If someone says, "my heart beats steady as a rock", they probably need to be warned that this could be a warning of the increased likelihood of an impending heart attack. In contrast to many people’s intuition, the healthy heart does not beat steadily like a rock (do rocks even beat?) or a metronome, but with an irregular beat. This natural and healthy variation between heartbeats is known as "Heart Rate Variability" (often just called “HRV”) and is widely studied in sports and medicine, but the causes of the variability are not well understood. In this study, we will explore the causes of long-term Heart Rate Variability and investigate whether any component of Heart Rate Variability correlates with patient outcome in an intensive care unit. Our overall hypothesis is that previously undetected heart rate variability biomarkers of disease lie hidden within long-range ECG and can be detected with artificial intelligence.
The challenge of recording long range Heart Rate Variability, in the past was insoluble due to historic technical difficulties, but recent developments in the field of artificial intelligence (AI) now allow us to solve these problems. This technology is often called “Deep Learning”.
The student will:
1. Begin by deploying deep learning methods for fully automated identification of ECG QRS peeks in ECG records of healthy people and animals using both our own and publicly available ECG data repositories.
2. Next, we will tackle one of the issues often quoted about deep learning, which is that it can sometimes be opaque to users and simply outputs answers (e.g., “normal” or “abnormal”), without allowing clinicians/ other users to see why it reached that conclusion. We will solve this problem by developing data visualisation techniques that interrogate network structure. This work will enable us to extract actionable knowledge from the deep learning models.
3. Finally, the student will use ECG data from multiple patients in the Royal Liverpool University Hospital for extended periods and use deep learning models to segment the data and automatically annotate and model it. To this aim the project will use a range of advanced statistical tools (partial correlation, principal component analysis and K-means clustering) to investigate relationships between patient outcome, clinical condition and HRV parameters and identify reliable biomarkers of risk based on heart rate variability.
Student profile and training
The skills taught will vary depending on the background of the student, biology-physiology - medicine-OR maths/computing. Any of these would be suitable. The team of supervisors spans from physiology to clinical medicine and to Computing/Machine Learning and hence covers all aspects of the training needs of this project. We will provide training on Heart Rate Variability analysis, fundamental physiology, machine learning techniques coding, including Python and Matlab. This studentship will also be iCASE, which means that it includes an exciting placement with an industry where the student will work alongside a leading design and manufacturer of state of the art “wearable” heart and physiology monitoring systems.
Benefits of being in the DiMeN DTP:
This project is part of the Discovery Medicine North Doctoral Training Partnership (DiMeN DTP), a diverse community of PhD students across the North of England researching the major health problems facing the world today. Our partner institutions (Universities of Leeds, Liverpool, Newcastle and Sheffield) are internationally recognised as centres of research excellence and can offer you access to state-of the-art facilities to deliver high impact research.
We are very proud of our student-centred ethos and committed to supporting you throughout your PhD. As part of the DTP, we offer bespoke training in key skills sought after in early career researchers, as well as opportunities to broaden your career horizons in a range of non-academic sectors.
Being funded by the MRC means you can access additional funding for research placements, international training opportunities or internships in science policy, science communication and beyond. See how our current DiMeN students have benefited from this funding here: http://www.dimen.org.uk/overview/student-profiles/flexible-supplement-awards
Further information on the programme can be found on our website: http://www.dimen.org.uk/