Application of artificial neural network in the diagnosis of lung cancer
Wu Yong · Zhonghua weishengwuxue he mianyixue zazhi · 2003
Objective To develop an intelligent diagnosis system of lung cancer using artificial neural network (ANN) based on 12 tumor markers. Mehtods Radioimmunoassay (RIA), Enzyme linked immuosorbent assay (ELISA), high performance liquid chromatography (HPLC) and spectrophotometry were applied to detect 12 tumor markers. According to 12 tumor markers, the intelligent diagnosis system was developed based on ANN. Results This method is superior to traditional medical statistical method. The rates of discrimination and predication are both 100%, and the system can be used as a discriminator among normal, benign and malignant. Conclusions Artificial neural network has been first introduced into the diagnosis of lung cancer, and developed the intelligence diagnosis system. The system is in favor of extensive survey for high risk persons, and can provide a method for clinical diagnosis.