Mapping populations to patients: designing optimal ablation therapy for atrial fibrillation through simulation and deep learning of digital twin

We will combine biophysical simulation and deep learning methods with a longitudinal digital twin approach to optimise risk prediction and choice of therapy for atrial fibrillation. We aim to move predictions from the acute response to the long-term response; from the average patient to an individual patient; from standard treatments to any treatment approach; from small patient cohorts to large virtual trials; and from long simulation times to short clinical timescales.

Development and Validation of Smartphone-Based Tools for Characterisation of Gait

This project aims to develop and validate smartphone-based tools for characterising gait. By utilizing the sensors and capabilities of modern smartphones, the project seeks to provide accessible, accurate, and cost-effective solutions for gait analysis, benefiting both healthcare providers and researchers in diagnosing and monitoring gait-related conditions.

Virtual Atria with Personalised Electrophysiology for Atrial Fibrillation Therapy Planning - SEMS Industry-supported PhD Studentship

Predicting Atrial Fibrillation Mechanisms Through Deep Learning

Persistent atrial fibrillation (AF) patients are a heterogeneous population: some patients require multiple procedures, with more extensive ablation strategies; while for others, isolation of the pulmonary veins using ablation (PVI) is sufficient. Identifying persistent AF patients where PVI will be a sufficient treatment remains a clinical challenge, which if solved could lead to improved safety, better patient selection, as well as decreased time and cost for procedures. Biophysical simulations personalised to cardiac imaging and electrical data may offer substantial insights into the mechanisms underlying AF, but run too slowly to be used during clinical procedures. My objective is to develop a combined biophysical simulation and deep learning network pipeline that accurately quantifies the likelihood of success of PVI for an individual patient quickly enough for use during a clinical procedure, to guide ablation therapy.