EUVIMEDEUVIMED entdecken
Crossref

Machine learning and radiomics for ventricular tachyarrhythmia prediction in hypertrophic cardiomyopathy: insights from an MRI-based analysis

Emine Sebnem Durmaz, Mert Karabacak iD, Burak Berksu Ozkara, Osman Aykan Kargın iD, Bilal Demir, Damla Raimoglou, Ahmet Atil Aygun, Ibrahim Adaletli, Ahmet Bas, Eser Durmaz

Acta Radiologica · 2024

DOI: 10.1177/02841851241283041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Radiologica, 2024. Verfasst von Emine Sebnem Durmaz und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Cerrahpasa Faculty of Medicine, Istanbul University-Cerrahpasa, Istanbul, Turkey. Hauptthemen laut MEDLINE: Cardiomyopathy, Hypertrophic, Machine Learning, Tachycardia, Ventricular, Magnetic Resonance Imaging, Cine. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 33 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Myocardial fibrosis is often detected in patients with hypertrophic cardiomyopathy (HCM), which causes left ventricular (LV) dysfunction and tachyarrhythmias.

Purpose

To evaluate the potential value of a machine learning (ML) approach that uses radiomic features from late gadolinium enhancement (LGE) and cine images for the prediction of ventricular tachyarrhythmia (VT) in patients with HCM. Material and Methods Hyperenhancing areas of LV myocardium on LGE images were manually segmented, and the segmentation was propagated to corresponding areas on cine images. Radiomic features were extracted using the PyRadiomics library. The least absolute shrinkage and selection operator (LASSO) method was employed for radiomic feature selection. Our model development employed the TabPFN algorithm, an adapted Prior-Data Fitted Network design. Model performance was evaluated graphically and numerically over five-repeat fivefold cross-validation. SHapley Additive exPlanations (SHAP) were employed to determine the relative importance of selected radiomic features.

Results

Our cohort consisted of 60 patients with HCM (73.3% male; median age = 51.5 years), among whom 17 had documented VT during the follow-up. A total of 1612 radiomic features were extracted for each patient. The LASSO algorithm led to a final selection of 18 radiomic features. The model achieved a mean area under the receiver operating characteristic curve of 0.877, demonstrating good discrimination, and a mean Brier score of 0.119, demonstrating good calibration.

Conclusion

Radiomics-based ML models are promising for predicting VT in patients with HCM during the follow-up period. Developing predictive models as clinically useful decision-making tools may significantly improve risk assessment and prognosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiomyopathy, HypertrophicMachine LearningTachycardia, VentricularMagnetic Resonance Imaging, CineContrast MediaHumansMaleFemaleMiddle AgedPredictive Value of TestsAdultRetrospective StudiesMagnetic Resonance ImagingRadiomics

Stichwörter der Autor:innen

Cardiac magnetic resonance imaginghypertrophic cardiomyopathymachine learningradiomics

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Department of Radiology, Cerrahpasa Faculty of Medicine, Istanbul University-Cerrahpasa, Istanbul, Turkey.
  • Cerrahpasa Faculty of Medicine, Istanbul University-Cerrahpasa, Istanbul, Turkey.
  • Department of Neurosurgery, Mount Sinai Health System, New York, NY, USA.
  • Department of Neuroradiology, MD Anderson Cancer Center, Houston, TX, USA.
  • Department of Cardiology, Cerrahpasa Faculty of Medicine, Istanbul University-Cerrahpasa, Istanbul, Turkey.

ORCID-Profile: Mert Karabacak, Osman Aykan Kargın

Zitieren

APA

Durmaz, E. S., Karabacak, M., Ozkara, B. B., Kargın, O. A., Demir, B., Raimoglou, D., Aygun, A. A., Adaletli, I., Bas, A., & Durmaz, E. (2024). Machine learning and radiomics for ventricular tachyarrhythmia prediction in hypertrophic cardiomyopathy: insights from an MRI-based analysis. Acta Radiologica. https://doi.org/10.1177/02841851241283041

Vancouver

Durmaz ES, Karabacak M, Ozkara BB, Kargın OA, Demir B, Raimoglou D, et al. Machine learning and radiomics for ventricular tachyarrhythmia prediction in hypertrophic cardiomyopathy: insights from an MRI-based analysis. Acta Radiologica. 2024. doi:10.1177/02841851241283041

BibTeX
@article{Durmaz2024,
  author = {Durmaz, Emine Sebnem and Karabacak, Mert and Ozkara, Burak Berksu and Kargın, Osman Aykan and Demir, Bilal and Raimoglou, Damla and Aygun, Ahmet Atil and Adaletli, Ibrahim and Bas, Ahmet and Durmaz, Eser},
  title = {Machine learning and radiomics for ventricular tachyarrhythmia prediction in hypertrophic cardiomyopathy: insights from an MRI-based analysis},
  journal = {Acta Radiologica},
  year = {2024},
  doi = {10.1177/02841851241283041}
}
Kostenlos starten →