EUVIMEDObjevte EUVIMED
Open access · CC BY-NC-ND 4.0

Early Detection of Left Ventricular Dysfunction With Machine Learning‐Based Strain Imaging in Aortic Stenosis Patients

Amir Yahav iD, Dan Adam

Echocardiography · 2024

DOI: 10.1111/echo.70007 ↗

At a glance

Journal article in Echocardiography, 2024. Written by Amir Yahav and 1 co-authors. Institution: Faculty of Biomedical Engineering, Technion - Israel Institute of Technology, Haifa, Israel. Major MEDLINE topics: Aortic Valve Stenosis, Ventricular Dysfunction, Left, Machine Learning, Early Diagnosis. Cited 3 times so far (Crossref); 65 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: KAMIN program of the Israel Innovation Authority.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Purpose

Aortic stenosis (AS) is a common cardiovascular condition where early detection of left ventricular (LV) dysfunction is essential for timely intervention and optimal management. Current echocardiographic measurements, such as ejection fraction (EF), are insensitive to minor changes in LV function, and strain imaging is typically limited to the global longitudinal strain (GLS) parameter due to robustness issues. This study introduces a novel, fully automatic algorithm to enhance the detection of LV dysfunction in AS patients using multiple strain imaging parameters.

Methods

We applied supervised machine‐learning techniques to classify data from 82 severe AS patients, 96 chest pain subjects, and 319 healthy volunteers.

Results

Our model significantly outperformed EF and GLS in distinguishing AS patients from healthy volunteers (area under the curve [AUC] = 0.97 vs. 0.88 and 0.82, respectively). It also surpassed EF and GLS in differentiating AS patients from chest pain subjects (AUC = 0.95 vs. 0.90 and 0.55, respectively).

Conclusion

This novel, clinically interpretable model leverages the potential of strain imaging to enhance diagnostic accuracy and guide clinical decision‐making in LV dysfunction, thereby improving clinical practice.

Subjects

MeSH terms (MEDLINE)

Aortic Valve StenosisVentricular Dysfunction, LeftMachine LearningEarly DiagnosisEchocardiographyHumansMaleFemaleAgedMiddle AgedHeart VentriclesReproducibility of ResultsStroke Volume

Author keywords

aortic stenosisclassificationechocardiographymachine learningmyocardial strain

Authors and institutions

  • Faculty of Biomedical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.

ORCID profiles: Amir Yahav

Funding

  • KAMIN program of the Israel Innovation Authority

Cite

APA

Yahav, A., & Adam, D. (2024). Early Detection of Left Ventricular Dysfunction With Machine Learning‐Based Strain Imaging in Aortic Stenosis Patients. Echocardiography. https://doi.org/10.1111/echo.70007

Vancouver

Yahav A, Adam D. Early Detection of Left Ventricular Dysfunction With Machine Learning‐Based Strain Imaging in Aortic Stenosis Patients. Echocardiography. 2024. doi:10.1111/echo.70007

BibTeX
@article{Yahav2024,
  author = {Yahav, Amir and Adam, Dan},
  title = {Early Detection of Left Ventricular Dysfunction With Machine Learning‐Based Strain Imaging in Aortic Stenosis Patients},
  journal = {Echocardiography},
  year = {2024},
  doi = {10.1111/echo.70007}
}
Start for free →