Research Assistant/Associate in Cardiac Computational Modelling via Machine Learning and Biomechanics Simulations

You will engage in cutting-edge translational research that develops computational models for assessing cardiac biomechanics and for predicting outcomes in cardiac diseases. This includes (1) a machine learning model to rule out heart attacks in the emergency room, which has the potential to translate to large savings for healthcare systems in the world, (2) a computational modelling to assist in selecting the most suitable patients for fetal heart interventions performed at 2 centres in Europe.

You will work with a team of biomechanics and AI experts as well as skilled clinicians and biologists to deliver the research, and will have the chance to utilize unique large datasets.

You will be conducting research in three areas.

First, you will refine and develop a machine learning model for rapidly ruling out heart attacks in the emergency room (ER). More than a million patients present to the ER in the UK suspecting a heart attack, but only 20% actually have it. The rest are typically retained for long durations in the hospital for further monitoring, but this saps substantial hospital resources for the already burdened NHS. Our model will rapidly and safely rule out cases to avoid the retention to conserve hospital resources. You will work with a team of AI experts and cardiologists to refine the model, based on the NIHR Health Informatics Collaborative large dataset, particularly on imputation modelling to address missing data and uneven data collection across different centres.

Second, based on our recent deep learning biomechanics modelling work, you will perform cardiac biomechanical modelling to evaluate fetal heart function, to refine patient selection criteria for a fetal heart intervention, fetal aortic valvuloplasty. This intervention is a minimally invasive, catheter-based intervention to alter the development process of a fetal baby’s heart to help it avoid malformation at birth. Currently, patient selection is insufficiently accuracy, our preliminary modelling work suggest that biomechanics modelling can improve this. You will work with clinicians across Europe to test your algorithm.

You will be responsible for liaising with internal and external collaborators on data collation, perform model development and testing, and collecting feedback on results. There are ample opportunities to network with highly skilled AI experts, clinicians and biologists. You will also have the opportunity to co-mentor undergraduate, Masters and/or PhD students. You are further expected to publish findings, and help attract funding.

PhD in Computer Science, Computational Bioengineering, Mechanical or Electrical Engineering
Excellent coding skills
Preferably a familiarity with machine learning and deep learning models, as well as a familiarity with cardiology.
Ability to work well in a team, and coordinate team research
Ability to mentor junior researchers
Highly driven and proactive worker with a passionate for the academics.

The opportunity to continue your career at a world-leading institution and be part of our mission to continue science for humanity.
Grow your career: gain access to Imperial’s sector-leading as well as opportunities for promotion and progression. Sector-leading salary and remuneration package (including 39 days off a year and generous pension schemes). Be part of a diverse, inclusive and collaborative work culture with various and resources to support your personal and professional .