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 have low sensitivity (SEN) and specificity (SPE). This is a first preplanned interim analysis (Nordic non-interventional, prospective, exploratory, EXPLAIN study [NCT02630654]). Its objective is to investigate if a plasma protein multi-biomarker strategy can improve diagnostic accuracy (ACC) in SI-NETs.
Methods: At the time of diagnosis, before 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 sex-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 SEN and 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 30 patients with normal CgA concentrations, the model provided a diagnostic SPE of 98%, SEN of 56%, and NPV 90%, PPV of 90%, and AUROC 97%, regardless of proton pump inhibitor intake.
Conclusion: This interim analysis demonstrates that a multi-biomarker/machine learning strategy improves diagnostic ACC 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.
Keywords: Biomarker; Diagnosis; Machine learning; Neuroendocrine tumor.
© 2020 S. Karger AG, Basel.