Detection of Human Cholangiocarcinoma Markers in Serum Using Infrared Spectroscopy

Abstract

Cholangiocarcinoma (CCA) is a malignancy of the bile duct epithelium. Opisthorchis viverrini infection is a known high-risk factor for CCA and in found, predominantly, in Northeast Thailand. The silent disease development and ineffective diagnosis have led to late-stage detection and reduction in the survival rate. Attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) is currently being explored as a diagnostic tool in medicine. In this study, we apply ATR-FTIR to discriminate CCA sera from hepatocellular carcinoma (HCC), biliary disease (BD) and healthy donors using a multivariate analysis. Spectral markers differing from healthy ones are observed in the collagen band at 1284, 1339 and 1035 cm−1, the phosphate band () at 1073 cm−1, the polysaccharides band at 1152 cm−1 and 1747 cm−1 of lipid ester carbonyl. A Principal Component Analysis (PCA) shows discrimination between CCA and healthy sera using the 1400–1000 cm−1 region and the combined 1800—1700 + 1400–1000 cm−1 region. Partial Least Square-Discriminant Analysis (PLS-DA) scores plots in four of five regions investigated, namely, the 1400–1000 cm−1, 1800–1000 cm−1, 3000–2800 + 1800–1000 cm−1 and 1800–1700 + 1400–1000 cm−1 regions, show discrimination between sera from CCA and healthy volunteers. It was not possible to separate CCA from HCC and BD by PCA and PLS-DA. CCA spectral modelling is established using the PLS-DA, Support Vector Machine (SVM), Random Forest (RF) and Neural Network (NN). The best model is the NN, which achieved a sensitivity of 80–100% and a specificity between 83 and 100% for CCA, depending on the spectral window used to model the spectra. This study demonstrates the potential of ATR-FTIR spectroscopy and spectral modelling as an additional tool to discriminate CCA from other conditions.

Attenuated Total Reflectance-Fourier Transform Infrared (ATR-FTIR) Spectroscopy Discriminates the Elderly with a Low and High Percentage of Pathogenic CD4+ T Cells

“…The different performances of a classification model in terms of % accuracy, sensitivity, and specificity are not only influenced by the algorithm used, but also the input attributes, data complexity, and sample size. Until now, there has been no agreement on the best method of analysis [42]. A limitation of this study was the number of spectra used for building the classification models.…”

“…Classification model performance was evaluated in terms of % accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) [42,50]. A confusion matrix or 2 × 2 table (Table 1) was employed for calculations with the following formulas:…”

“…In their study, they used various machine learning methods, such as partial least square discriminant analysis (PLS-DA), support vector machine (SVM), random forest (RF), and neural network (NN). Furthermore, the NN algorithm showed the best performance with a test sensitivity of 80-100% and specificity of 83-100% [42]. In addition, the application of ATR-FTIR combined with a neural network could differentiate between sera from healthy subjects and from breast cancer patients with a sensitivity of 92-95% and specificity of 95-100% [43].…”

“…The combination of vibrational spectroscopy and machine learning algorithms has been utilized as a diagnostic tool for various diseases with excellent discrimination results. Chatchawal et al (2021) explored the potential of ATR-FTIR combined with several machine learning algorithms to identify cholangiocarcinoma from human sera. In their study, they used various machine learning methods, such as partial least square discriminant analysis (PLS-DA), support vector machine (SVM), random forest (RF), and neural network (NN).…”

Vibrational spectroscopy – are we close to finding a solution for early pancreatic cancer diagnosis?

“…ATR-FTIR is characterized by high sensitivity in biomedical diagnostics[ 52 ] and can detect spectral markers of many pathologies in physiological liquids such as saliva or blood serum. ATR-FTIR was used to detect lung[ 53 ], bile duct[ 54 ], ovary[ 55 , 56 ], breast[ 57 ], and brain[ 58 , 59 ] tumors in the blood serum samples. In a study by Butler et al [ 59 ], the team described the methodology of using ATR-FTIR in an early screening of brain tumor patients with sensitivity and specificity of 93.2% and 92.8%, respectively.…”