EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Female anatomies disguise ECG abnormalities following myocardial infarction: An artificial intelligence−enabled modelling and simulation study

Hannah Joy Smith, Leto Luana Riebel, Ruben Doste, Maxx Holmes, Vicente Grau, Abhirup Banerjee, Blanca Rodriguez

The Journal of Physiology · 19.11.2026

DOI: 10.1113/jp290759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Physiology, online erschienen am 19.11.2026. Verfasst von Hannah Joy Smith und 6 weiteren Autor:innen. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ECG is modulated by torso‐heart anatomy, challenging patients’ diagnosis and risk stratification. This study aims to quantify how torso‐heart anatomical factors affect sex differences in ECG biomarkers in acute and chronic myocardial infarction (MI). We exploit the perfect control of artificial intelligence (AI)‐augmented multiscale modelling and simulation, using clinical magnetic resonance imaging (MRI) and ECGs for model construction and validation. A cohort of 1720 torso‐ventricular anatomies (50% female) was constructed from MRIs of healthy and post‐MI participants in the UK Biobank. A total of 8600 simulations were performed considering anatomical variability, three electrophysiological stages (healthy, ischaemic and infarcted) and two infarct locations (anteroseptal and inferolateral). Quantifying the effect of cardiac size, position and orientation on each ECG biomarker, we found that female anatomies had larger distances between infarct and ECG electrodes (relative to cardiac size) and larger angles between infarct normal and ECG lead axes, both primarily caused by their more superior cardiac position. This reduced ST elevation and amplitude of late depolarisation and repolarisation tails, ultimately shortening QRS duration (QRSd) and T‐peak‐to‐end interval (TpTe). Overall, position and orientation of the heart impacted TpTe more severely than QRSd; our AI‐enabled mechanistic modelling and simulation identified smaller ventricles, superior cardiac position and different ventricular orientation as key anatomical contributors of QRSd, TpTe and ST elevation being reduced in female versus male anatomies. Our framework provides a blueprint for quantifying the impact of anatomical sex differences on functional markers and enables future work in tailoring clinical guidelines considering unique patient anatomy to reduce biased outcomes. image Key points The ECG, important in diagnosing and managing treatment for myocardial infarction (heart attacks), is known to be impacted by the anatomy of the heart and torso. Women suffering myocardial infarction are underdiagnosed, and the effect of anatomical sex differences on the ECG in myocardial infarction is poorly understood. Our human computational modelling and simulation demonstrate that ST elevation in ischaemia was reduced in female anatomies, mainly as their hearts are higher in the torso than male anatomies. We show that ECG time intervals were affected differently by anatomy: the T‐peak‐to‐end interval was more sensitive to cardiac positioning, whereas QRS duration was more sensitive to cardiac size. Our study demonstrates how computer simulations provide an efficient mechanistic tool to quantify the role of anatomical differences in clinical biomarkers and could ultimately support the inclusion of sex differences in clinical guidelines.

Förderung

  • Wellcome Trust

Zitieren

APA

Smith, H. J., Riebel, L. L., Doste, R., Holmes, M., Grau, V., Banerjee, A., & Rodriguez, B. (2026). Female anatomies disguise ECG abnormalities following myocardial infarction: An artificial intelligence−enabled modelling and simulation study. The Journal of Physiology. https://doi.org/10.1113/jp290759

Vancouver

Smith HJ, Riebel LL, Doste R, Holmes M, Grau V, Banerjee A, et al. Female anatomies disguise ECG abnormalities following myocardial infarction: An artificial intelligence−enabled modelling and simulation study. The Journal of Physiology. 2026. doi:10.1113/jp290759

BibTeX
@article{Smith2026,
  author = {Smith, Hannah Joy and Riebel, Leto Luana and Doste, Ruben and Holmes, Maxx and Grau, Vicente and Banerjee, Abhirup and Rodriguez, Blanca},
  title = {Female anatomies disguise ECG abnormalities following myocardial infarction: An artificial intelligence−enabled modelling and simulation study},
  journal = {The Journal of Physiology},
  year = {2026},
  doi = {10.1113/jp290759}
}
Kostenlos starten →