Chatchawal Patutong, Wongwattanakul Molin, Tippayawat Patcharaporn, Kochan Kamilla, Jearanaikoon Nichada, Wood Bayden R, Jearanaikoon Patcharee
Biomedical Sciences, Graduate School, Khon Kaen University, Khon Kaen 40002, Thailand.
Center for Research and Development of Medical Diagnosis Laboratories, Faculty of Associated Medical Sciences, Khon Kaen University, Khon Kaen 40002, Thailand.
Cancers (Basel). 2021 Oct 12;13(20):5109. doi: 10.3390/cancers13205109.
Cholangiocarcinoma (CCA) is a malignancy of the bile duct epithelium. 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, the phosphate band (vsPO2-) at 1073 cm, the polysaccharides band at 1152 cm and 1747 cm of lipid ester carbonyl. A Principal Component Analysis (PCA) shows discrimination between CCA and healthy sera using the 1400-1000 cm region and the combined 1800-1700 + 1400-1000 cm region. Partial Least Square-Discriminant Analysis (PLS-DA) scores plots in four of five regions investigated, namely, the 1400-1000 cm, 1800-1000 cm, 3000-2800 + 1800-1000 cm and 1800-1700 + 1400-1000 cm 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.
胆管癌（CCA）是胆管上皮的恶性肿瘤。感染是已知的CCA高危因素，主要在泰国东北部发现。这种疾病的隐匿性发展和无效诊断导致了晚期检测以及生存率降低。衰减全反射傅里叶变换红外光谱（ATR-FTIR）目前正在作为一种医学诊断工具进行探索。在本研究中，我们应用ATR-FTIR通过多变量分析来区分CCA血清与肝细胞癌（HCC）、胆道疾病（BD）和健康供体的血清。在1284、1339和1035厘米处的胶原带、1073厘米处的磷酸盐带（vsPO2-）、1152厘米和1747厘米处的脂质酯羰基多糖带中观察到与健康血清不同的光谱标记。主成分分析（PCA）显示使用1400 - 1000厘米区域以及1800 - 1700 + 1400 - 1000厘米组合区域可区分CCA和健康血清。在五个研究区域中的四个区域，即1400 - 1000厘米、1800 - 1000厘米、3000 - 2800 + 1800 - 1000厘米和1800 - 1700 + 1400 - 1000厘米区域的偏最小二乘判别分析（PLS-DA）得分图显示了CCA血清与健康志愿者血清之间的区分。通过PCA和PLS-DA无法将CCA与HCC和BD区分开来。使用PLS-DA、支持向量机（SVM）、随机森林（RF）和神经网络（NN）建立了CCA光谱模型。最佳模型是NN，根据用于光谱建模的光谱窗口不同，其对CCA的灵敏度达到80 - 100%，特异性在83%至100%之间。本研究证明了ATR-FTIR光谱和光谱建模作为区分CCA与其他病症的附加工具的潜力。
