Post-Doctoral Research Associate in Statistical Risk Prediction of Sudden Cardiac Death using Machine Learning & Advanced Digital Twin Cardiac Modelling

King's College London

Job id: 085347. Salary: £43,205 – £50,585 per annum, including London Weighting Allowance.

Posted: 27 February 2024. Closing date: 03 March 2024.

Business unit: Faculty of Life Sciences & Medicine. Department: Biomedical Engineering.

Contact details:Dr Martin Bishop. [email protected]

Location: St Thomas’ Campus. Category: Research.

Job description

Sudden cardiac death due to major arrhythmic events remains one of the biggest causes of mortality in Western Society. Although implanted cardioverter defibrillators represent a potentially life-saving treatment for people suffering lethal arrhythmias, the clinical decision to identify those patients who should receive such a device remains one of the utmost challenges in present-day clinical medicine. Currently-used clinical tools available to help make these life-or-death decisions are woefully lacking. Subsequently, the vast majority of patients who receive a device never make use of it, whilst large numbers of people suffer sudden cardiac death without a device because their elevated need was not identified.

In this project, funded by the British Heart Foundation, we will develop novel ways to predict individual patient risk of suffering lethal arrhythmias. We plan to do this using computer models derived from images and measurements of patients’ hearts to come-up with new methods of assessing individual patient risk. The models will assess the arrhythmogenic potential of a patient’s heart by considering the changes in shape of the ventricle as well as the vulnerability to sustain arrhythmic electrical behaviour within areas of scarred tissue in the heart (formed from prior heart attacks) using detailed biophysical simulations. An important component will be creating and training artificial intelligence (machine learning) models which utilise the ‘raw’ clinical data (images, ECGs, etc) alongside the simulation-derived biomarkers. Initially, our models will be trained on existing extensive databases to ensure that they provide robust predictive power. We hope that our innovative new approach will bring about a paradigm shift in risk prediction and provide clinicians with a tool to facilitate more accurate decision making.

This work will be performed in close collaboration with the clinical researchers at KCL, St Thomas’ Hospital and the Royal Brompton Hospital. The post will use the computational and clinical electrophysiological infrastructure provided by the School of Biomedical Engineering and Imaging Sciences and will be based at St Thomas’ Hospital.

This post will be offered on a fixed-term contract for 2 years.

This is a full-time post – 100% full time equivalent.

Key responsibilities

  • Curation and analysis of cardiac MR images, ECG and other patient data  
  • Construction of detailed computational patient-specific models from imaging data 
  • Execution and analysis of advanced cardiac electrophysiology simulations 
  • Creation of advanced machine learning models for risk prediction using patient data and simulation-derived biomarkers. 
  • Statistical analysis of data for risk prediction 
  • Achieve the above objectives in a coordinated way by effective teamwork and collaboration with colleagues

The above list of responsibilities may not be exhaustive, and the post holder will be required to undertake such tasks and responsibilities as may reasonably be expected within the scope and grading of the post.

Skills, knowledge, and experience

Essential criteria

  • 1st or 2nd class hons degree in computer science, biomedical engineering, physics, mathematics or related subject 
  • PhD awarded, or near completion*, in computer science, biomedical engineering, physics, mathematics or related subject 
  • Good programming skills in Python, Matlab and/or C++. 
  • Developing complex software 
  • Advanced knowledge of artificial intelligence, machine learning and statistical approaches for prediction with large data sets. 
  • Good writing and presentation skills 
  • Desire to work in medical modelling in a clinical environment 
  • Flexible approach to hours of work and duties 
  • Able to work on own initiative and in a team 
  • Able to work with and communicate effectively with people from wide variety of disciplines and organisations 
  • * Please note that this is a PhD level role but candidates who have submitted their thesis and are awaiting award of their PhDs will be considered. In these circumstances the appointment will be made at Grade 5, spine point 30 with the title of Research Assistant. Upon confirmation of the award of the PhD, the job title will become Research Associate and the salary will increase to Grade 6.

    Desirable criteria

  • Knowledge of cardiac physiology
  • Knowledge of how to perform numerical simulations and analysis
  • Advanced knowledge of signal and image processing techniques
  • Experience in computational physiological modelling
  • View or Apply
    To help us track our recruitment effort, please indicate in your email – cover/motivation letter where ( you saw this job posting.

    Job Location