ABSTRACT
Medical applications of artificial neural networks are mostly based on their ability to handle classification problems: multiple examples are presented to the system together with the known output; the neural network is allowed to “learn” by adaptation using various paradigms. Neural networks are best trained by using as large a dataset as possible, with numerous features of information and a large number of examples to learn from. Classifications generated by artificial neural networks can be used in medicine to develop objective classifications of illnesses or to estimate prognosis. The assessment of prognosis has always been an important part of medical practice. In addition, evaluation of a large number of prognostic variables is needed to develop a comprehensive prognostic system for patients with lung cancer. Carcinoma of the lung is the generic name for malignant epithelial neoplasms of the lung. Nonsmall cell bronchogenic carcinomas include adenocarcinoma, squamous cell carcinoma, and large cell undifferentiated carcinoma, as the more frequent types.
