An infrared spectroscopic blood test for non-small cell lung carcinoma and subtyping into pulmonary squamous cell carcinoma or adenocarcinoma

Abstract

BACKGROUND: Lung cancer is the leading cause of death for male and female cancer patients alike. Early diagnosis improves prognosis. A blood test would be a valuable support. OBJECTIVE: Infrared spectroscopy provides a label-free biochemical fingerprint of a sample. A study was conducted on 161 patients with initial cancer suspicion to identify and verify spectral biomarker candidate patterns to detect non-small cell lung carcinoma (NSCLC). METHODS: Blood serum and plasma samples were analysed with an automated FTIR spectroscopic system. Two pattern recognition algorithms and two classifiers were applied. Monte Carlo cross validation was performed with linear discriminant analysis and random forest classification. RESULTS: Marker patterns for the discrimination of cancer from clinically relevant disease control patients were identified in FTIR spectra of blood samples. An accuracy of up to 79% was achieved. Squamous cell and adenocarcinoma patients were separable with an accuracy of 80%. CONCLUSIONS: The study demonstrates the applicability of FTIR spectroscopic blood testing for lung cancer detection. Evidence for cancer subtype discrimination is given. With an improved performance, the method could be developed as a routine diagnostic tool for blood testing detecting NSCLC.