determining the expression levels of at least 23 biomarkers from a test sample from the human subject by performing reverse transcription polymerase chain reaction (RT-PCR) with a plurality of probes or primers specific to detect the expression of the at least 23 biomarkers, wherein the at least 23 biomarkers comprise APLP2, ARAF, CD59, CTGF, FZD7, KRAS, MKI67/KI67, MORF4L2, NAP1L1, NOL3, PNMA2, RAF1, RSF1, SLC18A2/VMAT2, SPATA7, SSTR1, SSTR3, SSTR4, SSTR5, TPH1, TRMT112, ZFHX3, and ALG9, wherein the test sample is blood, serum, plasma, or neoplastic tissue;

normalizing the expression levels of APLP2, ARAF, CD59, CTGF, FZD7, KRAS, MKI67/KI67, MORF4L2, NAP1L1, NOL3, PNMA2, RAF1, RSF1, SLC18A2/VMAT2, SPATA7, SSTR1, SSTR3, SSTR4, SSTR5, TPH1, TRMT112, and ZFHX3 to the expression level of ALG9 to obtain normalized expression levels;

classifying the test sample with respect to the presence or development of a GEP-NEN using the normalized expression levels in a classification system, wherein the classification system is a machine learning system that comprises four different algorithms: Support Vector Machine, Linear Discrimination Analysis, K-Nearest Neighbor, and Naïve Bayes;

assigning a score based on a result of each of the four different algorithms;

comparing the score with a predetermined cutoff value;

determining the presence of a progressive GEP-NEN in the subject, wherein determining the presence of a progressive GEP-NEN in the subject comprises determining that the score is equal to or greater than the predetermined cutoff value, wherein the predetermined cutoff value is 5 on a MAARC-NET scoring system scale of 0-8;

administering a treatment to the subject identified as having a progressive GEP-NEN, wherein the treatment comprises surgery or drug therapy.