Artificial neural networks are a kind of pattern classifiers, with gro
wing acceptance in medical and biological research. We applied a singl
e layer perceptron to data of 4302 patients from National Cancer Centr
e in Tokyo and compared the results to the Maruyama diagnostic system
(MDS) and classic statistical analysis with logistic regression. While
logistic regression reached no sensitivity and a specificity of 1.00
in median, MDS had a sensitivity of 0.74 and a specificity of 0.75 in
median. The perceptron reached a median sensitivity of 0.83 and a medi
an specificity of 0.71.