Open AccessPredicting Overall Survival in Patients with Metastatic Rectal Cancer: a Machine Learning Approach
Author(s) -
Beiqun Zhao,
Rodney A. Gabriel,
Florin Vaida,
Nicole Lopez,
Samuel Eisenstein,
Bryan M. Clary
Publication year - 2019
Publication title -
journal of gastrointestinal surgery
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.168
H-Index - 126
eISSN - 1873-4626
pISSN - 1091-255X
DOI - 10.1007/s11605-019-04373-z
Subject(s) - medicine , nomogram , lasso (programming language) , colorectal cancer , concordance , proportional hazards model , hazard ratio , cancer , machine learning , artificial intelligence , oncology , confidence interval , world wide web , computer science
A significant proportion of patients with rectal cancer will present with synchronous metastasis at the time of diagnosis. Overall survival (OS) for these patients are highly variable and previous attempts to build predictive models often have low predictive power, with concordance indexes (c-index) less than 0.70.