Medical Physics Unit, Fondazione IRCCS Istituto Nazionale dei Tumori, Via Venezian 1, 20133, Milan, Italy.
Epidemiology and Prevention Unit, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy.
BMC Cancer. 2018 Aug 22;18(1):841. doi: 10.1186/s12885-018-4754-2.
An increase in naturally-occurring porphyrins has been described in the blood of subjects bearing different kinds of tumors, including colorectal, and this is probably related to a systemic alteration of heme metabolism induced by tumor cells. The aim of our study was to develop an artificial neural network (ANN) classifier for early detection of colorectal adenocarcinoma based on plasma porphyrin accumulation and risk factors.
We measured the endogenous fluorescence of blood plasma in 100 colorectal adenocarcinoma patients and 112 controls using a conventional spectrofluorometer. Height, weight, personal and family medical history, use of alcohol, red meat, vegetables and tobacco were all recorded. An ANN model was built up from demographic data and from the integral of the fluorescence emission peak in the range 610-650 nm. We used the Receiver Operating Characteristic (ROC) curve to assess performance in distinguishing colorectal adenocarcinoma patients and controls. A liquid chromatography-high resolution mass spectrometry (LC-HRMS) analytical method was employed to identify the agents responsible for native fluorescence.
The fluorescence analysis indicated that the integral of the fluorescence emission peak in the range 610-650 nm was significantly higher in colorectal adenocarcinoma patients than controls (p < 0.0001) and was weakly correlated with the TNM staging (Spearman's rho = 0.224, p = 0.011). LC-HRMS measurements showed that the agents responsible for the fluorescence emission were mainly protoporphyrin-IX (PpIX) and coproporphyrin-I (CpI). The overall accuracy of our ANN model was 88% (87% sensitivity and 90% specificity) with an area under the ROC curve of 0.83.
These results confirm that tumor cells accumulate a diagnostic level of endogenous porphyrin compounds and suggest that plasma porphyrin concentrations, indirectly measured through fluorescence analysis, may be useful, together with risk factors, as a clinical decision support tool for the early detection of colorectal adenocarcinoma. Our future efforts will be aimed at examining how plasma porphyrin accumulation correlates with survival and response to therapy.
在患有包括结直肠在内的不同类型肿瘤的患者的血液中，已经描述了天然卟啉的增加，这可能与肿瘤细胞诱导的血红素代谢的全身性改变有关。我们的研究目的是开发一种基于血浆卟啉积累和危险因素的用于早期检测结直肠腺癌的人工神经网络 (ANN) 分类器。
我们使用常规荧光分光光度计测量了 100 例结直肠腺癌患者和 112 例对照者的血液内源性荧光。记录了身高、体重、个人和家族病史、酒精、红肉、蔬菜和烟草的使用情况。ANN 模型是从人口统计学数据和荧光发射峰积分范围 610-650nm 建立起来的。我们使用接收者操作特征 (ROC) 曲线来评估区分结直肠腺癌患者和对照者的性能。采用液相色谱-高分辨质谱 (LC-HRMS) 分析方法鉴定产生天然荧光的物质。
荧光分析表明，结直肠腺癌患者的荧光发射峰积分范围 610-650nm 明显高于对照组（p<0.0001），且与 TNM 分期呈弱相关（Spearman's rho=0.224，p=0.011）。LC-HRMS 测量结果表明，产生荧光的物质主要为原卟啉-IX（PpIX）和粪卟啉-I（CpI）。我们的 ANN 模型的整体准确性为 88%（87%的灵敏度和 90%的特异性），ROC 曲线下面积为 0.83。
这些结果证实肿瘤细胞积累了诊断水平的内源性卟啉化合物，并表明通过荧光分析间接测量的血浆卟啉浓度可能与风险因素一起用作结直肠腺癌早期检测的临床决策支持工具。我们未来的努力将集中在研究血浆卟啉积累与生存和对治疗的反应如何相关。
