Personalized pancreatic cancer management: a systematic review of how machine learning is supporting decision-making

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This review critically analyzes how machine learning is being utilized to support clinical decision-making in the management of potentially resectable pancreatic cancer. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, electronic searches of MEDLINE, Embase, PubMed and Cochrane Database were undertaken. Studies were assessed using the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies (CHARMS) checklist. In total 89,959 citations were retrieved.

Six studies met the inclusion criteria. Three studies were Markov decision-analysis models comparing neoadjuvant therapy versus upfront surgery. Three studies predicted survival time using Bayesian modeling (n = 1), Artificial Neural Network (n = 1), and one study explored machine learning algorithms including: Bayesian Network, decision trees, nearest neighbor, and Artificial Neural Networks.

The main methodological issues identified were: limited data sources which limits generalizability and potentiates bias, lack of external validation, and the need for transparency in methods of internal validation, consecutive sampling, and selection of candidate predictors.

The future direction of research relies on expanding our view of the multidisciplinary team to include professionals from computing and data science with algorithms developed in conjunction with clinicians and viewed as aids, not replacement, to traditional clinical decision making.
LanguageEnglish
Pages598-604
Number of pages7
JournalPancreas
Volume48
Issue number5
DOIs
Publication statusPublished - 1 May 2019

Fingerprint

Checklist
Pancreatic Neoplasms
Learning systems
Decision Making
Cancer
Machine Learning
Decision making
Decision Trees
Neoadjuvant Therapy
Artificial Neural Network
Decision Support Techniques
Information Storage and Retrieval
PubMed
MEDLINE
Neural networks
Meta-Analysis
Bayesian Modeling
Decision Analysis
Decision theory
Survival Time

Keywords

  • pancreatic cancer
  • personalised medicine
  • machine learning
  • decision making

Cite this

@article{cdb1180175c840cdacf5f374a88b19f3,
title = "Personalized pancreatic cancer management: a systematic review of how machine learning is supporting decision-making",
abstract = "This review critically analyzes how machine learning is being utilized to support clinical decision-making in the management of potentially resectable pancreatic cancer. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, electronic searches of MEDLINE, Embase, PubMed and Cochrane Database were undertaken. Studies were assessed using the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies (CHARMS) checklist. In total 89,959 citations were retrieved. Six studies met the inclusion criteria. Three studies were Markov decision-analysis models comparing neoadjuvant therapy versus upfront surgery. Three studies predicted survival time using Bayesian modeling (n = 1), Artificial Neural Network (n = 1), and one study explored machine learning algorithms including: Bayesian Network, decision trees, nearest neighbor, and Artificial Neural Networks.The main methodological issues identified were: limited data sources which limits generalizability and potentiates bias, lack of external validation, and the need for transparency in methods of internal validation, consecutive sampling, and selection of candidate predictors.The future direction of research relies on expanding our view of the multidisciplinary team to include professionals from computing and data science with algorithms developed in conjunction with clinicians and viewed as aids, not replacement, to traditional clinical decision making.",
keywords = "pancreatic cancer, personalised medicine, machine learning, decision making",
author = "Alison Bradley and {Van Der Meer}, Robert and Colin McKay",
year = "2019",
month = "5",
day = "1",
doi = "10.1097/MPA.0000000000001312",
language = "English",
volume = "48",
pages = "598--604",
journal = "Pancreas",
issn = "0885-3177",
number = "5",

}

Personalized pancreatic cancer management : a systematic review of how machine learning is supporting decision-making. / Bradley, Alison; Van Der Meer, Robert; McKay, Colin.

In: Pancreas, Vol. 48, No. 5, 01.05.2019, p. 598-604.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Personalized pancreatic cancer management

T2 - Pancreas

AU - Bradley, Alison

AU - Van Der Meer, Robert

AU - McKay, Colin

PY - 2019/5/1

Y1 - 2019/5/1

N2 - This review critically analyzes how machine learning is being utilized to support clinical decision-making in the management of potentially resectable pancreatic cancer. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, electronic searches of MEDLINE, Embase, PubMed and Cochrane Database were undertaken. Studies were assessed using the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies (CHARMS) checklist. In total 89,959 citations were retrieved. Six studies met the inclusion criteria. Three studies were Markov decision-analysis models comparing neoadjuvant therapy versus upfront surgery. Three studies predicted survival time using Bayesian modeling (n = 1), Artificial Neural Network (n = 1), and one study explored machine learning algorithms including: Bayesian Network, decision trees, nearest neighbor, and Artificial Neural Networks.The main methodological issues identified were: limited data sources which limits generalizability and potentiates bias, lack of external validation, and the need for transparency in methods of internal validation, consecutive sampling, and selection of candidate predictors.The future direction of research relies on expanding our view of the multidisciplinary team to include professionals from computing and data science with algorithms developed in conjunction with clinicians and viewed as aids, not replacement, to traditional clinical decision making.

AB - This review critically analyzes how machine learning is being utilized to support clinical decision-making in the management of potentially resectable pancreatic cancer. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, electronic searches of MEDLINE, Embase, PubMed and Cochrane Database were undertaken. Studies were assessed using the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies (CHARMS) checklist. In total 89,959 citations were retrieved. Six studies met the inclusion criteria. Three studies were Markov decision-analysis models comparing neoadjuvant therapy versus upfront surgery. Three studies predicted survival time using Bayesian modeling (n = 1), Artificial Neural Network (n = 1), and one study explored machine learning algorithms including: Bayesian Network, decision trees, nearest neighbor, and Artificial Neural Networks.The main methodological issues identified were: limited data sources which limits generalizability and potentiates bias, lack of external validation, and the need for transparency in methods of internal validation, consecutive sampling, and selection of candidate predictors.The future direction of research relies on expanding our view of the multidisciplinary team to include professionals from computing and data science with algorithms developed in conjunction with clinicians and viewed as aids, not replacement, to traditional clinical decision making.

KW - pancreatic cancer

KW - personalised medicine

KW - machine learning

KW - decision making

U2 - 10.1097/MPA.0000000000001312

DO - 10.1097/MPA.0000000000001312

M3 - Article

VL - 48

SP - 598

EP - 604

JO - Pancreas

JF - Pancreas

SN - 0885-3177

IS - 5

ER -