Left Atrial Strain in the Assessment of Diastolic Function in Heart Failure: A Machine Learning Approach
Circulation: Cardiovascular Imaging · 2023-02 · 16 (2)
DOI: 10.1161/circimaging.122.014605 ↗Kurz gefasst
Fachartikel in der Zeitschrift Circulation: Cardiovascular Imaging, 2023-02. Verfasst von Erberto Carluccio und 10 weiteren Autor:innen. Beteiligte Einrichtung: Cardiology and Cardiovascular Pathophysiology, S. Maria della Misericordia Hospital, University of Perugia, Italy (E.C., P.B., A.M., F.J., G.A.). Hauptthemen laut MEDLINE: Atrial Fibrillation, Heart Failure, Ventricular Dysfunction, Left. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 27 Literaturangaben.
Themen: Künstliche Intelligenz in der Pflege, Herzinsuffizienz
Abstract (Originalsprache)
Background
Diastolic dysfunction (DD) assessment in heart failure is still challenging. Peak atrial longitudinal strain (PALS) is strongly related to end-diastolic pressure and prognosis, but it is still not part of standard DD assessment. We tested the hypothesis that a machine learning approach would be useful to include PALS in DD classification and refine prognostic stratification.
Methods
In a derivation cohort of 864 heart failure patients in sinus rhythm (age, 66.6±12 years; heart failure with reduced ejection fraction, n=541; heart failure with mildly reduced ejection fraction, n=129; heart failure with preserved ejection fraction, n=194), machine learning techniques were retrospectively applied to PALS and guideline-recommended diastolic variables. Outcome (death/heart failure rehospitalization) of the identified DD-clusters was compared with that by guidelines-based classification. To identify the best combination of variables able to classify patients in one of the identified DD-clusters, classification and regression tree analysis was applied (with DD-clusters as dependent variable and PALS plus guidelines-recommended diastolic variables as explanatory variables). The algorithm was subsequently validated in a prospective cohort of 189 heart failure outpatients (age, 65±13 years).
Results
Three distinct echocardiographic DD-clusters were identified (cluster-1, n=212; cluster-2, n=376; cluster-3 DD, n=276), with modest agreement with guidelines-recommended classification (kappa=0.40; P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cardiology and Cardiovascular Pathophysiology, S. Maria della Misericordia Hospital, University of Perugia, Italy (E.C., P.B., A.M., F.J., G.A.).
- Division of Cardiology, Department of Medical Biotechnologies, University of Siena, Italy (M.C., G.E.M., M.C.P.).
- Azienda Ospedaliero-Universitaria, Verona, Italy (A.R., C.M.).
- Cardiac, Thoracic and Vascular Department, University of Pisa, Italy (F.L.D.).
ORCID-Profile: Erberto Carluccio, Matteo Cameli, Andrea Rossi, Maria Concetta Pastore, Giuseppe Ambrosio
Zitieren
APA
Carluccio, E., Cameli, M., Rossi, A., Dini, F. L., Biagioli, P., Mengoni, A., Jacoangeli, F., Mandoli, G. E., Pastore, M. C., Maffeis, C., & Ambrosio, G. (2023). Left Atrial Strain in the Assessment of Diastolic Function in Heart Failure: A Machine Learning Approach. Circulation: Cardiovascular Imaging, 16(2). https://doi.org/10.1161/circimaging.122.014605
Vancouver
Carluccio E, Cameli M, Rossi A, Dini FL, Biagioli P, Mengoni A, et al. Left Atrial Strain in the Assessment of Diastolic Function in Heart Failure: A Machine Learning Approach. Circulation: Cardiovascular Imaging. 2023;16(2). doi:10.1161/circimaging.122.014605
BibTeX
@article{Carluccio2023,
author = {Carluccio, Erberto and Cameli, Matteo and Rossi, Andrea and Dini, Frank Lloyd and Biagioli, Paolo and Mengoni, Anna and Jacoangeli, Francesca and Mandoli, Giulia Elena and Pastore, Maria Concetta and Maffeis, Caterina and Ambrosio, Giuseppe},
title = {Left Atrial Strain in the Assessment of Diastolic Function in Heart Failure: A Machine Learning Approach},
journal = {Circulation: Cardiovascular Imaging},
year = {2023},
volume = {16},
number = {2},
doi = {10.1161/circimaging.122.014605}
}
EUVIMED