An interactive Bayesian model for prediction of lymph node ratio and survival in pancreatic cancer patients

Brian J Smith; James J Mezhir

doi:10.1136/amiajnl-2013-002171

Back

An interactive Bayesian model for prediction of lymph node ratio and survival in pancreatic cancer patients

Journal article

Open access

An interactive Bayesian model for prediction of lymph node ratio and survival in pancreatic cancer patients

Brian J Smith and James J Mezhir

Journal of the American Medical Informatics Association : JAMIA, Vol.21(e2), pp.e203-e211

10/2014

DOI: 10.1136/amiajnl-2013-002171

PMCID: PMC4173165

PMID: 24444460

Files and links (1)

url

https://doi.org/10.1136/amiajnl-2013-002171View

Published (Version of record) Open Access

Abstract

Regional lymph node status has long been used as a dichotomous predictor of clinical outcomes in cancer patients. More recently, interest has turned to the prognostic utility of lymph node ratio (LNR), quantified as the proportion of positive nodes examined. However, statistical tools for the joint modeling of LNR and its effect on cancer survival are lacking. Data were obtained from the NCI SEER cancer registry on 6400 patients diagnosed with pancreatic ductal adenocarcinoma from 2004 to 2010 and who underwent radical oncologic resection. A novel Bayesian statistical approach was developed and applied to model simultaneously patients' true, but unobservable, LNR statuses and overall survival. New web development tools were then employed to create an interactive web application for individualized patient prediction. Histologic grade and T and M stages were important predictors of LNR status. Significant predictors of survival included age, gender, marital status, grade, histology, T and M stages, tumor size, and radiation therapy. LNR was found to have a highly significant, non-linear effect on survival. Furthermore, predictive performance of the survival model compared favorably to those from studies with more homogeneous patients and individualized predictors. We provide a new approach and tool set for the prediction of LNR and survival that are generally applicable to a host of cancer types, including breast, colon, melanoma, and stomach. Our methods are illustrated with the development of a validated model and web applications for the prediction of survival in a large set of pancreatic cancer patients.

SEER Program

Lymph Nodes - pathology

Prognosis

Humans

Pancreatic Neoplasms - pathology

Logistic Models

Lymphatic Metastasis

Carcinoma, Pancreatic Ductal - pathology

Neoplasm Grading

Bayes Theorem

Survival Analysis

Carcinoma, Pancreatic Ductal - mortality

Pancreatic Neoplasms - mortality

Internet

Neoplasm Staging

Details

Title: Subtitle: An interactive Bayesian model for prediction of lymph node ratio and survival in pancreatic cancer patients
Creators: Brian J Smith - Department of Biostatistics, College of Public Health, University of Iowa, Iowa City, Iowa, USA
James J Mezhir - Division of Surgical Oncology and Endocrine Surgery, Department of Surgery, University of Iowa Carver College of Medicine, Iowa City, Iowa, USA
Resource Type: Journal article
Publication Details: Journal of the American Medical Informatics Association : JAMIA, Vol.21(e2), pp.e203-e211
Publisher: England
DOI: 10.1136/amiajnl-2013-002171
PMID: 24444460
PMCID: PMC4173165
ISSN: 1527-974X
eISSN: 1527-974X
Grant note: P30 CA086862 / NCI NIH HHS
Language: English
Date published: 10/2014
Academic Unit: Biostatistics; Holden Comprehensive Cancer Center
Record Identifier: 9983997344902771

Metrics

25 Record Views

28 Times Cited - Web of Science