I work under Dr Caroline Roney and very closely with Dr Alexander Zolotarev in the research of Physics Informed Neural Networks and its impacts on personalised atrial fibrillation. 

What is it that I do?

Atrial fibrillation is characterised by irregular and disorganised electrical activity in the atria which can vary significantly across individuals. Current modeling techniques often struggle to balance precision, computational efficiency, and personalisation. PINNs provide a promising solution by embedding the governing equations of cardiac electrophysiology directly into the structure of neural networks. This allows us to leverage the power of deep learning while ensuring the results adhere to the underlying physics of electrical signal propagation.

In this research, we aim to develop patient-specific models of atrial electrical activity by integrating individual anatomical data and tissue-specific electrophysiological parameters. By doing so, we hope to uncover precise activation patterns, identify potential arrhythmic pathways, and provide insights that could inform more effective and personalised treatment strategies for AF. PINNs represent a paradigm shift in modeling complex systems like the heart, enabling us to achieve a level of personalisation and accuracy that was previously unattainable. As I dive deeper into this work, I’m excited to contribute to a field that bridges physics, engineering, and medicine, with the ultimate goal of advancing patient care.