EVALUATION OF COMPLICATIONS OF KIDNEY-TRANSPLANTATION USING ARTIFICIAL NEURAL NETWORKS

The aim of this study was to develop an artificial neural network (ANN ) to differentiate between rejection, acute tubular necrosis (ATN) and normally functioning kidneys in a group of patients with renal transp lants. The performance of ANN was compared with that of an experienced observer using a database of 35 patients' records, each of which incl uded 12 quantitative parameters derived from renograms and clinical da ta as well as a clinical evaluation. These findings were encoded as fe atures for a three-layered neural network to predict the outcome of bi opsy or clinical diagnosis. The network was trained and tested using t he jackknife method and its performance was then compared to that of a radiologist. The network was able to correctly classify 31 of the 35 original cases and gave a better diagnostic accuracy (88%) than the ra diologist (83%), by showing an association between the quantitative da ta and the corresponding pathological results (r = 0.78, P < 0.001). W e conclude that an ANN can be trained to differentiate rejection from acute tubular necrosis, as well as normally functioning transplants, w ith a reasonable degree of accuracy.