Diagnosis of Lung Cancer by ATR-FTIR Spectroscopy and Chemometrics

Abstract

Lung cancer is the leading cause of cancer-related death in the world. Early diagnosis has great significance for the survival of patients with lung cancer. In this paper, attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy combined with chemometrics was used to study the serum samples from patients with lung cancer and healthy people. The results of spectral band area comparison showed that the concentrations of protein, lipid and nucleic acids molecules in serum of patients with lung cancer were increased compared with those in healthy people. The original spectra were preprocessed to improve the accuracy of principal component regression (PCR) and partial least squares-discriminant analysis (PLS-DA) models. PLS-DA results for first derivative spectral data in nucleic acids (1250-1000cm^-1) band showed 80% sensitivity, 91.89% specificity and 87.10% accuracy with high ${\text{R}}_{\text{c}}^2$ of 0.8949 and ${\text{R}}_{\text{v}}^2$ of 0.8153, low RMSEC of 0.3136 and RMSEV of 0.4180. It is shown that ATR-FTIR spectroscopy combined with chemometrics might be developed as a simple method for clinical screening and diagnosis of lung cancer.

Keywords: ATR-FTIR spectroscopy; Beer-Lambert law; chemometrics; lung cancer; serum.