Application of the dual-frequency ultrasonometer for osteoporosis detection

A multi-parametric linear classifier based on a set of the parameters derived from 2D acoustic waveform profiles has been developed. The efficiency of this classifier in differentiating osteoporosis from a normal sample was assessed using a receiver operating characteristic (ROC) curve analysis. Based on the ROC analysis, BUSS demonstrated 76% sensitivity and 70% specificity to DXA-identified osteoporosis. The area under the ROC curve, which is a measure of how well a parameter can distinguish between the two diagnostic groups (diseased/normal) was 79.3%. The study confirmed BUSS's capability to discriminate between stages of bone atrophy and in particular to distinguish early changes induced by osteoporosis.