EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Predicting Successful Chronic Total Occlusion Crossing With Primary Antegrade Wiring Using Machine Learning

Athanasios Rempakos, Michaella Alexandrou, Deniz Mutlu, Arun Kalyanasundaram, Luiz F Ybarra, Rodrigo Bagur, James W Choi, Paul Poommipanit, Jaikirshan J Khatri, Laura Young, Rhian Davies, Stewart Benton und 22 weitere

JACC: Cardiovascular Interventions · 2024

DOI: 10.1016/j.jcin.2024.04.043 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift JACC: Cardiovascular Interventions, 2024. Verfasst von Athanasios Rempakos und 33 weiteren Autor:innen. Beteiligte Einrichtung: Minneapolis Heart Institute and Minneapolis Heart Institute Foundation, Abbott Northwestern Hospital, Minneapolis, Minnesota, USA. Hauptthemen laut MEDLINE: Coronary Occlusion, Machine Learning, Registries, Percutaneous Coronary Intervention. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Joseph Durda Foundation, Minneapolis Heart Institute Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: There is limited data on predicting successful chronic total occlusion crossing using primary antegrade wiring (AW). OBJECTIVES: The aim of this study was to develop and validate a machine learning (ML) prognostic model for successful chronic total occlusion crossing using primary AW. METHODS: We used data from 12,136 primary AW cases performed between 2012 and 2023 at 48 centers in the PROGRESS CTO registry (Prospective Global Registry for the Study of Chronic Total Occlusion Intervention; NCT02061436) to develop 5 ML models. Hyperparameter tuning was performed for the model with the best performance, and the SHAP (SHapley Additive exPlanations) explainer was implemented to estimate feature importance. RESULTS: Primary AW was successful in 6,965 cases (57.4%). Extreme gradient boosting was the best performing ML model with an average area under the receiver-operating characteristic curve of 0.775 (± 0.010). After hyperparameter tuning, the average area under the receiver-operating characteristic curve of the extreme gradient boosting model was 0.782 in the training set and 0.780 in the testing set. Among the factors examined, occlusion length had the most significant impact on predicting successful primary AW crossing followed by blunt/no stump, presence of interventional collaterals, vessel diameter, and proximal cap ambiguity. In contrast, aorto-ostial lesion location had the least impact on the outcome. A web-based application for predicting successful primary AW wiring crossing is available online (PROGRESS-CTO website) (https://www.progresscto.org/predict-aw-success). CONCLUSIONS: We developed an ML model with 14 features and high predictive capacity for successful primary AW in chronic total occlusion percutaneous coronary intervention.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Coronary OcclusionMachine LearningRegistriesPercutaneous Coronary InterventionPredictive Value of TestsHumansMaleFemaleTreatment OutcomeChronic DiseaseAgedMiddle AgedReproducibility of ResultsRisk FactorsDecision Support TechniquesTime Factors

Stichwörter der Autor:innen

chronic total occlusioncoronary artery diseasemachine learningpercutaneous coronary interventionprimary antegrade wiring

Autor:innen und Institutionen

  • Minneapolis Heart Institute and Minneapolis Heart Institute Foundation, Abbott Northwestern Hospital, Minneapolis, Minnesota, USA.
  • The Promed Hospital, Chennai, India.
  • London Health Sciences Centre, Western University, London, Ontario, Canada.
  • Texas Health Presbyterian Hospital, Dallas, Texas, USA.
  • University Hospitals, Case Western Reserve University, Cleveland, Ohio, USA.
  • Cleveland Clinic, Cleveland, Ohio, USA.

Förderung

  • Joseph Durda Foundation
  • Minneapolis Heart Institute Foundation

Zitieren

APA

Rempakos, A., Alexandrou, M., Mutlu, D., Kalyanasundaram, A., Ybarra, L. F., Bagur, R., Choi, J. W., Poommipanit, P., Khatri, J. J., Young, L., Davies, R., Benton, S., Gorgulu, S., Jaffer, F. A., Chandwaney, R., Jaber, W., Rinfret, S., Nicholson, W., Azzalini, L., …, & Brilakis, E. S. (2024). Predicting Successful Chronic Total Occlusion Crossing With Primary Antegrade Wiring Using Machine Learning. JACC: Cardiovascular Interventions. https://doi.org/10.1016/j.jcin.2024.04.043

Vancouver

Rempakos A, Alexandrou M, Mutlu D, Kalyanasundaram A, Ybarra LF, Bagur R, et al. Predicting Successful Chronic Total Occlusion Crossing With Primary Antegrade Wiring Using Machine Learning. JACC: Cardiovascular Interventions. 2024. doi:10.1016/j.jcin.2024.04.043

BibTeX
@article{Rempakos2024,
  author = {Rempakos, Athanasios and Alexandrou, Michaella and Mutlu, Deniz and Kalyanasundaram, Arun and Ybarra, Luiz F and Bagur, Rodrigo and Choi, James W and Poommipanit, Paul and Khatri, Jaikirshan J and Young, Laura and Davies, Rhian and Benton, Stewart and Gorgulu, Sevket and Jaffer, Farouc A and Chandwaney, Raj and Jaber, Wissam and Rinfret, Stephane and Nicholson, William and Azzalini, Lorenzo and Kearney, Kathleen E and Alaswad, Khaldoon and Basir, Mir B and Krestyaninov, Oleg and Khelimskii, Dmitrii and Abi-Rafeh, Nidal and Elguindy, Ahmed and Goktekin, Omer and Aygul, Nazif and Rangan, Bavana V and Mastrodemos, Olga C and Al-Ogaili, Ahmed and Sandoval, Yader and Burke, M Nicholas and Brilakis, Emmanouil S},
  title = {Predicting Successful Chronic Total Occlusion Crossing With Primary Antegrade Wiring Using Machine Learning},
  journal = {JACC: Cardiovascular Interventions},
  year = {2024},
  doi = {10.1016/j.jcin.2024.04.043}
}
Kostenlos starten →