ABSTRACT
Cancers of the oesophagus, stomach, and oesophago-gastric junction have important implications for health resources. Data from patients undergoing potentially curative resection of adenocarcinoma of the oesophago-gastric junction has been collected prospectively and analysed by an artificial neural network system. Oesophago-gastric oncological practice in the West has altered with an overall reduction in the incidence of gastric cancer and the emergence of adenocarcinoma of the oesophagus. Artificial neural networks are able to reliably predict, even with limited clinical preoperative information, patients destined to fail when treated by surgery alone. In contrast to the lack of preoperative information, clinicians are faced with increasingly more postoperative pathological data, but can find it difficult to interpret this information in a useful way. The rise in incidence of proximal gastric cancer and distal oesophageal adenocarcinoma has important implications for resources and health care management.
