A speckle-tracking strain-based artificial neural network model to differentiate cardiomyopathy type.

Journal: Scandinavian cardiovascular journal : SCJ
Published Date: Oct 18, 2019

Abstract

In heart failure, invasive angiography is often employed to differentiate ischaemic from non-ischaemic cardiomyopathy. We aim to examine the predictive value of echocardiographic strain features alone and in combination with other features to differentiate ischaemic from non-ischaemic cardiomyopathy, using artificial neural network (ANN) and logistic regression modelling. We retrospectively identified 204 consecutive patients with an ejection fraction <50% and a diagnostic angiogram. Patients were categorized as either ischaemic ( = 146) or non-ischaemic cardiomyopathy ( = 58). For each patient, left ventricular strain parameters were obtained. Additionally, regional wall motion abnormality, 13 electrocardiographic (ECG) features and six demographic features were retrieved for analysis. The entire cohort was randomly divided into a derivation and a validation cohort. Using the parameters retrieved, logistic regression and ANN models were developed in the derivation cohort to differentiate ischaemic from non-ischaemic cardiomyopathy, the models were then tested in the validation cohort. A final strain-based ANN model, full feature ANN model and full feature logistic regression model were developed and validated, scores were 0.82, 0.79 and 0.63, respectively. Both ANN models were more accurate at predicting cardiomyopathy type than the logistic regression model. The strain-based ANN model should be validated in other cohorts. This model or similar models could be used to aid the diagnosis of underlying heart failure aetiology in the form of the online calculator (https://cimti.usj.edu.lb/strain/index.html) or built into echocardiogram software.

Authors

  • Jason Leo Walsh
    Vascular Medicine Program, Division of Cardiology, American University of Beirut Medical Center, Beirut, Lebanon.
  • Wael A AlJaroudi
    Division of Cardiovascular Medicine, Clemenceau Medical Center, Beirut, Lebanon.
  • Nader Lamaa
    Division of Cardiology, Department of Internal Medicine, American University of Beirut, PO-BOX 11-0236, Riad el Solh, Beirut, 11072020, Lebanon.
  • Ossama K Abou Hassan
    3Internal Medicine DepartmentAmerican University of BeirutBeirutLebanon.
  • Khalil Jalkh
    Vascular Medicine Program, Division of Cardiology, American University of Beirut Medical Center, Beirut, Lebanon.
  • Imad H Elhajj
    Vascular Medicine Program, American University of Beirut Medical Center, Riad el Solh, PO Box 11-023, Beirut, 11072020, Lebanon.
  • George Sakr
    Computer Engineering Department, St Joseph University of Beirut, Beirut, Lebanon.
  • Hussain Isma'eel
    3Internal Medicine DepartmentAmerican University of BeirutBeirutLebanon.

Keywords

External Resources

Popular Topics
Recent Journals