Bilateral asymmetry prediction

This study predicts asymmetries in lateral organ cancer incidence from text mining of the Medline database. Lung, kidney, teste, and ovary cancers were examined. For each cancer, Medline case report articles focused solely on (1) cancer of the right organ and (2) cancer of the left organ were retrieved. The ratio of right organ to left organ articles was compared to actual patient incidence data obtained from the National Cancer Institute's (NCI) SEER database for the period 1979-1998. The agreement between the Medline record ratios and the NCI's patient incidence data ratios ranged from within 3% for lung cancer to within 1% for teste and ovary cancer. This is the first known study to generate cancer lateral incidence asymmetries from the Medline database. The technique should be applicable to other diseases and other types of system asymmetries. Published by Elsevier Science Ltd.