Detection of small cell lung cancer by electronic nose

Abstract

Introduction: Small cell lung cancer (SCLC) is an aggressive type of lung cancer and accounts for 15% of all lung cancer cases. Progress in the survival rate of SCLC is poor with a 5-year survival rate of only 5-10%, depending on tumour stage at presentation. Tumour detection earlier in the course of this disease is a potential tool to improve outcome. Exhaled-breath analysis of volatile organic compounds (VOC’s), reflecting pathological processes, have the potential to diagnose lung cancer in a sensitive, non-invasive way. We aimed to determine the diagnostic accuracy of breath analysis in SCLC using an electronic nose (Aeonose™). Methods: Subjects with confirmed SCLC and healthy subjects breathed into the Aeonose™ (The eNose Company, Zutphen, The Netherlands) for 5 minutes. Diagnostic performance was studied in a prospective multicentre study conducted in 4 hospitals in 93 subjects of which 18 had pathologically confirmed SCLC. The breath prints of the two groups were compared, using data compression and artificial neural networks for the statistical analysis of VOC data. Results: SCLC patients and healthy subjects had a mean age of 63.2±8.2 and 65.9±8.8 years, respectively. Choosing a proper point at the ROC curve to rule out SCLC resulted in a sensitivity of 88.9%, a specificity of 80.0%, a positive predictive value of 51.6%, a negative predictive value of 96.8%, and an area under the curve of 0.86. Conclusion: The data show that electronic nose technology with the Aeonose™ can play an important role in rapidly excluding SCLC due to the high negative predictive value that was obtained in this study. Patients showing positive breath tests should still be subjected to further diagnostic testing.