Please use this identifier to cite or link to this item: https://doi.org/10.1109/BDCAT.2018.00021
Title: Development of a Radiology Decision Support System for the Classification of MRI Brain Scans
Authors: Zhang, Alwin Yaoxian 
Lam, Sean Shao Wei 
Liu, Nan 
Pang, Yan 
Chan, Ling Ling 
Tang, Phua Hwee 
Keywords: Science & Technology
Technology
Computer Science, Information Systems
Computer Science, Theory & Methods
Computer Science
Machine Learning
Text Analytics
Text Mining
Natural Language Processing
MRI
LIME
Issue Date: 1-Jan-2018
Publisher: IEEE
Citation: Zhang, Alwin Yaoxian, Lam, Sean Shao Wei, Liu, Nan, Pang, Yan, Chan, Ling Ling, Tang, Phua Hwee (2018-01-01). Development of a Radiology Decision Support System for the Classification of MRI Brain Scans. 11th IEEE/ACM International Conference on Utility and Cloud Computing (UCC-Companion) / 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT) : 107-115. ScholarBank@NUS Repository. https://doi.org/10.1109/BDCAT.2018.00021
Abstract: © 2018 IEEE. Previous studies revealed that the ordering of Magnetic resonance imaging (MRI) brain scans following American College of Radiology (ACR) guidelines showed a higher percentage of brain abnormalities compared to scans that do not. As the process of manually labelling patient orders obtained from a local tertiary hospital in accordance to ACR guidelines is intensive and time consuming, this study aims to develop predictive machine learning models; Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF) and XGBoost (XGB), to automate the classification process through text mining methods and derive insights that are useful for future clinical decision-making and resource optimization. Using 1,924 observations as the labelled training data, RF and XGB were found to be the best performing robust models with ROC values of 0.9459 and 0.9508 respectively on the validation set (481 observations). Further exploration into the interpretability of black-box algorithms using the model agnostic LIME (Local Interpretable Model-Agnostic Explanations) framework was used to generate further insights for decisions made using a separate XGB model with respect to individual patients. The LIME framework is a significant first step towards the development of a comprehensive decision support system for patient-level decisions in the ordering of MRI scans.
Source Title: 11th IEEE/ACM International Conference on Utility and Cloud Computing (UCC-Companion) / 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT)
URI: https://scholarbank.nus.edu.sg/handle/10635/157159
ISBN: 9781538655023
DOI: 10.1109/BDCAT.2018.00021
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Development of a Radiology Decision Support System for the Classification of MRI Brain Scans.pdfPublished version800.64 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

34
checked on Nov 14, 2019

Download(s)

2
checked on Nov 14, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.