Background: Small intestinal neuroendocrine tumors (SI-NETs) are difficult to diagnose in the early stage of disease. Current blood biomarkers such as chromogranin A (CgA) and 5-hydroxyindolacetic acid (5-HIAA) have low sensitivity and specificity. This is a first pre-planned interim analysis (NORDIC non-interventional, exploratory, EXPLAIN study (NCT02630654)). Its objective is to investigate if a plasma protein multi-biomarker strategy can improve diagnostic accuracy in SI-NETs. Methods: At time of diagnosis, prior any disease specific treatment was initiated, blood was collected from patients with advanced SI-NETs and 92 putative cancer-related plasma proteins from 135 patients were analyzed and compared with the results of age and gender matched controls (n=143), using multiplex proximity extension assay and machine learning techniques. Results: Using a random forest model including 12 top ranked plasma proteins in patients with SI-NETs, the multi-biomarker strategy showed sensitivity (SEN) and specificity (SPE) of 89% and 91%, respectively, with negative predictive value (NPV) and positive predictive value (PPV) of 90% and 91%, respectively, to identify patients with regional or metastatic disease with an area under the receiver operator characteristic curve (AUROC) of 99%. In thirty patients with normal CgA concentrations the model provided diagnostic SPE of 98%, a SEN of 56%, and NPV 90%, PPV of 90%, and AUROC 97%, regardless of proton pump inhibitor intake. Conclusion: This interim analysis demonstrate that a multi-biomarker/machine learning strategy improve diagnostic accuracy of patients with SI-NET at the time of diagnosis, especially in patients with normal CgA levels. The results indicate that this multi-biomarker strategy can be useful for early detection of SI-NETs at presentation and conceivably detect recurrence after radical primary resection.


中文翻译：

---

用于检测小肠神经内分泌肿瘤的血浆蛋白生物标志物策略。

背景：小肠神经内分泌肿瘤（SI-NETs）在疾病早期很难诊断。目前的血液生物标志物如嗜铬粒蛋白 A (CgA) 和 5-羟基吲哚乙酸 (5-HIAA) 的敏感性和特异性较低。这是第一个预先计划的中期分析（NORDIC 非干预性、探索性、解释性研究（NCT02630654））。其目的是研究血浆蛋白多生物标志物策略是否可以提高 SI-NET 的诊断准确性。方法：在诊断时，在开始任何疾病特异性治疗之前，采集晚期 SI-NET 患者的血液，分析来自 135 名患者的 92 种推定的癌症相关血浆蛋白，并与年龄和性别匹配对照的结果进行比较。 n = 143），使用多重邻近扩展分析和机器学习技术。结果：使用随机森林模型，包括 SI-NET 患者中排名最高的 12 种血浆蛋白，多生物标志物策略的敏感性 (SEN) 和特异性 (SPE) 分别为 89% 和 91%，具有阴性预测值 (NPV) ) 和阳性预测值 (PPV) 分别为 90% 和 91%，以确定接受者操作特征曲线 (AUROC) 下面积为 99% 的区域或转移性疾病患者。在 CgA 浓度正常的 30 名患者中，该模型提供了 98% 的诊断性 SPE、56% 的 SEN、90% 的 NPV、90% 的 PPV 和 97% 的 AUROC，无论质子泵抑制剂摄入量如何。结论：该中期分析表明，多生物标志物/机器学习策略可提高 SI-NET 患者在诊断时的诊断准确性，尤其是 CgA 水平正常的患者。