Citation: Kigka, V.I.; Georga, E.;
Tsakanikas, V.; Kyriakidis, S.;
Tsompou, P.; Siogkas, P.; Michalis,
L.K.; Naka, K.K.; Neglia, D.;
Rocchiccioli, S.; et al. Machine
Learning Coronary Artery Disease
Prediction Based on Imaging and
Non-Imaging Data. Diagnostics 2022,
12, 1466. https://doi.org/10.3390/
diagnostics12061466
Academic Editors: Keun Ho Ryu
and Nipon Theera-Umpon
Received: 15 April 2022
Accepted: 11 June 2022
Published: 14 June 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Machine Learning Coronary Artery Disease Prediction Based on
Imaging and Non-Imaging Data
Vassiliki I. Kigka
1,2
, Eleni Georga
1,2
, Vassilis Tsakanikas
1,2
, Savvas Kyriakidis
1,2
, Panagiota Tsompou
1
,
Panagiotis Siogkas
1,2
, Lampros K. Michalis
3
, Katerina K. Naka
3
, Danilo Neglia
4
, Silvia Rocchiccioli
5
,
Gualtiero Pelosi
5
, Dimitrios I. Fotiadis
1,2
and Antonis Sakellarios
1,2,
*
1
Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and
Engineering, University of Ioannina, GR 45110 Ioannina, Greece; kigkavaso@gmail.com (V.I.K.);
egewrga@gmail.com (E.G.); vasilistsakanikas@gmail.com (V.T.); savvasik21@gmail.com (S.K.);
panagiotatsompou@gmail.com (P.T.); psiogkas4454@gmail.com (P.S.); dimitris.fotiadis30@gmail.com (D.I.F.)
2
Institute of Molecular Biology and Biotechnology, Department of Biomedical Research—FORTH,
University Campus of Ioannina, GR 45110 Ioannina, Greece
3
Department of Cardiology, Medical School, University of Ioannina, GR 45110 Ioannina, Greece;
lamprosmihalis@gmail.com (L.K.M.); drkknaka@gmail.com (K.K.N.)
4
Fondazione Toscana Gabriele Monasterio, IT 56126 Pisa, Italy; dneglia@ftgm.it
5
Institute of Clinical Physiology, National Research Council, IT 56124 Pisa, Italy;
silvia.rocchiccioli@ifc.cnr.it (S.R.); pelosi@ifc.cnr.it (G.P.)
* Correspondence: ansakel13@gmail.com; Tel.: +30-26510-07848
Abstract:
The prediction of obstructive atherosclerotic disease has significant clinical meaning for
the decision making. In this study, a machine learning predictive model based on gradient boosting
classifier is presented, aiming to identify the patients of high CAD risk and those of low CAD risk.
The machine learning methodology includes five steps: the preprocessing of the input data, the
class imbalance handling applying the Easy Ensemble algorithm, the recursive feature elimination
technique implementation, the implementation of gradient boosting classifier, and finally the model
evaluation, while the fine tuning of the presented model was implemented through a randomized
search optimization of the model’s hyper-parameters over an internal 3-fold cross-validation. In total,
187 participants with suspicion of CAD previously underwent CTCA during EVINCI and ARTreat
clinical studies and were prospectively included to undergo follow-up CTCA. The predictive model
was trained using imaging data (geometrical and blood flow based) and non-imaging data. The
overall predictive accuracy of the model was 0.81, using both imaging and non-imaging data. The
innovative aspect of the proposed study is the combination of imaging-based data with the typical
CAD risk factors to provide an integrated CAD risk-predictive model.
Keywords:
coronary artery disease; noninvasive cardiovascular imaging; coronary artery disease
risk stratification; machine learning models
1. Introduction
Atherosclerosis is considered as a chronic inflammatory disease of arteries, and its clin-
ical manifestation accounts for a significant number of deaths worldwide. Atherosclerotic
disease is characterized by the pathologic process of lipid accumulation and inflammation
in the vessel wall, leading to the vessel wall thickening, lumen stenosis, calcification, and
in some cases thrombosis [
1
]. The most important form of atherosclerosis is coronary artery
disease (CAD), which accounts for the largest portion of cardiovascular disease deaths
and leads to narrowing of the arteries that carry blood to the heart muscle [
2
]. The recent
advances in coronary imaging techniques, either invasive or noninvasive, have enabled the
identification of coronary vessels features, which are considered as CAD risk factors.
However, despite the recent technological cardiovascular imaging advancements
to recognize the subclinical disease and the improvement of patient’s management, the
Diagnostics 2022, 12, 1466. https://doi.org/10.3390/diagnostics12061466 https://www.mdpi.com/journal/diagnostics
