The determination of three subcutaneous adipose tissue compartments in non-insulin-dependent diabetes mellitus women with artificial neural networks and factor analysis

The optical device LIPOMETER allows for non-invasive, quick, precise and sa fe determination of subcutaneous fat distribution, so-called subcutaneous a dipose tissue topography (SAT-Top). In this paper, we show how the high-dim ensional SAT-Top information of women with type-2 diabetes mellitus (non-in sulin-dependent diabetes mellitus (NIDDM)) and a healthy control group can be analysed and represented in low-dimensional plots by applying factor ana lysis and special artificial neural networks. Three top-down sorted subcuta neous adipose tissue compartments are determined (upper trunk, lower trunk, legs). NIDDM women provide significantly higher upper trunk obesity and si gnificantly lower leg ep. obesity ('apple' type), as compared with their he althy control group. Further, we show that the results of the applied netwo rks are very similar to the results of factor analysis. (C) 1999 Elsevier S cience B.V. All rights reserved.