Label-free surface-enhanced Raman spectroscopy of serum with machine-learning algorithms for gallbladder cancer diagnosis

Author：Wubulitalifu Dawuti a,b,1 , Jingrui Dou a,b,1 , Jintian Li a,b , Rui Zhang a,b , Jing Zhou a,c , Maierhaba Maimaitiaili a,c , Run Zhou a,c , Renyong Lin a,* , Guodong Lü a,*

ABSTRACT：Gallbladder cancer (GBC) is a rare but frequently fatal biliary tract malignancy that is typically discovered when it is already advanced. In this study, we investigated a novel technique for the quick and non-invasive diagnosis of GBC based on serum surface-enhanced Raman spectroscopy (SERS). SERS spectra of serum from 41 patients with GBC and 72 normal subjects were recorded. Principal component analysis-linear discriminant analysis (PCA-LDA), and PCA-support vector machine (PCA-SVM), Linear SVM and Gaussian radial basis function-SVM (RBF-SVM) algorithms were used to establish the classification models, respectively. When the Linear SVM was used, the overall diagnostic accuracy for classifying the two groups could achieve 97.1%, and when RBFSVM was used, the diagnostic sensitivity of GBC was 100%. The results demonstrated that SERS combination with a machine learning algorithm is a promising candidate to be one of the diagnostic tools for GBC in the future.

Keywords:Gallbladder cancer (GBC) Serum Surface-enhanced Raman spectroscopy (SERS) Principal component analysis-linear discriminant analysis (PCA-LDA) Support vector machine (SVM)

关联产品：ATR6500-手持式拉曼光谱仪