Label-Free Surface-Enhanced Raman Spectroscopy (SERS) Combined with Machine Learning Using Gold Nanoparticles (AuNPs) as a Substrate for Characterizing Blood Serum from Hypopharyngeal Cancer Patients

Hypopharyngeal cancer contributes 3% of the overall head and neck cancers. The identification of major biochemical disease symptoms can be effective for diagnosing early stage of hypopharyngeal cancer. In the current work, gold nanoparticles (Au-NPs) were used as substrate for enhancement of Raman signal for the analysis of blood serum of different stages of hypopharyngeal cancer by surface-enhanced Raman spectroscopy (SERS). Major SERS spectral differentiating peaks were observed at 326, 446, 574, 622, 637, 680, 821, 876, 940, 964, 1081, 1133, 1284, 1325, 1432, 1451, 1574 and 1587 cm⁻¹ corresponding to biochemical changes of metabolites in blood serum of hypopharyngeal cancer patients. Moreover, chemometric tools like principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were applied for the effective differentiation and identification of biological changes along with sensitivity, specificity, precision, and accuracy of SERS for the classification of spectral groups of healthy and cancer samples.