OBJECTIVETo discuss the effect of different positive criteria on the sensitivity and specificity of sputum cytology screening for lung cancer among Yunnan tin miners.

METHODS9223 Yunnan tin miners who received at least one annual sputum cytology screening for lung cancer during the period between 1992 and 1999 were recruited in the study. At time of enrollment, all participants were aged over 40 years old, had at least 10 years of employment as an underground miner and(or) smelter, and had not been diagnosed with malignancy. In our study, a true positive was categorized as having at least one prior positive sputum screening and a diagnosis of lung cancer, while a true negative, by our definition, signified negative sputum examinations and no diagnosis of lung cancer during the follow up time. Based on different positive criteria, sensitivity and specificity of sputum cytology were computed and receiver operating characteristic (ROC) curve analysis was conducted. Z statistic was used to test the differences of the area under ROC based on Hanley and McNeil method.

RESULTSBy the end of following up on December 31, 2001, a total 500 lung cancer cases were diagnosed among 9223 participants: most were squamous cell carcinoma (55.8% (222/398)) and central lung cancers (68.5% (316/461)). 150 lung cancer cases had a previous positive sputum screening result. When positive criteria were taken as grave atypical metaplasia, moderate atypical metaplasia and slight atypical metaplasia, the corresponding sensitivities were 30.0% (150/500), 36.4% (182/500), 53.0% (265/500) respectively; while the corresponding specificities were 98.9% (8628/8723), 95.1% (8611/8723), 77.9% (7033/8723) respectively. The areas under ROC curve according to different positive criterias were 0.645 (95%CI: 0.635 - 0.654), 0.657 (95%CI: 0.668 - 0.667), 0.655 (95%CI: 0.645 - 0.664) respectively. There were no significant differences found in the comparisons between grave and moderate atypical metaplasia, grave and slight atypical metaplasia, moderate and slight atypical metaplasia(Z statistics were 0.780, 0.645, 0.209 respectively, all P values > 0.05).

CONCLUSIONWhile the standard of positive criteria for diagnosis of lung cancer decreased, the sensitivity of sputum cytology screening increased and the specificity decreased. Since there were no significant differences of accuracy for different positive criteria.