Parameterising the progression of cardiac electrophysiological variability across the healthy lifespan using machine learning
Dr Michael Colman
Dr Al Benson
No more applications being accepted
Competition Funded PhD Project (European/UK Students Only)
Computational models of the heart provide powerful research tools for undertaking systematic evaluations of normal physiologic function, as well as for studying the intricately integrated (and therefore non-intuitive) relationships that exist between the different components of a complex physiological system. However, the models currently available are deterministic and do not incorporate aspects that lead to normal physiological variability in the functioning of the heart (normal temporal and population variations in ion channel gating that lead to beat-to-beat variation in cellular action potential duration, for example).
These variations in normal cardiac function at the protein and cellular levels can have profound effects on normal function at the whole-heart level. This variability increases with ageing, and may contribute to the declining cardiac function seen with healthy ageing.
Due to the large number of parameters in cardiac models, interpretation of normal variability from experimental data, and quantification of its impact on cardiac function using our computational modelling approach, is non-trivial. We will use a machine learning approach (e.g. Cairns et al., Chaos 27, 093922, 2017) to analyse the large experimental datasets currently available, in order to parameterise normal temporal and population variability in our cell models, and quantify and interpret the impact of this variability at the whole heart level.
The primary supervisor and both secondary supervisors have a background in computational modelling of the heart at different temporal and spatial scales, involving the development of mathematical descriptions of physiological processes, computational coding of these mathematical equations, and development of efficient integration algorithms in order that the developed models are computationally tractable. Our computational approach allows us to generate very large datasets examining functional effects of all possible perturbations of a system (something that is not possible using experimental techniques), and subsequently use a bioinformatics “data mining” approach to identify the key control points in the system being studied; such data analysis techniques often require the development of bespoke mathematical/computational algorithms. Training in these areas (mathematics, computation and bioinformatics) will be a necessary aspect of the project for the student, and will be provided by the project supervisors. Although our computational techniques are typically applied to cardiac data, there is absolutely no reason why the techniques cannot be applied to other research areas (for example, we have previously trained students from the neuroscience research group how to use our techniques to analyse their data).
For informal enquiries please contact Dr. Michael Colman at [Email Address Removed]. Visit http://physicsoftheheart.com/ for further details on the research group.
Please apply online here: https://studentservices.leeds.ac.uk/pls/banprod/bwskalog_uol.P_DispLoginNon
Project is eligible for funding under the BBSRC White Rose DTP: Doctoral Studentships in Artificial Intelligence, Machine Learning and Data Driven Economy.
Successful candidates will receive funding for 4 years, covering UK/EU fees and research council stipend (£14,777 for 2018-19).
Candidates should have, or be expecting, a 2.1 or above at undergraduate level in a relevant field. If English is not your first language, you will also be required to meet our language entry requirements. The PhD is to start in Oct 2018.
Apply online: https://studentservices.leeds.ac.uk/pls/banprod/bwskalog_uol.P_DispLoginNon
Include project title and supervisor name, and upload a CV and transcripts.
How good is research at University of Leeds in Biological Sciences?
FTE Category A staff submitted: 60.90
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities