EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudieOpen Access · CC BY-NC-ND 4.0

Development of machine learning models for fractional flow reserve prediction in angiographically intermediate coronary lesions

Marco Lombardi iD, Rocco Vergallo, Andrea Costantino, Francesco Bianchini iD, Tsunekazu Kakuta iD, Tomasz Pawlowski iD, Antonio M Leone iD, Gennaro Sardella, Pierfrancesco Agostoni iD, Jonathan M Hill, Giovanni L De Maria iD, Adrian P Banning und 4 weitere

Catheterization and Cardiovascular Interventions · 2024

DOI: 10.1002/ccd.31167 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Catheterization and Cardiovascular Interventions, 2024. Verfasst von Marco Lombardi und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiovascular Sciences, Fondazione Policlinico Universitario A. Gemelli IRCCS, Università Cattolica Sacro Cuore, Rome, Italy. Hauptthemen laut MEDLINE: Coronary Angiography, Coronary Artery Disease, Coronary Vessels, Supervised Machine Learning. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Fractional flow reserve (FFR) represents the gold standard in guiding the decision to proceed or not with coronary revascularization of angiographically intermediate coronary lesion (AICL). Optical coherence tomography (OCT) allows to carefully characterize coronary plaque morphology and lumen dimensions.

Objectives

We sought to develop machine learning (ML) models based on clinical, angiographic and OCT variables for predicting FFR.

Methods

Data from a multicenter, international, pooled analysis of individual patient's level data from published studies assessing FFR and OCT on the same target AICL were collected through a dedicated database to train ( n = 351) and validate ( n = 151) six two‐class supervised ML models employing 25 clinical, angiographic and OCT variables.

Results

A total of 502 coronary lesions in 489 patients were included. The AUC of the six ML models ranged from 0.71 to 0.78, whereas the measured F1 score was from 0.70 to 0.75. The ML algorithms showed moderate sensitivity (range: 0.68–0.77) and specificity (range: 0.59–0.69) in detecting patients with a positive or negative FFR. In the sensitivity analysis, using 0.75 as FFR cut‐off, we found a higher AUC (0.78–0.86) and a similar F1 score (range: 0.63–0.76). Specifically, the six ML models showed a higher specificity (0.71–0.84), with a similar sensitivity (0.58–0.80) with respect to 0.80 cut‐off.

Conclusions

ML algorithms derived from clinical, angiographic, and OCT parameters can identify patients with a positive or negative FFR.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Coronary AngiographyCoronary Artery DiseaseCoronary VesselsSupervised Machine LearningAgedFemaleHumansMaleMiddle AgedCardiac CatheterizationCoronary StenosisDatabases, FactualDecision Support TechniquesFractional Flow Reserve, MyocardialPlaque, AtheroscleroticPredictive Value of TestsReproducibility of ResultsSeverity of Illness IndexTomography, Optical CoherenceSoftware

Stichwörter der Autor:innen

artificial intelligencefractional flow reserveintermediate coronary lesionsmachine learningoptical coherence tomography

Autor:innen und Institutionen

  • Department of Cardiovascular Sciences, Fondazione Policlinico Universitario A. Gemelli IRCCS, Università Cattolica Sacro Cuore, Rome, Italy.
  • Department of Internal Medicine and Medical Specialties (DIMI), Università di Genova, Genova, Italy.
  • Interventional Cardiology Unit, Cardiothoracic and Vascular Department (DICATOV), IRCCS Ospedale Policlinico San Martino, Genova, Italy.
  • Department of Biomedical Sciences, Humanitas University, Milan, Italy.
  • Department of Cardiovascular Medicine, Tsuchiura Kyodo General Hospital, Tsuchiura, Japan.
  • Department of Cardiology, Central Hospital of Internal Affairs and Administration Ministry, Postgraduate Medical Education Centre, Warsaw, Poland.

ORCID-Profile: Marco Lombardi, Francesco Bianchini, Tsunekazu Kakuta, Tomasz Pawlowski, Antonio M Leone, Pierfrancesco Agostoni, Giovanni L De Maria, Tomasz Roleder, Carlo Trani

Zitieren

APA

Lombardi, M., Vergallo, R., Costantino, A., Bianchini, F., Kakuta, T., Pawlowski, T., Leone, A. M., Sardella, G., Agostoni, P., Hill, J. M., De Maria, G. L., Banning, A. P., Roleder, T., Belkacemi, A., Trani, C., & Burzotta, F. (2024). Development of machine learning models for fractional flow reserve prediction in angiographically intermediate coronary lesions. Catheterization and Cardiovascular Interventions. https://doi.org/10.1002/ccd.31167

Vancouver

Lombardi M, Vergallo R, Costantino A, Bianchini F, Kakuta T, Pawlowski T, et al. Development of machine learning models for fractional flow reserve prediction in angiographically intermediate coronary lesions. Catheterization and Cardiovascular Interventions. 2024. doi:10.1002/ccd.31167

BibTeX
@article{Lombardi2024,
  author = {Lombardi, Marco and Vergallo, Rocco and Costantino, Andrea and Bianchini, Francesco and Kakuta, Tsunekazu and Pawlowski, Tomasz and Leone, Antonio M and Sardella, Gennaro and Agostoni, Pierfrancesco and Hill, Jonathan M and De Maria, Giovanni L and Banning, Adrian P and Roleder, Tomasz and Belkacemi, Anouar and Trani, Carlo and Burzotta, Francesco},
  title = {Development of machine learning models for fractional flow reserve prediction in angiographically intermediate coronary lesions},
  journal = {Catheterization and Cardiovascular Interventions},
  year = {2024},
  doi = {10.1002/ccd.31167}
}
Kostenlos starten →