Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization

Shuang Qian; Devran Ugurlu; Elliot Fairweather; Laura Dal Toso; Yu Deng; Marina Strocchi; Ludovica Cicci; Richard E. Jones; Hassan Zaidi; Sanjay Prasad; Brian P. Halliday; Daniel Hammersley; Xingchi Liu; Gernot Plank; Edward Vigmond; Reza Razavi; Alistair Young; Pablo Lamata; Martin Bishop; Steven Niederer

doi:10.1038/s44161-025-00650-0

Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization

Shuang Qian^*, Devran Ugurlu, Elliot Fairweather, Laura Dal Toso, Yu Deng, Marina Strocchi, Ludovica Cicci, Richard E. Jones, Hassan Zaidi, Sanjay Prasad, Brian P. Halliday, Daniel Hammersley, Xingchi Liu, Gernot Plank, Edward Vigmond, Reza Razavi, Alistair Young, Pablo Lamata, Martin Bishop, Steven Niederer

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

13 Downloads (Pure)

Abstract

Large-cohort imaging and diagnostic studies often assess cardiac function but overlook underlying biological mechanisms. Cardiac digital twins (CDTs) are personalized physics-constrained and physiology-constrained in silico representations, uncovering multi-scale insights tied to these mechanisms. In this study, we constructed 3,461 CDTs from the UK Biobank and another 359 from an ischemic heart disease (IHD) cohort, using cardiac magnetic resonance images and electrocardiograms. We show here that sex-specific differences in QRS duration were fully explained by myocardial anatomy while their myocardial conduction velocity (CV) remains similar across sexes but changes with age and obesity, indicating myocardial tissue remodeling. Longer QTc intervals in obese females were attributed to larger delayed rectifier potassium conductance G_KrKs. These findings were validated in the IHD cohort. Moreover, CV and G_KrKs were associated with cardiac function, lifestyle and mental health phenotypes, and CV was also linked with adverse clinical outcomes. Our study demonstrates how CDT development at scale reveals biological insights across populations.

Original language	English
Article number	11437
Pages (from-to)	624-636
Number of pages	13
Journal	Nature Cardiovascular Research
Volume	4
Issue number	5
Early online date	16 May 2025
DOIs	https://doi.org/10.1038/s44161-025-00650-0
Publication status	E-pub ahead of print - 16 May 2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s44161-025-00650-0Licence: CC BY

Developing cardiac digital_QIAN_Publishedonline16May2025_GOLD VoR (CC-BY)Final published version, 40.1 MBLicence: CC BY

Cite this

Qian, S., Ugurlu, D., Fairweather, E., Toso, L. D., Deng, Y., Strocchi, M., Cicci, L., Jones, R. E., Zaidi, H., Prasad, S., Halliday, B. P., Hammersley, D., Liu, X., Plank, G., Vigmond, E., Razavi, R., Young, A., Lamata, P., Bishop, M., & Niederer, S. (2025). Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization. Nature Cardiovascular Research, 4(5), 624-636. Article 11437. Advance online publication. https://doi.org/10.1038/s44161-025-00650-0

@article{63be6cae56df428a8e648148b48ace9e,

title = "Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization",

abstract = "Large-cohort imaging and diagnostic studies often assess cardiac function but overlook underlying biological mechanisms. Cardiac digital twins (CDTs) are personalized physics-constrained and physiology-constrained in silico representations, uncovering multi-scale insights tied to these mechanisms. In this study, we constructed 3,461 CDTs from the UK Biobank and another 359 from an ischemic heart disease (IHD) cohort, using cardiac magnetic resonance images and electrocardiograms. We show here that sex-specific differences in QRS duration were fully explained by myocardial anatomy while their myocardial conduction velocity (CV) remains similar across sexes but changes with age and obesity, indicating myocardial tissue remodeling. Longer QTc intervals in obese females were attributed to larger delayed rectifier potassium conductance GKrKs. These findings were validated in the IHD cohort. Moreover, CV and GKrKs were associated with cardiac function, lifestyle and mental health phenotypes, and CV was also linked with adverse clinical outcomes. Our study demonstrates how CDT development at scale reveals biological insights across populations.",

author = "Shuang Qian and Devran Ugurlu and Elliot Fairweather and Toso, {Laura Dal} and Yu Deng and Marina Strocchi and Ludovica Cicci and Jones, {Richard E.} and Hassan Zaidi and Sanjay Prasad and Halliday, {Brian P.} and Daniel Hammersley and Xingchi Liu and Gernot Plank and Edward Vigmond and Reza Razavi and Alistair Young and Pablo Lamata and Martin Bishop and Steven Niederer",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",

year = "2025",

month = may,

day = "16",

doi = "10.1038/s44161-025-00650-0",

language = "English",

volume = "4",

pages = "624--636",

journal = "Nature Cardiovascular Research",

issn = "2731-0590",

publisher = "Springer",

number = "5",

}

Qian, S , Ugurlu, D, Fairweather, E, Toso, LD, Deng, Y, Strocchi, M, Cicci, L, Jones, RE, Zaidi, H, Prasad, S, Halliday, BP, Hammersley, D, Liu, X, Plank, G, Vigmond, E, Razavi, R , Young, A , Lamata, P , Bishop, M & Niederer, S 2025, 'Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization', Nature Cardiovascular Research, vol. 4, no. 5, 11437, pp. 624-636. https://doi.org/10.1038/s44161-025-00650-0

TY - JOUR

T1 - Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization

AU - Qian, Shuang

AU - Ugurlu, Devran

AU - Fairweather, Elliot

AU - Toso, Laura Dal

AU - Deng, Yu

AU - Strocchi, Marina

AU - Cicci, Ludovica

AU - Jones, Richard E.

AU - Zaidi, Hassan

AU - Prasad, Sanjay

AU - Halliday, Brian P.

AU - Hammersley, Daniel

AU - Liu, Xingchi

AU - Plank, Gernot

AU - Vigmond, Edward

AU - Razavi, Reza

AU - Young, Alistair

AU - Lamata, Pablo

AU - Bishop, Martin

AU - Niederer, Steven

PY - 2025/5/16

Y1 - 2025/5/16

N2 - Large-cohort imaging and diagnostic studies often assess cardiac function but overlook underlying biological mechanisms. Cardiac digital twins (CDTs) are personalized physics-constrained and physiology-constrained in silico representations, uncovering multi-scale insights tied to these mechanisms. In this study, we constructed 3,461 CDTs from the UK Biobank and another 359 from an ischemic heart disease (IHD) cohort, using cardiac magnetic resonance images and electrocardiograms. We show here that sex-specific differences in QRS duration were fully explained by myocardial anatomy while their myocardial conduction velocity (CV) remains similar across sexes but changes with age and obesity, indicating myocardial tissue remodeling. Longer QTc intervals in obese females were attributed to larger delayed rectifier potassium conductance GKrKs. These findings were validated in the IHD cohort. Moreover, CV and GKrKs were associated with cardiac function, lifestyle and mental health phenotypes, and CV was also linked with adverse clinical outcomes. Our study demonstrates how CDT development at scale reveals biological insights across populations.

AB - Large-cohort imaging and diagnostic studies often assess cardiac function but overlook underlying biological mechanisms. Cardiac digital twins (CDTs) are personalized physics-constrained and physiology-constrained in silico representations, uncovering multi-scale insights tied to these mechanisms. In this study, we constructed 3,461 CDTs from the UK Biobank and another 359 from an ischemic heart disease (IHD) cohort, using cardiac magnetic resonance images and electrocardiograms. We show here that sex-specific differences in QRS duration were fully explained by myocardial anatomy while their myocardial conduction velocity (CV) remains similar across sexes but changes with age and obesity, indicating myocardial tissue remodeling. Longer QTc intervals in obese females were attributed to larger delayed rectifier potassium conductance GKrKs. These findings were validated in the IHD cohort. Moreover, CV and GKrKs were associated with cardiac function, lifestyle and mental health phenotypes, and CV was also linked with adverse clinical outcomes. Our study demonstrates how CDT development at scale reveals biological insights across populations.

UR - http://www.scopus.com/inward/record.url?scp=105005464890&partnerID=8YFLogxK

U2 - 10.1038/s44161-025-00650-0

DO - 10.1038/s44161-025-00650-0

M3 - Article

AN - SCOPUS:105005464890

SN - 2731-0590

VL - 4

SP - 624

EP - 636

JO - Nature Cardiovascular Research

JF - Nature Cardiovascular Research

IS - 5

M1 - 11437

ER -

Developing cardiac digital twin populations powered by machine learning provides electrophysiological insights in conduction and repolarization

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this