Dataset Information

A predictive Bayesian network that risk stratifies patients undergoing Barrett's surveillance for personalized risk of developing malignancy.

ABSTRACT: BACKGROUND:Barrett's esophagus is strongly associated with esophageal adenocarcinoma. Considering costs and risks associated with invasive surveillance endoscopies better methods of risk stratification are required to assist decision-making and move toward more personalised tailoring of Barrett's surveillance. METHODS:A Bayesian network was created by synthesizing data from published studies analysing risk factors for developing adenocarcinoma in Barrett's oesophagus through a two-stage weighting process. RESULTS:Data was synthesized from 114 studies (n = 394,827) to create the Bayesian network, which was validated against a prospectively maintained institutional database (n = 571). Version 1 contained 10 variables (dysplasia, gender, age, Barrett's segment length, statin use, proton pump inhibitor use, BMI, smoking, aspirin and NSAID use) and achieved AUC of 0.61. Version 2 contained 4 variables with the strongest evidence of association with the development of adenocarcinoma in Barrett's (dysplasia, gender, age, Barrett's segment length) and achieved an AUC 0.90. CONCLUSION:This Bayesian network is unique in the way it utilizes published data to translate the existing empirical evidence surrounding the risk of developing adenocarcinoma in Barrett's esophagus to make personalized risk predictions. Further work is required but this tool marks a vital step towards delivering a more personalized approach to Barrett's surveillance.

SUBMITTER: Bradley A

PROVIDER: S-EPMC7549831 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A predictive Bayesian network that risk stratifies patients undergoing Barrett's surveillance for personalized risk of developing malignancy.

Bradley Alison A Sami Sharukh S N G Hwei H Macleod Anne A Prasanth Manju M Zafar Muneeb M Hemadasa Niroshini N Neagle Gregg G Rosindell Isobelle I Apollos Jeyakumar J

PloS one 20201012 10

<h4>Background</h4>Barrett's esophagus is strongly associated with esophageal adenocarcinoma. Considering costs and risks associated with invasive surveillance endoscopies better methods of risk stratification are required to assist decision-making and move toward more personalised tailoring of Barrett's surveillance.<h4>Methods</h4>A Bayesian network was created by synthesizing data from published studies analysing risk factors for developing adenocarcinoma in Barrett's oesophagus through a two ...[more]

PMID: 33045017

Similar Datasets

Project description:Background and aimsCardiovascular magnetic resonance (CMR) comprehensively assesses aortic stiffness and myocardial ischemia in a single examination. Aortic stiffness represents a subclinical marker of cardiovascular risk in the general population, including patients with diabetes mellitus. However, there is no prognostic data regarding aortic stiffness in patients with diabetes mellitus undergoing stress perfusion CMR.MethodsConsecutive patients with diabetes mellitus with suspected myocardial ischemia referred for adenosine stress perfusion CMR with aortic pulse wave velocity (PWV) during 2010-2013 were studied. The primary outcome was major adverse cardiovascular events (MACE), defined as the composite of cardiac mortality, nonfatal myocardial infarction (MI), hospitalization for heart failure, coronary revascularization (> 90 days post-CMR), and ischemic stroke. The secondary outcome was hard cardiac events, defined as the composite of cardiac mortality and nonfatal MI.ResultsA total of 424 patients (median follow-up 7.2 years) were included. The mean PWV was 12.16 ± 6.28 m/s. MACE and hard cardiac events occurred in 26.8% and 9.4% of patients, respectively. Patients with elevated PWV (> 12.16 m/s) had a significantly higher incidence of MACE (HR 2.14 [95%CI 1.48, 3.09], p < 0.001) and hard cardiac events (HR 2.69 [95%CI 1.42, 5.10], p = 0.002) compared to those with non-elevated PWV. Multivariable analysis demonstrated that PWV independently predicts MACE (p = 0.003) and hard cardiac events (p = 0.01). Addition of PWV provided incremental prognostic value beyond clinical data, left ventricular mass index, myocardial ischemia, and late gadolinium enhancement in predicting MACE (incremental χ² 7.54, p = 0.006) and hard cardiac events (incremental χ² 5.99, p = 0.01).ConclusionsAortic stiffness measured by CMR independently predicts MACE and hard cardiac events and confers significant incremental prognostic value in patients with diabetes mellitus with suspected myocardial ischemia. Aortic stiffness measurement could potentially be considered as part of a stress perfusion CMR protocol to enhance risk prediction in patients with diabetes mellitus.

Dataset Information

A predictive Bayesian network that risk stratifies patients undergoing Barrett's surveillance for personalized risk of developing malignancy.

Publications

A predictive Bayesian network that risk stratifies patients undergoing Barrett's surveillance for personalized risk of developing malignancy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets