Plasma protein biomarkers for the detection of pancreatic neuroendocrine tumors (Pan-NET) and differentiation from small intestinal (SI) NET

#3122

Introduction: There is an unmet need for novel biomarkers to diagnose and monitor patients with Pan-NET and SI-NET.

Aim(s): The EXPLAIN study explores a multi plasma protein strategy to improve the detection of Pan-NET and to differentiate them from SI-NET and a control group (GC).

Materials and methods: At time of diagnosis blood were collected from 39 patients with Pan-NET and 135 with SI-NET, (WHO G 1-2) and 144 CG individuals. Exclusion criteria: Other malignant diseases, chronic inflammatory diseases, kidney or liver failure. Proseek Oncology-II (OLink) was used to measure 92 cancer related plasma proteins a long with Chromogranin A (CgA). Machine learning (Boosted Tree (BT)) was used to classify between Pan-NET versus SI-NET and CG individuals. 3k-fold cross-validation was performed (80% training, 20% validation).

Conference: 18th Annual ENETS Concerence (2021)

Presenting Author: Thiis-Evensen E

Authors: Thiis-Evensen E, Kjellman M, Knigge U, Gronbaek H, Schalin-Jäntti C,

Keywords: detection, Pan-NET, SI-NET, biomarker, plasma protein, machine learning,