Physics-informed neural network for predicting myocardial mechanics from in vivo physiological measurements

Abstract

Structural heart diseases (SHDs) are characterized by progressive myocardial remodeling, yet the tissue-level mechanical properties underlying this process cannot be measured directly in vivo. This limitation restricts the ability of conventional physiological measurements to fully characterize myocardial remodeling and disease progression. Here, we present a physics-informed neural network (PINN) framework that integrates constitutive biomechanics with organ-level physiological measurements to simultaneously infer myocardial biomechanical descriptors and predict physically consistent stress responses. By embedding a hyperelastic constitutive model within the learning process, the framework links physiological measurements with tissue-level mechanics while preserving biomechanical consistency. Using right ventricular remodeling in pulmonary hypertension (PH) as a representative model of SHDs, the proposed framework accurately reproduced nonlinear stress-stretch behavior and outperformed conventional data-driven machine learning approaches for stress prediction. Furthermore, incorporation of PINN-derived tissue-level descriptors with organ-level physiological measurements improved disease stratification and enhanced separation between control, mild, and severe PH remodeling states. These findings support physics-informed constitutive learning as an interpretable framework for integrating organ-level physiology with tissue-level biomechanics and establish a foundation for future biomechanics-informed characterization of myocardial remodeling across SHDs.

In vivo measurements of fascia lata effective mechanics combined to a memory fiber–recruitment–viscoelastic modeling approach
Franck Germain, Thomas Gibaud
Soft Matter23 Sep 2026Peer-reviewedLicence not statedFull textGeneral biologyHAL
Can non-invasive surface measurements predict abdominal wall myofascial mechanics? An exploratory study
Grégoire Deshairs, Arthur Jourdan, Catherine Masson +2
Multidisciplinary Biomechanics Journal26 Oct 2026Peer-reviewedCC BY 4.0Full textCell biologyHAL
Mechanofiltration Enables High-Throughput Measurements of Bacterial Cell Mechanics
K. G. DeFrates, J. W. Hwang, G. Jimenez +3
bioRxiv1 Sep 2026PreprintAll rights reservedFull textMicrobiologybioRxiv
Replacing EEG with peripheral physiological signals for driving behavior recognition: a physiology-informed multimodal approach
Huaqiang Xu, Yuwei Zhang, Xiaoqing Sun +2
Cognitive Neurodynamics27 Oct 2026Peer-reviewedLicence not statedFull textNeurosciencePMC
Predicting Cerebral Pericyte Contractility Across Experimental and Physiological Conditions: an in-silico framework
A. Coccarelli, A. Al-Areqi, O. F. Harraz
bioRxiv1 Sep 2026PreprintCC BYFull textSystems & synthetic biologybioRxiv

Cite

BibTeX RIS

BibTeX

@misc{mehdi2026physicsinformed,
  title = {{Physics-informed neural network for predicting myocardial mechanics from in vivo physiological measurements}},
  author = {Rana Raza Mehdi and Nikhil Kadivar and Sunder Neelakantan and Kyle J. Myers and Eric Wang and Melih Agraz and Peng Zhang and George Karniadakis and Gaurav Choudhary and Reza Avazmohammadi},
  howpublished = {bioRxiv},
  year = {2026},
  month = oct,
  doi = {10.64898/2026.10.16.756787},
  url = {https://www.biorxiv.org/content/10.64898/2026.10.16.756787v1},
  note = {CC BY},
}

RIS

TY  - UNPB
TI  - Physics-informed neural network for predicting myocardial mechanics from in vivo physiological measurements
AU  - Rana Raza Mehdi
AU  - Nikhil Kadivar
AU  - Sunder Neelakantan
AU  - Kyle J. Myers
AU  - Eric Wang
AU  - Melih Agraz
AU  - Peng Zhang
AU  - George Karniadakis
AU  - Gaurav Choudhary
AU  - Reza Avazmohammadi
PY  - 2026
DA  - 2026/10/16
PB  - bioRxiv
DO  - 10.64898/2026.10.16.756787
UR  - https://www.biorxiv.org/content/10.64898/2026.10.16.756787v1
AB  - Structural heart diseases (SHDs) are characterized by progressive myocardial remodeling, yet the tissue-level mechanical properties underlying this process cannot be measured directly in vivo. This limitation restricts the ability of conventional physiological measurements to fully characterize myocardial remodeling and disease progression. Here, we present a physics-informed neural network (PINN) framework that integrates constitutive biomechanics with organ-level physiological measurements to simultaneously infer myocardial biomechanical descriptors and predict physically consistent stress responses. By embedding a hyperelastic constitutive model within the learning process, the framework links physiological measurements with tissue-level mechanics while preserving biomechanical consistency. Using right ventricular remodeling in pulmonary hypertension (PH) as a representative model of SHDs, the proposed framework accurately reproduced nonlinear stress-stretch behavior and outperformed conventional data-driven machine learning approaches for stress prediction. Furthermore, incorporation of PINN-derived tissue-level descriptors with organ-level physiological measurements improved disease stratification and enhanced separation between control, mild, and severe PH remodeling states. These findings support physics-informed constitutive learning as an interpretable framework for integrating organ-level physiology with tissue-level biomechanics and establish a foundation for future biomechanics-informed characterization of myocardial remodeling across SHDs.
SN  - 2692-8205
ER  -

Abstract

Related

Cite