Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography
Circulation: Cardiovascular Imaging · 2024
DOI: 10.1161/circimaging.123.016274 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Circulation: Cardiovascular Imaging, 2024. Verfasst von Francesco Pisu und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Azienda Ospedaliero-Universitaria, Monserrato (Cagliari), Italy (F.P., M.P., R.C., A.B., L.S.). Hauptthemen laut MEDLINE: Computed Tomography Angiography, Machine Learning, Plaque, Atherosclerotic, Carotid Artery Diseases. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
BACKGROUND: This study aimed to develop and validate a computed tomography angiography based machine learning model that uses plaque composition data and degree of carotid stenosis to detect symptomatic carotid plaques in patients with carotid atherosclerosis. METHODS: The machine learning based model was trained using degree of stenosis and the volumes of 13 computed tomography angiography derived intracarotid plaque subcomponents (eg, lipid, intraplaque hemorrhage, calcium) to identify plaques associated with cerebrovascular events. The model was internally validated through repeated 10-fold cross-validation and tested on a dedicated testing cohort according to discrimination and calibration. RESULTS: This retrospective, single-center study evaluated computed tomography angiography scans of 268 patients with both symptomatic and asymptomatic carotid atherosclerosis (163 for the derivation set and 106 for the testing set) performed between March 2013 and October 2019. The area-under-receiver-operating characteristics curve by machine learning on the testing cohort (0.89) was significantly higher than the areas under the curve of traditional logit analysis based on the degree of stenosis (0.51, P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Azienda Ospedaliero-Universitaria, Monserrato (Cagliari), Italy (F.P., M.P., R.C., A.B., L.S.).
- Department of Radiology, University of Cincinnati, Cincinnati, OH (B.J.W., A.V., A.M.).
- Department of Radiology, Mayo Clinic, Rochester, MN (V.N., J.C.B., G.L.).
- Department of Vascular Surgery, Central Clinic of Athens, Athens, Greece (K.I.P.).
- Department of Radiology (IDI), Hospital Universitari de Girona, Girona, Spain (J.P.).
- UOC Neuroradiology Diagnostic and Interventional, San Camillo-Forlanini Hospital, Rome, Italy (G.R.).
ORCID-Profile: Francesco Pisu, Brady J Williamson, Valentina Nardi, Kosmas I Paraskevas, Achala Vagal, Gianluca de Rubeis, Michele Porcu, Riccardo Cau, John C Benson, Antonella Balestrieri, Giuseppe Lanzino, Luca Saba
Zitieren
APA
Pisu, F., Williamson, B. J., Nardi, V., Paraskevas, K. I., Puig, J., Vagal, A., de Rubeis, G., Porcu, M., Cau, R., Benson, J. C., Balestrieri, A., Lanzino, G., Suri, J. S., Mahammedi, A., & Saba, L. (2024). Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography. Circulation: Cardiovascular Imaging. https://doi.org/10.1161/circimaging.123.016274
Vancouver
Pisu F, Williamson BJ, Nardi V, Paraskevas KI, Puig J, Vagal A, et al. Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography. Circulation: Cardiovascular Imaging. 2024. doi:10.1161/circimaging.123.016274
BibTeX
@article{Pisu2024,
author = {Pisu, Francesco and Williamson, Brady J and Nardi, Valentina and Paraskevas, Kosmas I and Puig, Josep and Vagal, Achala and de Rubeis, Gianluca and Porcu, Michele and Cau, Riccardo and Benson, John C and Balestrieri, Antonella and Lanzino, Giuseppe and Suri, Jasjit S and Mahammedi, Abdelkader and Saba, Luca},
title = {Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography},
journal = {Circulation: Cardiovascular Imaging},
year = {2024},
doi = {10.1161/circimaging.123.016274}
}
EUVIMED