About us:
We specialise in developing models of personalised physiology to simulate different treatment approaches. An example application is developing engineering methodologies to personalise treatment approaches for cardiac arrhythmias. We use a combination of signal processing, machine learning and computational modelling techniques to develop novel methodologies for investigating cardiac arrhythmia mechanisms from clinical imaging data and electrical recordings. We aim to translate the tools we develop for analysing electrical and imaging data to clinically predict optimal patient specific treatment strategies. We are based at the Digital Environment Research Institute and the School of Engineering & Materials Science, Queen Mary University of London. We are also a part of the Centre for Advanced Cardiovascular Imaging.
What’s New:
June 2026: ISI Malta
Caroline presented in a session on statistical modelling and machine learning for healthcare at the Regional Statistics Conference 2026 in Malta.
June 2026: Publication
Congratulations to Mahmoud for this publication in Journal of Physiology on Comparative multimodal calibration of patient-specific atrial fibrillation models: Impact of imaging and electrophysiology data on arrhythmogenic substrate identification.
Latest Software:
Constructing bilayer and volumetric atrial models at scale
Download atrialmtk, an open-source user-friendly pipeline for generating atrial models from imaging or electroanatomical mapping data enabling in silico clinical trials at scale, available at https://github.com/pcmlab/atrialmtk.
