ARTIFICIAL NEURAL-NETWORK APPLIED TO DIAG NOSIS OF LUNG-CANCER

Artificial neural network(ANN) approach was applied to classification of normal persons and lung cancer patients based on the metal content of hair and serum samples obtained by inductively coupled plasma atomi c emission spectrometry (ICP-AES) for the two groups. This method was verified with independent prediction samples and can be used as an aid ing means of the diagnosis of lung cancer. The case of predictive clas sification with one element missing in the prediction samples was stud ied in details, The significance of elements in hair and serum samples for classification prediction was also investigated.