No Cover Image

Journal article 79 views 27 downloads

A proof of concept study for machine learning application to stenosis detection

Gareth Jones, Jim Parr, Perumal Nithiarasu Orcid Logo, Sanjay Pant Orcid Logo

Medical & Biological Engineering & Computing, Volume: 59, Issue: 10, Pages: 2085 - 2114

Swansea University Authors: Perumal Nithiarasu Orcid Logo, Sanjay Pant Orcid Logo

  • 57550.pdf

    PDF | Version of Record

    © The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License

    Download (1.89MB)

Abstract

This proof of concept (PoC) assesses the ability of machine learning (ML) classifiers to predict the presence of a stenosis in a three vessel arterial system consisting of the abdominal aorta bifurcating into the two common iliacs. A virtual patient database (VPD) is created using one-dimensional pu...

Full description

Published in: Medical & Biological Engineering & Computing
ISSN: 0140-0118 1741-0444
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57550
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: This proof of concept (PoC) assesses the ability of machine learning (ML) classifiers to predict the presence of a stenosis in a three vessel arterial system consisting of the abdominal aorta bifurcating into the two common iliacs. A virtual patient database (VPD) is created using one-dimensional pulse wave propagation model of haemodynamics. Four different machine learning (ML) methods are used to train and test a series of classifiers—both binary and multiclass—to distinguish between healthy and unhealthy virtual patients (VPs) using different combinations of pressure and flow-rate measurements. It is found that the ML classifiers achieve specificities larger than 80% and sensitivities ranging from 50 to 75%. The most balanced classifier also achieves an area under the receiver operative characteristic curve of 0.75, outperforming approximately 20 methods used in clinical practice, and thus placing the method as moderately accurate. Other important observations from this study are that (i) few measurements can provide similar classification accuracies compared to the case when more/all the measurements are used; (ii) some measurements are more informative than others for classification; and (iii) a modification of standard methods can result in detection of not only the presence of stenosis, but also the stenosed vessel.
Keywords: Arterial disease diagnosis; Machine learning; Virtual patient database; Pulse wave haemodynamics
College: College of Engineering
Funders: This work is supported by an Engineering and Physical Science Research Council studentship ref. EP/N509553/1 and an Engineering and Physical Science Research Council grant ref. EP/R010811/1.
Issue: 10
Start Page: 2085
End Page: 2114