Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 31;4(6):433-443.
doi: 10.1093/ehjdh/ztad051. eCollection 2023 Dec.

Predicting target lesion failure following percutaneous coronary intervention through machine learning risk assessment models

Mamas A Mamas  1 , Marco Roffi  2 , Ole Fröbert  3 , Alaide Chieffo  4 , Alessandro Beneduce  4 , Andrija Matetic  1   5 , Pim A L Tonino  6 , Dragica Paunovic  7 , Lotte Jacobs  8 , Roxane Debrus  9 , Jérémy El Aissaoui  10 , Frank van Leeuwen  8 , Evangelos Kontopantelis  11
Affiliations

Predicting target lesion failure following percutaneous coronary intervention through machine learning risk assessment models

Mamas A Mamas et al. Eur Heart J Digit Health. .

Abstract

Aims: Central to the practice of precision medicine in percutaneous coronary intervention (PCI) is a risk-stratification tool to predict outcomes following the procedure. This study is intended to assess machine learning (ML)-based risk models to predict clinically relevant outcomes in PCI and to support individualized clinical decision-making in this setting.

Methods and results: Five different ML models [gradient boosting classifier (GBC), linear discrimination analysis, Naïve Bayes, logistic regression, and K-nearest neighbours algorithm) for the prediction of 1-year target lesion failure (TLF) were trained on an extensive data set of 35 389 patients undergoing PCI and enrolled in the global, all-comers e-ULTIMASTER registry. The data set was split into a training (80%) and a test set (20%). Twenty-three patient and procedural characteristics were used as predictive variables. The models were compared for discrimination according to the area under the receiver operating characteristic curve (AUC) and for calibration. The GBC model showed the best discriminative ability with an AUC of 0.72 (95% confidence interval 0.69-0.75) for 1-year TLF on the test set. The discriminative ability of the GBC model for the components of TLF was highest for cardiac death with an AUC of 0.82, followed by target vessel myocardial infarction with an AUC of 0.75 and clinically driven target lesion revascularization with an AUC of 0.68. The calibration was fair until the highest risk deciles showed an underestimation of the risk.

Conclusion: Machine learning-derived predictive models provide a reasonably accurate prediction of 1-year TLF in patients undergoing PCI. A prospective evaluation of the predictive score is warranted.

Registration: Clinicaltrial.gov identifier is NCT02188355.

Keywords: Drug-eluting stent; Machine learning; Outcomes; Percutaneous coronary intervention; Target lesion failure.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: M.A.M. receives unrestricted educational grant and consulting fees from Terumo; M.R. receives unrestricted educational grant from Terumo, Cordis/Cardinal Health, Medtronic, and Biotronik; O.F. receives speaker fees from Sanofi Pasteur; A.C. receives speaker fees from Abbott Vascular, Biosensor, and Boston Scientific, as well as consulting fees from Abiomed and Shock Wave Medical; D.P. is a former employee of Terumo Europe NV (Belgium); L.J. is an employee of Terumo Europe NV (Belgium); R.D. is a former employee of Terumo Europe NV (Belgium).

Figures

Graphical Abstract
Graphical Abstract
Figure 1
Figure 1
Receiver operating characteristic curves and performance metrics on test sets. AUC, area under the curve; GBC, gradient boosting classifier; LDA, linear discriminant analysis; LR, logistic regression; NB, Naïve Bayes; KNN, K-nearest neighbours; ROC, receiver operating characteristic; TLF1Y, target lesion failure at 1-year follow-up.
Figure 2
Figure 2
Probability calibration curves on the test set. GBC, gradient boosting classifier; LDA, linear discriminant analysis; LR, logistic regression; NB, Naïve Bayes; KNN, K-nearest neighbours; TLF1Y, target lesion failure at 1-year follow-up.
Figure 3
Figure 3
Predicted vs. observed frequency of events per risk deciles. Decile 1 represents 10% of the population with the lowest predicted risk score, Decile 10 represents 10% of the population with the highest predicted risk score. GBC, gradient boosting classifier; LDA, linear discriminant analysis; LR, logistic regression; NB, Naïve Bayes; KNN, K-nearest neighbours; TLF1Y, target lesion failure at 1-year follow-up.
See this image and copyright information in PMC

References

    1. Garratt KN, Schneider MA. Thinking machines and risk assessment: on the path to precision medicine. J Am Heart Assoc 2019;8:e011969. - PMC - PubMed
    1. Neumann FJ, Sousa-Uva M, Ahlsson A, Alfonso F, Banning AP, Benedetto U, et al. 2018 ESC/EACTS guidelines on myocardial revascularization. Eur Heart J 2019;40:87–16.
    1. Cutlip DE, Windecker S, Mehran R, Boam A, Cohen DJ, van Es GA, et al. Clinical endpoints in coronary stent trials: a case for standardised definitions. Circulation 2007;115:2344–2351. - PubMed
    1. Sianos G, Morel MA, Kappetein AP, Morice MC, Colombo A, Dawkins K, et al. The SYNTAX score: an angiographic tool grading the complexity of coronary artery disease. EuroIntervention 2005;1:219–227. - PubMed
    1. Farooq V, van Klavern D, Steyerberg EW, Meliga E, Vergouwe Y, Chieffo A, et al. Anatomical and clinical characteristics to guide decision making between coronary artery bypass surgery and percutaneous coronary intervention for individual patients: development and validation of SYNTAX score II. Lancet 2013;381:639–650. - PubMed

Associated data

LinkOut - more resources