Combining urine surface-enhanced Raman spectroscopy with PCA-SVM algorithm for improving the identification of colorectal cancer at different stages

Abstract

Cancer staging detection is important for clinician to assess the patients’ status and make optimal therapy decision. In this study, the machine learning algorithm based on principal component analysis (PCA) and support vector machine (SVM) was combined with urine surface-enhanced Raman scattering (SERS) spectroscopy for improving the identification of colorectal cancer (CRC) at early and advanced stages. Two discriminant methods, linear discriminant analysis (LDA) and SVM were compared, and the results indicated that the diagnostic accuracy of SVM (93.65%) was superior to that of LDA (80.95%). This exploratory study demonstrated the great promise of urine SERS spectra along with PCA-SVM for facilitating more accurate detection of CRC at different stages.