Personalized prognostic bayesian network for pancreatic cancer: delivering personalized pancreatic cancer management throughout the patient journey

Alison Bradley, Robert Van der Meer, Colin McKay, Nigel Jamieson

Research output: Contribution to journalMeeting abstract

3 Citations (Scopus)

Abstract

Background and Objectives:
The aim of this study is to create the first Personalized Prognostic Bayesian Network for Pancreatic Cancer (PPBN-PC) to provide personalized predictions of 3-year or more survival time post resection. PPBN-PC’s ability to handle the dynamic nature of the care processes, with predictions evolving as more information becomes available, was assessed at the pre and post-operative stage of the patient journey.

Materials and Methods:
Parent nodes were identified from PubMed survival analysis studies (n=48691) and included: tumour factors, patient factors, tumour markers, inflammatory markers, neoadjuvant therapy, pathology and adjuvant therapy. Variables underwent a two-stage weighting process to summarise both the weight of the evidence against conflicting findings and a normalized weighting process placing each variable’s weighting within the entirety of the existing body of evidence. Priors for the model were calculated using the normalized weight for each variable as the weighted mean of the TNormal distribution for the corresponding parent node.

Results:
The PPBN-PC was validated against a dataset of 365 patients who presented to a tertiary referral centre with potentially resectable pancreatic cancer. Model performance measured by Area Under the Curve (AUC) ranged from 0.94 (P-value 0.002; 95% CI 0.859-1.000) for 0 missing data points to AUC 0.74 (P-value 0.000; 95% CI 0.660-0.809) accepting more than 4 missing data points in the validation dataset, for accuracy of pre-operative predictions. PPBN-PC performance for prognostic updating based on post-operatively available information ranged from AUC 0.97 (P-value 0.000; 95% CI 0.908-1.000) for 0 missing data points in pre and post-operative validation dataset to AUC 0.75 (P-value 0.000; 95% CI 0.655-0.838) accepting more than 4 missing data points in the pre and up to and including 2 missing data points in the post-operative validation dataset. The latter was the only point at which AUC fell below 0.80. Validated against every other combination of missing pre and post-operative data points PPBN-PC maintained an AUC greater than 0.8 (range 0.97-0.80) with P-value consistently below 0.001.

Conclusion:
This marks an important step towards achieving the delivery of precision medicine, as the next step will be to incorporated genomic data into the model hence combining genetic, pathology and clinical data, creating a vehicle to deliver personalized precision medicine.
LanguageEnglish
Article numberP1-40
PagesS31-S32
Number of pages2
JournalPancreatology
Volume19
Issue numberS1
DOIs
Publication statusPublished - 5 Jun 2019
Event51st Annual Meeting of the European Pancreatic Club - Grieghallen, Bergen, Norway
Duration: 26 Jun 201929 Jun 2019
https://epc2019.no/welcome/

Fingerprint

Bayesian Networks
Pancreatic Neoplasms
Area Under Curve
Cancer
Missing Data
Precision Medicine
Curve
Weighting
Medicine
Therapy
Prediction
Tumor
Weights and Measures
Clinical Pathology
Neoadjuvant Therapy
Weighted Mean
Survival Analysis
Tumor Biomarkers
PubMed
Tertiary Care Centers

Keywords

  • pancreatic cancer
  • bayesian network
  • personalized medicine
  • prognostic model development
  • prognostic health management
  • personalized cancer management

Cite this

@article{bcbdd278501045549042cf1caf3197c2,
title = "Personalized prognostic bayesian network for pancreatic cancer: delivering personalized pancreatic cancer management throughout the patient journey",
abstract = "Background and Objectives:The aim of this study is to create the first Personalized Prognostic Bayesian Network for Pancreatic Cancer (PPBN-PC) to provide personalized predictions of 3-year or more survival time post resection. PPBN-PC’s ability to handle the dynamic nature of the care processes, with predictions evolving as more information becomes available, was assessed at the pre and post-operative stage of the patient journey.Materials and Methods:Parent nodes were identified from PubMed survival analysis studies (n=48691) and included: tumour factors, patient factors, tumour markers, inflammatory markers, neoadjuvant therapy, pathology and adjuvant therapy. Variables underwent a two-stage weighting process to summarise both the weight of the evidence against conflicting findings and a normalized weighting process placing each variable’s weighting within the entirety of the existing body of evidence. Priors for the model were calculated using the normalized weight for each variable as the weighted mean of the TNormal distribution for the corresponding parent node.Results:The PPBN-PC was validated against a dataset of 365 patients who presented to a tertiary referral centre with potentially resectable pancreatic cancer. Model performance measured by Area Under the Curve (AUC) ranged from 0.94 (P-value 0.002; 95{\%} CI 0.859-1.000) for 0 missing data points to AUC 0.74 (P-value 0.000; 95{\%} CI 0.660-0.809) accepting more than 4 missing data points in the validation dataset, for accuracy of pre-operative predictions. PPBN-PC performance for prognostic updating based on post-operatively available information ranged from AUC 0.97 (P-value 0.000; 95{\%} CI 0.908-1.000) for 0 missing data points in pre and post-operative validation dataset to AUC 0.75 (P-value 0.000; 95{\%} CI 0.655-0.838) accepting more than 4 missing data points in the pre and up to and including 2 missing data points in the post-operative validation dataset. The latter was the only point at which AUC fell below 0.80. Validated against every other combination of missing pre and post-operative data points PPBN-PC maintained an AUC greater than 0.8 (range 0.97-0.80) with P-value consistently below 0.001.Conclusion:This marks an important step towards achieving the delivery of precision medicine, as the next step will be to incorporated genomic data into the model hence combining genetic, pathology and clinical data, creating a vehicle to deliver personalized precision medicine.",
keywords = "pancreatic cancer, bayesian network, personalized medicine, prognostic model development, prognostic health management, personalized cancer management",
author = "Alison Bradley and {Van der Meer}, Robert and Colin McKay and Nigel Jamieson",
year = "2019",
month = "6",
day = "5",
doi = "10.1016/j.pan.2019.05.077",
language = "English",
volume = "19",
pages = "S31--S32",
number = "S1",

}

Personalized prognostic bayesian network for pancreatic cancer : delivering personalized pancreatic cancer management throughout the patient journey. / Bradley, Alison; Van der Meer, Robert; McKay, Colin; Jamieson, Nigel.

Vol. 19, No. S1, P1-40, 05.06.2019, p. S31-S32.

Research output: Contribution to journalMeeting abstract

TY - JOUR

T1 - Personalized prognostic bayesian network for pancreatic cancer

T2 - delivering personalized pancreatic cancer management throughout the patient journey

AU - Bradley, Alison

AU - Van der Meer, Robert

AU - McKay, Colin

AU - Jamieson, Nigel

PY - 2019/6/5

Y1 - 2019/6/5

N2 - Background and Objectives:The aim of this study is to create the first Personalized Prognostic Bayesian Network for Pancreatic Cancer (PPBN-PC) to provide personalized predictions of 3-year or more survival time post resection. PPBN-PC’s ability to handle the dynamic nature of the care processes, with predictions evolving as more information becomes available, was assessed at the pre and post-operative stage of the patient journey.Materials and Methods:Parent nodes were identified from PubMed survival analysis studies (n=48691) and included: tumour factors, patient factors, tumour markers, inflammatory markers, neoadjuvant therapy, pathology and adjuvant therapy. Variables underwent a two-stage weighting process to summarise both the weight of the evidence against conflicting findings and a normalized weighting process placing each variable’s weighting within the entirety of the existing body of evidence. Priors for the model were calculated using the normalized weight for each variable as the weighted mean of the TNormal distribution for the corresponding parent node.Results:The PPBN-PC was validated against a dataset of 365 patients who presented to a tertiary referral centre with potentially resectable pancreatic cancer. Model performance measured by Area Under the Curve (AUC) ranged from 0.94 (P-value 0.002; 95% CI 0.859-1.000) for 0 missing data points to AUC 0.74 (P-value 0.000; 95% CI 0.660-0.809) accepting more than 4 missing data points in the validation dataset, for accuracy of pre-operative predictions. PPBN-PC performance for prognostic updating based on post-operatively available information ranged from AUC 0.97 (P-value 0.000; 95% CI 0.908-1.000) for 0 missing data points in pre and post-operative validation dataset to AUC 0.75 (P-value 0.000; 95% CI 0.655-0.838) accepting more than 4 missing data points in the pre and up to and including 2 missing data points in the post-operative validation dataset. The latter was the only point at which AUC fell below 0.80. Validated against every other combination of missing pre and post-operative data points PPBN-PC maintained an AUC greater than 0.8 (range 0.97-0.80) with P-value consistently below 0.001.Conclusion:This marks an important step towards achieving the delivery of precision medicine, as the next step will be to incorporated genomic data into the model hence combining genetic, pathology and clinical data, creating a vehicle to deliver personalized precision medicine.

AB - Background and Objectives:The aim of this study is to create the first Personalized Prognostic Bayesian Network for Pancreatic Cancer (PPBN-PC) to provide personalized predictions of 3-year or more survival time post resection. PPBN-PC’s ability to handle the dynamic nature of the care processes, with predictions evolving as more information becomes available, was assessed at the pre and post-operative stage of the patient journey.Materials and Methods:Parent nodes were identified from PubMed survival analysis studies (n=48691) and included: tumour factors, patient factors, tumour markers, inflammatory markers, neoadjuvant therapy, pathology and adjuvant therapy. Variables underwent a two-stage weighting process to summarise both the weight of the evidence against conflicting findings and a normalized weighting process placing each variable’s weighting within the entirety of the existing body of evidence. Priors for the model were calculated using the normalized weight for each variable as the weighted mean of the TNormal distribution for the corresponding parent node.Results:The PPBN-PC was validated against a dataset of 365 patients who presented to a tertiary referral centre with potentially resectable pancreatic cancer. Model performance measured by Area Under the Curve (AUC) ranged from 0.94 (P-value 0.002; 95% CI 0.859-1.000) for 0 missing data points to AUC 0.74 (P-value 0.000; 95% CI 0.660-0.809) accepting more than 4 missing data points in the validation dataset, for accuracy of pre-operative predictions. PPBN-PC performance for prognostic updating based on post-operatively available information ranged from AUC 0.97 (P-value 0.000; 95% CI 0.908-1.000) for 0 missing data points in pre and post-operative validation dataset to AUC 0.75 (P-value 0.000; 95% CI 0.655-0.838) accepting more than 4 missing data points in the pre and up to and including 2 missing data points in the post-operative validation dataset. The latter was the only point at which AUC fell below 0.80. Validated against every other combination of missing pre and post-operative data points PPBN-PC maintained an AUC greater than 0.8 (range 0.97-0.80) with P-value consistently below 0.001.Conclusion:This marks an important step towards achieving the delivery of precision medicine, as the next step will be to incorporated genomic data into the model hence combining genetic, pathology and clinical data, creating a vehicle to deliver personalized precision medicine.

KW - pancreatic cancer

KW - bayesian network

KW - personalized medicine

KW - prognostic model development

KW - prognostic health management

KW - personalized cancer management

U2 - 10.1016/j.pan.2019.05.077

DO - 10.1016/j.pan.2019.05.077

M3 - Meeting abstract

VL - 19

SP - S31-S32

IS - S1

M1 - P1-40

ER -