An Open-Source Analysis of Cardiomyopathy Using Machine Learning and Electrocardiograms
Diagnostics · 28.02.2026 · 16 (5) · 719
DOI: 10.3390/diagnostics16050719 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 28.02.2026. Verfasst von Arda Altintepe und 3 weiteren Autor:innen. Beteiligte Einrichtung: Horace Mann School, Bronx, NY 10471, USA. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Dilated cardiomyopathy (DCM) and hypertrophic cardiomyopathy (HCM) are common cardiomyopathies associated with heart failure. Electrocardiogram (ECG) screening before an echocardiogram could help streamline diagnosis, particularly in rural areas. Prior ECG–machine learning (ML) studies do not use open-source data when studying cardiomyopathy, and very few proprietary studies directly compare HCM and DCM or address ECG differences within obstructive (HOCM) and non-obstructive HCM (HNCM).
Methods
Standard and vectorcardiogram-derived (VCG) ECG features were extracted from the MIMIC-IV-ECG database. The final cohort comprised 599 patients (HCM = 208 [HOCM = 99, HNCM = 53, unknown = 56]; DCM = 391 [ischemic cardiomyopathy with left ventricular dilation = 250, non-ischemic = 141]). Logistic regression (LR) and extreme gradient boosting (XGBoost) with five-fold cross-validation separated HCM from ischemic cardiomyopathy with left ventricular dilation (DCM-I) and non-ischemic DCM (DCM-NI), and HOCM from HNCM.
Results
Using the area under the receiver-operating-characteristic curve (AUC-ROC) as the performance metric, LR achieved high discrimination of HCM from DCM-I (0.92) and DCM-NI (0.90). However, differentiating HOCM from HNCM proved more difficult (XGBoost = 0.81; LR = 0.75). Both DCM subtypes (especially ischemic) showed lower QRS amplitudes and right-posterior ventricular gradient orientation; HCM displayed higher amplitudes and larger, more complex T-loops. Within HCM, HOCM had stronger leftward electrical activity and more dipolar to non-dipolar QRS energy after singular value decomposition.
Conclusions
Using only open-access data, we demonstrate an interpretable ECG-based pipeline that discriminates cardiomyopathy and highlights distinct features. While detecting obstruction remains difficult, ECG features provide measurable separation, supporting possible diagnostic screening and offering a reproducible framework for future studies.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Horace Mann School, Bronx, NY 10471, USA.
- Ocean Cardiovascular, LLC, Toms River, NJ 08755, USA.
- Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA.
- Princeton Precision Health, Princeton University, Princeton, NJ 08544, USA.
- Omenn-Darling Bioengineering Institute, Princeton University, Bioengineering Building, 35 Ivy Lane, Princeton, NJ 08540, USA.
ORCID-Profile: Arda Altintepe, Amir Reza Vazifeh
Zitieren
APA
Altintepe, A., Rustemli, A., Vazifeh, A. R., & Fleischer, J. W. (2026). An Open-Source Analysis of Cardiomyopathy Using Machine Learning and Electrocardiograms. Diagnostics, 16(5), 719. https://doi.org/10.3390/diagnostics16050719
Vancouver
Altintepe A, Rustemli A, Vazifeh AR, Fleischer JW. An Open-Source Analysis of Cardiomyopathy Using Machine Learning and Electrocardiograms. Diagnostics. 2026;16(5):719. doi:10.3390/diagnostics16050719
BibTeX
@article{Altintepe2026,
author = {Altintepe, Arda and Rustemli, Asu and Vazifeh, Amir Reza and Fleischer, Jason W},
title = {An Open-Source Analysis of Cardiomyopathy Using Machine Learning and Electrocardiograms},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {5},
pages = {719},
doi = {10.3390/diagnostics16050719}
}
EUVIMED