The aim of our study is to design and compare some predictive models for estimating the Bone Mineral Density score (BMD) t-score. The data were collected, except the t-score, by self-report from 356 women recruited from the Cantacuzino Hospital, Bucharest, Romania, during the period 1998-2003. The following methods are tuned and compared on this data: the General Regression Model (GRM), the Classification Trees (CT) and the Multilayer Perceptrons Network (MLP). Comparatively with a number of different bone densitometry criteria, currently used in clinical practice, we show that each of the above investigated models have a better sensitivity and specificity.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.