. The Self-Organizing Map. Proc IEEE 1990; 78(9): 1464–1480
Kohonen T. Self-Organizing maps (Springer Series in Information Sciences, Vol 30). Springer-Verlag, 1995
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sharpe, P.K., Caleb, P. Self organising maps for the investigation of clinical data: A case study. Neural Comput & Applic 7, 65–70 (1998). https://doi.org/10.1007/BF01413710
Issue Date:
DOI: https://doi.org/10.1007/BF01413710