A fuzzy-classifier using a marker panel for the detection of lung cancers in asbestosis patients

Background: The aim of this study was to evaluate the diagnostic power of a fuzzy classifier and a marker panel (CYTRA 21-1, NSE, CRP) for the detection of lung cancers in comparison to asbestosis patients at high-risk of developing lung cancer. Patients and Methods: A panel of four tumour markers, i.e. CEA, CYFRA 21-1, NSE, SCC and CRP, was measured in newly diagnosed lung cancer patients of different histological types and stages in comparison to asbestosis patients. In this prospective study, a fuzzy classifier was generated with the data of 216 primary lung cancer patients and 76 patients suffering from asbestosis. The patients and controls were recruited in the clinics of the University in Giessen. Results: At 95%-specificity, it was possible with this tool to detect non-small cell lung cancers in 70% at stage I (n = 30), in 95% at stage II (n = 22), in 98% at stage III (n = 56), in 92% at stage IV (n = 50) and small cell lung cancers with limited disease status (n = 21) in 90.7% and with extensive disease status (n = 37) in 97.3%. In contrast, single markers had a detection rate significantly far below these. The application of the classifier was examined on an independent collective of 38 non-small cell lung cancers and 76 asbestosis patients. The latter underwent stationary rehabilitation in the clinics for occupational diseases in Bad Reichenhall or Falkenstein. The fuzzy classifier showed correct negative classification in 75 out of the 76 cancer-free asbestosis patients, which confirmed a specificity of 97.4%. The overall sensitivity for lung cancer detection in high risk populations was 73.6%. All large cell carcinomas were detected. The positive predictive value was 77.7%. The negative predictive value reached 94.8%. Conclusion: With the fuzzy classifier and a marker panel, a reliable diagnostic tool for the detection of lung cancers in a high risk population is available.