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

TL;DR

This study demonstrates that machine learning classifiers, trained on virtual patient data, can moderately accurately detect arterial stenosis, with fewer measurements sometimes sufficing and some measurements being more informative.

Contribution

The paper presents a proof of concept showing ML classifiers can detect arterial stenosis using virtual data, outperforming some clinical methods and identifying key measurements.

Findings

ML classifiers achieve >80% specificity and 50-75% sensitivity.

The best classifier has an AUC of 0.75, better than 20 clinical methods.

Few measurements can match the accuracy of using all measurements.

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 50-75%. 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.