Label-free surface-enhanced Raman spectroscopy of serum based on multivariate statistical analysis for the diagnosis and staging of lung adenocarcinoma

The present study aims to detect human serum for the screening and staging of lung adenocarcinoma (LAC) based on Raman spectroscopy and multivariate analysis. The tests on 190 serum samples including 82 normal individuals (NI) and 108 LAC were performed through label-free surface-enhanced Raman spectroscopy (SERS). The silver nanorods (NRs) wrapped with Al2O3 layers were used as SERS substrate. The Raman spectra of NI and LAC were compared and classified based on orthogonal partial least squares discriminant analysis (OPLS-DA). The diagnostic results showed that the specificity and sensitivity can reach 97.6% and 98.1%, respectively, based on leave-one-patient-out cross validation. The area under the receiver operating characteristic curve is greater than 0.99, indicating excellent classification of the two groups. Besides, the staging of LAC in different stages was also achieved, with the overall screening accuracy in stage I, stage II and stage III/IV was 84.3%, 93.3%, and 86.5%, respectively. This study demonstrated the technique of combining serum SERS spectra with OPLS-DA is a potential tool for the screening and staging of lung disease.