Prediction of patients at high risk of upper gastrointestinal cancer for endoscopy using artificial intelligent technology

Lin, Y; Liu, Y; Chen, H; Lin, D; He, X

Prediction of patients at high risk of upper gastrointestinal cancer for endoscopy using artificial intelligent technology

Lin, Y

Liu, Y Chen, H Lin, D He, X

Permalink

Publisher:: Elsevier
Publication Type:: Conference Proceeding
Citation:: Annals of Oncology, 2021
Issue Date:: 2021-06-30

Closed Access

	Filename	Description	Size
	PD-6 Prediction of patients at high risk of upper gastrointestinal cancer for endoscopy using artificial intelligent technology - Annals of Oncology.pdf	Published version	101.01 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lin, Y https://orcid.org/0000-0002-4637-9701
dc.contributor.author	Liu, Y
dc.contributor.author	Chen, H
dc.contributor.author	Lin, D
dc.contributor.author	He, X
dc.date	2021-06-30
dc.date.accessioned	2021-07-06T13:31:38Z
dc.date.available	2021-04-16
dc.date.available	2021-07-06T13:31:38Z
dc.date.issued	2021-06-30
dc.identifier.citation	Annals of Oncology, 2021
dc.identifier.issn	0923-7534
dc.identifier.uri	http://hdl.handle.net/10453/149841
dc.description.abstract	Background: Endoscopic screening for early detection of upper gastrointestinal (UGI) cancer (oesophageal and stomach cancer) is important. However, population-based endoscopic screening is difficult to implement in populous countries. By identifying high-risk individuals from the general population, the screening targets can be narrowed to individuals who are in most need of an endoscopy. This study was designed to develop an artificial intelligence-based model to predict patient risk of UGI lesions to identify high-risk individuals for endoscopy. Methods: A total of 620 patients (from 5300 participants), 187 in normal group and 433 in lesion group, were equally allocated into 10 parts for 10-fold cross validation experiments. The machine-learning predictive models for UGI lesion risk were constructed using random forest, logistic regression, decision tree, and support vector machine (SVM) algorithms. A total of 48 variables covering lifestyles, social-economic status, clinical symptoms, serological results, and pathological data were used in the model construction. Results: The accuracies of the four models were between 79.3% and 93.4% in the training set and between 77.2% and 91.2% in the testing dataset (logistics regression:77.2%; decision tree:87.3%; random forest:88.2%; SVM:91.2%;). The AUCs of four models showed impressive predictive ability. Comparing the 4 models with the different algorithms, the SVM model featured the best sensitivity and specificity in all datasets tested. Conclusions: Machine-learning algorithms can accurately and reliably predict the risk of upper gastrointestinal cancer based on readily available parameters. The predictive models have the potential to be used clinically for identifying patients with high risk of UGI cancers and stratifying patients for necessary endoscopic screening.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Annals of Oncology
dc.relation.ispartof	The 22nd World Congress on Gastrointestinal Cancer
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	1112 Oncology and Carcinogenesis
dc.subject.classification	Oncology & Carcinogenesis
dc.title	Prediction of patients at high risk of upper gastrointestinal cancer for endoscopy using artificial intelligent technology
dc.type	Conference Proceeding
utslib.location.activity	Virtual
utslib.for	1112 Oncology and Carcinogenesis
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Life Sciences
utslib.copyright.status	closed_access	*
pubs.consider-herdc	true
dc.date.updated	2021-07-06T13:31:37Z
pubs.finish-date	2021-07-03
pubs.publication-status	Accepted
pubs.start-date	2021-06-30

Abstract:

Background: Endoscopic screening for early detection of upper gastrointestinal (UGI) cancer (oesophageal and stomach cancer) is important. However, population-based endoscopic screening is difficult to implement in populous countries. By identifying high-risk individuals from the general population, the screening targets can be narrowed to individuals who are in most need of an endoscopy. This study was designed to develop an artificial intelligence-based model to predict patient risk of UGI lesions to identify high-risk individuals for endoscopy. Methods: A total of 620 patients (from 5300 participants), 187 in normal group and 433 in lesion group, were equally allocated into 10 parts for 10-fold cross validation experiments. The machine-learning predictive models for UGI lesion risk were constructed using random forest, logistic regression, decision tree, and support vector machine (SVM) algorithms. A total of 48 variables covering lifestyles, social-economic status, clinical symptoms, serological results, and pathological data were used in the model construction. Results: The accuracies of the four models were between 79.3% and 93.4% in the training set and between 77.2% and 91.2% in the testing dataset (logistics regression:77.2%; decision tree:87.3%; random forest:88.2%; SVM:91.2%;). The AUCs of four models showed impressive predictive ability. Comparing the 4 models with the different algorithms, the SVM model featured the best sensitivity and specificity in all datasets tested. Conclusions: Machine-learning algorithms can accurately and reliably predict the risk of upper gastrointestinal cancer based on readily available parameters. The predictive models have the potential to be used clinically for identifying patients with high risk of UGI cancers and stratifying patients for necessary endoscopic screening.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/149841