Dataset Information

Artificial Intelligence and Machine Learning in the Diagnosis and Management of Gastroenteropancreatic Neuroendocrine Neoplasms-A Scoping Review.

ABSTRACT: Neuroendocrine neoplasms (NENs) and tumors (NETs) are rare neoplasms that may affect any part of the gastrointestinal system. In this scoping review, we attempt to map existing evidence on the role of artificial intelligence, machine learning and deep learning in the diagnosis and management of NENs of the gastrointestinal system. After implementation of inclusion and exclusion criteria, we retrieved 44 studies with 53 outcome analyses. We then classified the papers according to the type of studied NET (26 Pan-NETs, 59.1%; 3 metastatic liver NETs (6.8%), 2 small intestinal NETs, 4.5%; colorectal, rectal, non-specified gastroenteropancreatic and non-specified gastrointestinal NETs had from 1 study each, 2.3%). The most frequently used AI algorithms were Supporting Vector Classification/Machine (14 analyses, 29.8%), Convolutional Neural Network and Random Forest (10 analyses each, 21.3%), Random Forest (9 analyses, 19.1%), Logistic Regression (8 analyses, 17.0%), and Decision Tree (6 analyses, 12.8%). There was high heterogeneity on the description of the prediction model, structure of datasets, and performance metrics, whereas the majority of studies did not report any external validation set. Future studies should aim at incorporating a uniform structure in accordance with existing guidelines for purposes of reproducibility and research quality, which are prerequisites for integration into clinical practice.

SUBMITTER: Pantelis AG

PROVIDER: S-EPMC9027316 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Artificial Intelligence and Machine Learning in the Diagnosis and Management of Gastroenteropancreatic Neuroendocrine Neoplasms-A Scoping Review.

Pantelis Athanasios G AG Panagopoulou Panagiota A PA Lapatsanis Dimitris P DP

Diagnostics (Basel, Switzerland) 20220331 4

Neuroendocrine neoplasms (NENs) and tumors (NETs) are rare neoplasms that may affect any part of the gastrointestinal system. In this scoping review, we attempt to map existing evidence on the role of artificial intelligence, machine learning and deep learning in the diagnosis and management of NENs of the gastrointestinal system. After implementation of inclusion and exclusion criteria, we retrieved 44 studies with 53 outcome analyses. We then classified the papers according to the type of stud ...[more]

PMID: 35453922

Similar Datasets

Project description:Our understanding about the epidemiological aspects, pathogenesis, molecular diagnosis, and targeted therapies of neuroendocrine neoplasms (NENs) have drastically advanced in the past decade. Gastroenteropancreatic (GEP) NENs originate from the enteroendocrine cells of the embryonic gut which share common endocrine and neural differentiation factors. Most NENs are well-differentiated, and slow growing. Specific neuroendocrine biomarkers that are used in the diagnosis of functional NENs include insulin, glucagon, vasoactive intestinal polypeptide, gastrin, somatostatin, adrenocorticotropin, growth hormone releasing hormone, parathyroid hormone-related peptide, serotonin, histamine, and 5-hydroxy indole acetic acid (5-HIAA). Biomarkers such as pancreatic polypeptide, human chorionic gonadotrophin subunits, neurotensin, ghrelin, and calcitonin are used in the diagnosis of non-functional NENs. 5-HIAA levels correlate with tumour burden, prognosis and development of carcinoid heart disease and mesenteric fibrosis, however several diseases, medications and edible products can falsely elevate the 5-HIAA levels. Organ-specific transcription factors are useful in the differential diagnosis of metastasis from an unknown primary of well-differentiated NENs. Emerging novel biomarkers include circulating tumour cells, circulating tumour DNA, circulating micro-RNAs, and neuroendocrine neoplasms test (NETest) (simultaneous measurement of 51 neuroendocrine-specific marker genes in the peripheral blood). NETest has high sensitivity (85%-98%) and specificity (93%-97%) for the detection of gastrointestinal NENs, and is useful for monitoring treatment response, recurrence, and prognosis. In terms of management, surgery, radiofrequency ablation, symptom control with medications, chemotherapy and molecular targeted therapies are all considered as options. Surgery is the mainstay of treatment, but depends on factors including age of the individual, location, stage, grade, functional status, and the heredity of the tumour (sporadic vs inherited). Medical management is helpful to alleviate the symptoms, manage inoperable lesions, suppress postoperative tumour growth, and manage recurrences. Several molecular-targeted therapies are considered second line to somatostatin analogues. This review is a clinical update on the pathophysiological aspects, diagnostic algorithm, and management of GEP NENs.

Dataset Information

Artificial Intelligence and Machine Learning in the Diagnosis and Management of Gastroenteropancreatic Neuroendocrine Neoplasms-A Scoping Review.

Publications

Artificial Intelligence and Machine Learning in the Diagnosis and Management of Gastroenteropancreatic Neuroendocrine Neoplasms-A Scoping Review.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets