Article (Scientific journals)
Machine Learning-Based Algorithm to Predict Procedural Success in a Large European Cohort of Hybrid Chronic Total Occlusion Percutaneous Coronary Interventions.
Moroni, Alice; Mascaretti, Andrea; Dens, Jo et al.
2025In American Journal of Cardiology, 248, p. 50 - 57
Peer Reviewed verified by ORBi
 

Files


Full Text
Machine Learning-Based Algorithm to Predict Procedural Success CTO Am J Cardiology 2025.pdf
Author postprint (1.09 MB)
Request a copy

All documents in ORBi UMONS are protected by a user license.

Send to



Details



Keywords :
artificial intelligence; chronic total occlusion; machine learning; percutaneous coronary intervention; procedural success; Aged; Female; Humans; Male; Middle Aged; Chronic Disease; Coronary Angiography; Europe/epidemiology; ROC Curve; Treatment Outcome; Algorithms; Coronary Occlusion/surgery; Coronary Occlusion/diagnostic imaging; Coronary Occlusion/diagnosis; Machine Learning; Percutaneous Coronary Intervention/methods; Coronary Occlusion; Europe; Retrospective Studies; Cardiology and Cardiovascular Medicine
Abstract :
[en] CTOs are frequently encountered in patients undergoing invasive coronary angiography. Even though technical progress in CTO-PCI and enhanced skills of dedicated operators have led to substantial procedural improvement, the success of the intervention is still lower than in non-CTO PCI. Moreover, the scores developed to appraise lesion complexity and predict procedural outcomes have shown suboptimal discriminatory performance when applied to unselected cohorts. Accordingly, we sought to develop a machine learning (ML)-based model integrating clinical and angiographic characteristics to predict procedural success of chronic total occlusion (CTO)-percutaneous coronary intervention(PCI). Different ML-models were trained on a European multicenter cohort of 8904 patients undergoing attempted CTO-PCI according to the hybrid algorithm (randomly divided into a training set [75%] and a test set [25%]). Sixteen clinical and 16 angiographic variables routinely assessed were used to inform the models; procedural volume of each center was also considered together with 3 angiographic complexity scores (namely, J-CTO, PROGRESS-CTO and RECHARGE scores). The area under the curve (AUC) of the receiver operating characteristic curve was employed, as metric score. The performance of the model was also compared with that of 3 existing complexity scores. The best selected ML-model (Light Gradient Boosting Machine [LightGBM]) for procedural success prediction showed an AUC of 0.82 and 0.73 in the training and test set, respectively. The accuracy of the ML-based model outperformed those of the conventional scores (J-CTO AUC 0.66, PROGRESS-CTO AUC 0.62, RECHARGE AUC 0.64, p-value <0.01 for all the pairwise comparisons). In conclusion, the implementation of a ML-based model to predict procedural success in CTO-PCIs showed good prediction accuracy, thus potentially providing new elements for a tailored management. Prospective validation studies should be conducted in real-world settings, integrating ML-based model into operator decision-making processes in order to validate this new approach.
Precision for document type :
Review article
Disciplines :
Cardiovascular & respiratory systems
Author, co-author :
Moroni, Alice ;  HartCentrum Bonheiden-Lier, Imelda Hospital, Bonheiden, Belgium
Mascaretti, Andrea;  Department of Theoretical and Scientific Data Science, Scuola Superiore Internazionale di Studi Avanzati, Trieste, Italy
Dens, Jo;  Department of Cardiology, Ziekenhuis Oost-Limburg, Genk, Belgium
Knaapen, Paul;  Department of Cardiology, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
Nap, Alexander;  Department of Cardiology, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
Somsen, Yvemarie B O;  Department of Cardiology, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
Bennett, Johan;  Department of Cardiovascular Medicine, UZ Leuven, Leuven, Belgium
Ungureanu, Claudiu;  Department of Cardiology, Hôpital de Jolimont, La Louvière, Belgium
Bataille, Yoann;  Department of Cardiology, Jessa Ziekenhuis, Hasselt, Belgium
Haine, Steven;  Department of Cardiology, Antwerp University Hospital, Edegem, and University of Antwerp, Belgium
Coussement, Patrick;  Department of Cardiology, AZ Sint-Jan Brugge, Brugge, Belgium
Kayaert, Peter;  Department of Cardiology, Jessa Ziekenhuis, Hasselt, Belgium
Avran, Alexander;  Department of Interventional Cardiology, Valenciennes Hospital, Valenciennes, France
Sonck, Jeroen;  Cardiovascular Center Aalst, OLV-Clinic, Aalst, Belgium
Collet, Carlos;  Cardiovascular Center Aalst, OLV-Clinic, Aalst, Belgium
Carlier, Stéphane  ;  Université de Mons - UMONS > Faculté de Médecine et de Pharmacie > Service de Cardiologie
Vescovo, Giovanni;  Interventional Cardiology, Department of Cardio-Thoracic and Vascular Sciences, Ospedale dell'Angelo, Venice, Italy
Avesani, Giacomo;  Department of Imaging and Radiation Oncology, Fondazione Policlinico A. Gemelli IRCCS, Rome, Italy
Egred, Mohaned;  Department of Cardiology, Freeman Hospital, Newcastle upon Tyne, United Kingdom
Spratt, James C;  Department of Interventional Cardiology, St. George's, University of London, London, United Kingdom
Diletti, Roberto;  Department of Cardiology, Thorax Center, Erasmus MC Cardiovascular Institute, Rotterdam, the Netherlands
Goktekin, Omer;  Memorial Bahcelievler Hospital, Istanbul, Turkey
Boudou, Nicolas;  Interventional Cardiology Department, Clinique Saint-Augustin-Elsan, Bordeaux, France
Di Mario, Carlo;  Structural Interventional Cardiology, Department of Clinical & Experimental Medicine, Careggi University Hospital, Florence, Italy
Mashayekhi, Kambis;  Department of Cardiology and Angiology, II University Heart Center, Freiburg Bad Krozingen, Germany
Agostoni, Pierfrancesco;  HartCentrum, Ziekenhuis aan de Stroom (ZAS) Middelheim, Antwerp, Belgium
Zivelonghi, Carlo ;  HartCentrum, Ziekenhuis aan de Stroom (ZAS) Middelheim, Antwerp, Belgium. Electronic address: carlo.zivelonghi@gmail.com
More authors (17 more) Less
Language :
English
Title :
Machine Learning-Based Algorithm to Predict Procedural Success in a Large European Cohort of Hybrid Chronic Total Occlusion Percutaneous Coronary Interventions.
Publication date :
01 August 2025
Journal title :
American Journal of Cardiology
ISSN :
0002-9149
eISSN :
1879-1913
Publisher :
Elsevier Inc., United States
Volume :
248
Pages :
50 - 57
Peer reviewed :
Peer Reviewed verified by ORBi
Research unit :
M106 - Cardiologie
Research institute :
R550 - Institut des Sciences et Technologies de la Santé
Available on ORBi UMONS :
since 09 July 2025

Statistics


Number of views
21 (5 by UMONS)
Number of downloads
0 (0 by UMONS)

Scopus citations®
 
0
Scopus citations®
without self-citations
0
OpenCitations
 
0
OpenAlex citations
 
0

Bibliography


Similar publications



Contact ORBi UMONS