A prognostic Bayesian network that makes personalized predictions of poor prognostic outcome post resection of pancreatic ductal adenocarcinoma

Research output: Contribution to journalArticle

Abstract

Background
The narrative surrounding the management of potentially resectable pancreatic cancer is complex. Surgical resection is the only potentially curative treatment. However resection rates are low, the risk of operative morbidity and mortality are high, and survival outcomes remain poor. The aim of this study was to create a prognostic Bayesian network that pre-operatively makes personalized predictions of post-resection survival time of 12months or less and also performs post-operative prognostic updating.

Methods
A Bayesian network was created by synthesizing data from PubMed post-resection survival analysis studies through a two-stage weighting process. Input variables included: inflammatory markers, tumour factors, tumour markers, patient factors and, if applicable, response to neoadjuvant treatment for pre-operative predictions. Prognostic updating was performed by inclusion of post-operative input variables including: pathology results and adjuvant therapy.

Results
77 studies (n = 31,214) were used to create the Bayesian network, which was validated against a prospectively maintained tertiary referral centre database (n = 387). For pre-operative predictions an Area Under the Curve (AUC) of 0.7 (P value: 0.001; 95% CI 0.589–0.801) was achieved accepting up to 4 missing data-points in the dataset. For prognostic updating an AUC 0.8 (P value: 0.000; 95% CI:0.710–0.870) was achieved when validated against a dataset with up to 6 missing pre-operative, and 0 missing post-operative data-points. This dropped to AUC: 0.7 (P value: 0.000; 95% CI:0.667–0.818) when the post-operative validation dataset had up to 2 missing data-points.

Conclusion
This Bayesian network is currently unique in the way it utilizes PubMed and patient level data to translate the existing empirical evidence surrounding potentially resectable pancreatic cancer to make personalized prognostic predictions. We believe such a tool is vital in facilitating better shared decision-making in clinical practice and could be further developed to offer a vehicle for delivering personalized precision medicine in the future.
LanguageEnglish
Article numbere0222270
Number of pages14
JournalPLoS ONE
Volume14
Issue number9
DOIs
Publication statusPublished - 9 Sep 2019

Fingerprint

Bayesian networks
resection
adenocarcinoma
Bayesian Networks
Area Under Curve
Precision Medicine
Adenocarcinoma
Tumor Biomarkers
Updating
Pancreatic Neoplasms
PubMed
pancreatic neoplasms
prediction
Prediction
Missing Data
Curve
Tumor
Cancer
Neoadjuvant Therapy
Survival

Keywords

  • pancreatic cancer
  • pancreatic neoplasms
  • adenocarcinoma
  • neoadjuvant therapy
  • personalized cancer management
  • personalized medicine
  • prognostic health management
  • prognostic model development

Cite this

@article{828bcdf798cf47b2b740da945bb5a5c3,
title = "A prognostic Bayesian network that makes personalized predictions of poor prognostic outcome post resection of pancreatic ductal adenocarcinoma",
abstract = "BackgroundThe narrative surrounding the management of potentially resectable pancreatic cancer is complex. Surgical resection is the only potentially curative treatment. However resection rates are low, the risk of operative morbidity and mortality are high, and survival outcomes remain poor. The aim of this study was to create a prognostic Bayesian network that pre-operatively makes personalized predictions of post-resection survival time of 12months or less and also performs post-operative prognostic updating.MethodsA Bayesian network was created by synthesizing data from PubMed post-resection survival analysis studies through a two-stage weighting process. Input variables included: inflammatory markers, tumour factors, tumour markers, patient factors and, if applicable, response to neoadjuvant treatment for pre-operative predictions. Prognostic updating was performed by inclusion of post-operative input variables including: pathology results and adjuvant therapy.Results77 studies (n = 31,214) were used to create the Bayesian network, which was validated against a prospectively maintained tertiary referral centre database (n = 387). For pre-operative predictions an Area Under the Curve (AUC) of 0.7 (P value: 0.001; 95{\%} CI 0.589–0.801) was achieved accepting up to 4 missing data-points in the dataset. For prognostic updating an AUC 0.8 (P value: 0.000; 95{\%} CI:0.710–0.870) was achieved when validated against a dataset with up to 6 missing pre-operative, and 0 missing post-operative data-points. This dropped to AUC: 0.7 (P value: 0.000; 95{\%} CI:0.667–0.818) when the post-operative validation dataset had up to 2 missing data-points.ConclusionThis Bayesian network is currently unique in the way it utilizes PubMed and patient level data to translate the existing empirical evidence surrounding potentially resectable pancreatic cancer to make personalized prognostic predictions. We believe such a tool is vital in facilitating better shared decision-making in clinical practice and could be further developed to offer a vehicle for delivering personalized precision medicine in the future.",
keywords = "pancreatic cancer, pancreatic neoplasms, adenocarcinoma, neoadjuvant therapy, personalized cancer management, personalized medicine, prognostic health management, prognostic model development",
author = "Alison Bradley and {Van der Meer}, Robert and McKay, {Colin J.}",
year = "2019",
month = "9",
day = "9",
doi = "10.1371/journal.pone.0222270",
language = "English",
volume = "14",
journal = "PLOS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "9",

}

TY - JOUR

T1 - A prognostic Bayesian network that makes personalized predictions of poor prognostic outcome post resection of pancreatic ductal adenocarcinoma

AU - Bradley, Alison

AU - Van der Meer, Robert

AU - McKay, Colin J.

PY - 2019/9/9

Y1 - 2019/9/9

N2 - BackgroundThe narrative surrounding the management of potentially resectable pancreatic cancer is complex. Surgical resection is the only potentially curative treatment. However resection rates are low, the risk of operative morbidity and mortality are high, and survival outcomes remain poor. The aim of this study was to create a prognostic Bayesian network that pre-operatively makes personalized predictions of post-resection survival time of 12months or less and also performs post-operative prognostic updating.MethodsA Bayesian network was created by synthesizing data from PubMed post-resection survival analysis studies through a two-stage weighting process. Input variables included: inflammatory markers, tumour factors, tumour markers, patient factors and, if applicable, response to neoadjuvant treatment for pre-operative predictions. Prognostic updating was performed by inclusion of post-operative input variables including: pathology results and adjuvant therapy.Results77 studies (n = 31,214) were used to create the Bayesian network, which was validated against a prospectively maintained tertiary referral centre database (n = 387). For pre-operative predictions an Area Under the Curve (AUC) of 0.7 (P value: 0.001; 95% CI 0.589–0.801) was achieved accepting up to 4 missing data-points in the dataset. For prognostic updating an AUC 0.8 (P value: 0.000; 95% CI:0.710–0.870) was achieved when validated against a dataset with up to 6 missing pre-operative, and 0 missing post-operative data-points. This dropped to AUC: 0.7 (P value: 0.000; 95% CI:0.667–0.818) when the post-operative validation dataset had up to 2 missing data-points.ConclusionThis Bayesian network is currently unique in the way it utilizes PubMed and patient level data to translate the existing empirical evidence surrounding potentially resectable pancreatic cancer to make personalized prognostic predictions. We believe such a tool is vital in facilitating better shared decision-making in clinical practice and could be further developed to offer a vehicle for delivering personalized precision medicine in the future.

AB - BackgroundThe narrative surrounding the management of potentially resectable pancreatic cancer is complex. Surgical resection is the only potentially curative treatment. However resection rates are low, the risk of operative morbidity and mortality are high, and survival outcomes remain poor. The aim of this study was to create a prognostic Bayesian network that pre-operatively makes personalized predictions of post-resection survival time of 12months or less and also performs post-operative prognostic updating.MethodsA Bayesian network was created by synthesizing data from PubMed post-resection survival analysis studies through a two-stage weighting process. Input variables included: inflammatory markers, tumour factors, tumour markers, patient factors and, if applicable, response to neoadjuvant treatment for pre-operative predictions. Prognostic updating was performed by inclusion of post-operative input variables including: pathology results and adjuvant therapy.Results77 studies (n = 31,214) were used to create the Bayesian network, which was validated against a prospectively maintained tertiary referral centre database (n = 387). For pre-operative predictions an Area Under the Curve (AUC) of 0.7 (P value: 0.001; 95% CI 0.589–0.801) was achieved accepting up to 4 missing data-points in the dataset. For prognostic updating an AUC 0.8 (P value: 0.000; 95% CI:0.710–0.870) was achieved when validated against a dataset with up to 6 missing pre-operative, and 0 missing post-operative data-points. This dropped to AUC: 0.7 (P value: 0.000; 95% CI:0.667–0.818) when the post-operative validation dataset had up to 2 missing data-points.ConclusionThis Bayesian network is currently unique in the way it utilizes PubMed and patient level data to translate the existing empirical evidence surrounding potentially resectable pancreatic cancer to make personalized prognostic predictions. We believe such a tool is vital in facilitating better shared decision-making in clinical practice and could be further developed to offer a vehicle for delivering personalized precision medicine in the future.

KW - pancreatic cancer

KW - pancreatic neoplasms

KW - adenocarcinoma

KW - neoadjuvant therapy

KW - personalized cancer management

KW - personalized medicine

KW - prognostic health management

KW - prognostic model development

U2 - 10.1371/journal.pone.0222270

DO - 10.1371/journal.pone.0222270

M3 - Article

VL - 14

JO - PLOS One

T2 - PLOS One

JF - PLOS One

SN - 1932-6203

IS - 9

M1 - e0222270

ER -