Clustering of gastroenteropancreatic neuroendocrine neoplasms (GEP-NEN) using machine learning (ML) and comparison with tumour, node, metastasis (TNM) staging: A population-based study using surveillance, epidemiology, and end results (SEER)

#4462

Introduction: TNM 8 is the staging system for GEP-NEN, guiding prognosis and treatment. However, it does not include important prognostic factors such as age, sex, race, and morphology.

Aim(s): To evaluate the predictive ability of TNM staging system for survival and improve it using machine learning.

Materials and methods: 35,347 adults diagnosed between 2011-2021 with GEP-NEN with complete data were extracted from SEER. Age, sex, race, tumour site, size, morphology, number of lymph nodes and metastasis site were used to create 3 clusters using K-means ML clustering model. Cox regression, Kaplan Meier (KM) plots and overall survival (OS) estimates were generated for TNM stage (model-1) and clusters (model-2).

Conference:

Presenting Author: Mortagy M

Authors: Mortagy M, El Asmar M, White B, Chandrakumaran K, Ramage J,

Keywords: Clustering, Machine learning, GEP-NEN, TNM Staging, Survival Analysis, SEER,