Please find a list of available PHDs on offer.

Main Supervisor: Dr Fergal McCaffery

Duration: 4

This research will focus on the development of an approach that can assist Healthcare Delivery Organisations and Medical Device Manufacturers to implement the requirements of standards and regulations related to risks when placing devices into IT networks.

Main Supervisor: Rodd Bond (PL) Dr Julie Doyle

Duration: 4

This research will explore design strategies to implement multiple behavior change interventions in older people with heart conditions and co-morbidities. It will examine the effectiveness of these techniques over a trial period and investigate the impact of the technology on supporting / inhibiting behavior change.

Main Supervisor: Dr John Loane

Duration: 4

This research project will investigate the extent to which multi-modal ambient sensing and data analysis can track cardiac patients’ adherence to dietary and physical activity recommendations to improve their health and wellbeing in the home setting.

Main Supervisor: Dr Niamh Caprani

Duration: 4

This research will develop training models to help older adults to use ICT-based monitoring technologies at home to self-manage their cardiac conditions, addressing older learner’s capabilities, environment, family, community and healthcare provision context.

Main Supervisor: Dr Lucia Carragher

Duration: 4

This research will investigate strategies to transform community care for older people with cardiac conditions, supporting the development of a workforce skilled in person centred, technology enabled care, and informing the workforce development policy-making process.

Main Supervisor: Prof Brian Caulfield (PL)

Duration: 4

In this project, we will design and develop a knowledge discovery platform and study the effectiveness of multimodal data warehouse and data mining techniques on the accuracy, robustness, and scalability of the results of shared cardiology datasets and their sources. The techniques that will be used will take into account the feedback as an input for future use. That feedback will be given in a form of knowledge that has been already either extracted from the data or given in a form of initial repository. This project will explore new approaches of representing and modelling (like knowledge maps) the knowledge which can exploited to improve the speed-up, accuracy and reliability of the results.

Main Supervisor: Dr David Coyle

Duration: 4

This project will focus on the design, development and evaluation of mobile applications that embody differing theoretical approaches to behaviour change and coaching. It will focus on physical and mental wellbeing and will provide adaptive, personalised support for patients with cardiac conditions. The apps will take advantage of active and passive data collection and will be developed using a user-centred design methodology, involving close collaborations with representative stakeholders.

Main Supervisor: Dr Brian MacNamee

Duration: 4

This project will focus on the development of models that use patient generated data to recognise cardiac patient behaviour and lifestyle patterns in the home and community, and identify factors that influence changes in these patterns. The project will be based on the creation and analysis of a longitudinal patient-generated dataset that leverages mobile devices and sensors.

Main Supervisor: Dr David McEneaney

Duration: 3

Summary / rationale

The management of acutely unwell patients is challenging for many clinicians, as clinical decisions must be made quickly and must account for a large number of interdependent factors. A comprehensive clinical decision support system (CDSS) would be highly desirable in such a setting.

The number of interdependent and unpredictable factors involved in such scenarios results in complex adaptive systems. Conventional, algorithm-driven systems have limited utility under such circumstances. Machine learning-based systems represent a potential solution to this unmet need, but the difficulty in obtaining large datasets in the domain of acute care is a limiting factor. (More generally, there are many areas of medicine where machine learning-based systems could significantly improve patient care but where large datasets to train such systems are not readily available.) We propose that there may be a way to circumvent this issue, drawing upon the theory behind systems such as DeepMind’s AlphaGo.

Method

We propose to develop the existing prototype of the Virtu-ALS resuscitation simulator to incorporate a more comprehensive range of clinical scenarios and the ability to log and upload user actions within the software. This will be done in close liaison with the clinical staff and resuscitation training programme at Craigavon Area Hospital, where we will seek expert consultation on the clinical design of the training system and undertake early product testing and development with experienced healthcare professionals. Clinical accuracy of the system will be key to the success of the project, and in an area where high-level evidence is sparse this will rely heavily on individual experience and expertise.

When development is complete, the app will be updated on the publicly app stores. Over the last six months the app has had approximately 15 000 downloads. Based upon this, we estimate that we will be able to capture data from over 100 000 clinical decisions, along with information about scenario outcomes following these decisions. This data will come from users with widely varying and un-validated levels of experience and competence, but will be used as pre-training data for the machine-learning-based system and therefore does not need to be of especially high quality.

Following the pre-training with data accumulated from human users, we will further train the system through exposure to the resuscitation simulator. Its goal will be to optimise patient haemodynamics at any given point and minimise the time taken to reach predefined criteria for patient “stabilisation”. Assuming the simulator adequately reflects real-world clinical practice, the resultant “intelligent” system should have developed skills that are transferable to real-world situations. We will aim to demonstrate this by exposing the system to the scenarios used for the assessment of widely recognised resuscitation courses such as Advanced Life Support and Advanced Cardiac Life Support and objectively evaluating its performance.

NB – the criticism could be levelled that an algorithm-based system could pass an ALS course assessment, given the highly-controlled nature of such a scenario. We will assess the system in other ways to demonstrate that its capabilities go beyond this. The details of these further assessments have not yet been finalised.

Anticipated outcome

We aim to prove the concept that in areas of clinical medicine where machine-learning-based systems are highly desirable but where accumulation of large training sets is impractical, the use of well-designed clinical simulation can provide surrogate training data. We also expect to show that the design of such simulations is contingent upon a close working relationship and good respective domain understanding between experts in machine learning and clinical medicine, and that further collaboration between Ulster University and Craigavon Area Hospital is likely to be productive.

Main Supervisor: Dr Ian Menown

Duration: 3

Cardiovascular disease is one of the major causes of death worldwide. Substantial data indicate that CVD is a life course disease that begins with the evolution of risk factors that in turn contribute to the development of subclinical atherosclerosis. Assessing the risk for cardiovascular disease is an important aspect in clinical decision making and setting a diagnostic strategy that includes Ultrasound Intima-media thickness analysis in combination with specific biomarkers could be a way forward. In particular, assessing cardiovascular risk in primary care will be very important, as prioritising screening in the form of point-of-care diagnostics will improve patient pathways.

Intima-media thickness (IMT), is a measurement of the thickness of tunica intima and tunica media, the innermost two layers of the wall of an artery. The measurement is usually made by external ultrasound. IMT is used to detect the presence of atherosclerosis in humans and, more contentiously, to track the regression, arrest or progression of atherosclerosis. The carotid artery is the usual site of measurement of IMT. Although IMT is predictive of future cardiovascular events, the usefulness of measuring change in IMT over time is disputed, as meta-analyses have not found that change in IMT is predictive of cardiovascular events.

However, in 2003 the European Society of Hypertension–European Society of Cardiology guidelines for the management of arterial hypertension recommended the use of IMT measurements in high-risk patients to help identify target organ damage and in 2010 the American Heart Association and the American College of Cardiology advocated the use of IMT on intermediate risk patients if usual risk classification was not satisfactory.

Carotid IMT has been used in many epidemiological and clinical studies and these have shown associations with several risk factors, including type 2 diabetes, high-density lipoprotein cholesterol (HDLC), triglycerides, rheumatoid arthritis, non-alcoholic fatty liver disease etc.

Biomarkers are a common route to assessing cardiovascular risk. Markers for primary cardiovascular events include, from high to low result: C-reactive protein (CRP), fibrinogen, cholesterol, apolipoprotein-B, the apolipoprotein A/apolipoprotein B ratio, high-density lipoprotein and vitamin D.  Biomarkers for secondary cardiovascular events include, from high to low result: cardiac troponins I and T, CRP, serum creatinine, and cystatin C. For primary stroke, fibrinogen and serum uric acid are strong risk markers also.

 

Aim – The PhD will study the ability to collate critical dimensions from Ultrasound scans for the IMT and cross correlate this data with a set of determined biomarkers. Datasets will be collated from open data-sets; collated via patient trails and analysed in order to determine improved routes to evaluating cardiovascular risk in primary care scenarios.

 

Skills and Background:  Either – Image Analysis; Data Scientist; Bio-Engineering or Clinician

Main Supervisor: Dr Peter Sharpe

Duration: 3

This study will review and design new lateral flow based methodologies for assessing heart failure via blood diagnostics in line with new Heart Failure medicine that is now entering the NHS. In particular the project will focus on a lateral flow (LF) biomarker for cystatin C based kidney function diagnostics.

 

Heart Failure is the clinical syndrome that can result from any structural or functional cardiac disorder that impairs ability of ventricle to fill with or eject blood. It occurs when the heart is unable to pump sufficiently to maintain blood flow to meet the body’s needs. Signs and symptoms commonly include shortness of breath, excessive tiredness, and leg swelling.

 

This area is well known to be associated with high levels of readmissions and there is a high possibility that a point-of-care system can be developed to allow biomarker (nt-pro-BNP), respiration rate and kidney function (creatinine) monitoring thus allowing trend/alert patient management.

Key to this project realising its potential is feedbacking essential biomarker information to allow improved medicine management. Although much work is underway improved kidney function point of care diagnostics is required. Hence this project will ascertain a way forward for the use of point of care based cystatin C based kidney function LF diagnostics

 

Aim: Is to evaluate a new lateral flow biomarker based device suitable for HF assessment and monitoring in the home. To optimise and specify a way forward for the use of point-of-care based cystatin C based kidney function LF diagnostics.

 

Skills and Background:  Either – Bio-Engineering, Biochemist or Clinician

Main Supervisor: Prof Steve Leslie, Dr Mark Grindle

Duration: 3

Atrial fibrillation (AF) is a well-recognised risk factor for stroke. Despite a call for widespread screening, a proportion of patients (~30%) are asymptomatic and remain undiagnosed. Newer mobile and non-mobile technology and cloud based analysis offers the potential for opportunistic screening for AF, but the reliability and acceptability of the technology requires thorough field-tested. This project will undertake to evaluate the potential of new AF detection technologies in the Highlands and Islands with a view to informing discussions about a national screening programme.

Main Supervisor: Dr David Coyle

Main Supervisor: Prof Angus Watson, Dr Sarah-Anne Munoz

Duration: 3

There is a need for well designed, affordable and sustainable housing within the cross border area to address the demands of our social demographic. Technology enabled homes are being built to allow ambient monitoring of home dwellers and the home itself. Monitoring can be combined with digital platforms which will allow home occupants to access and order local services themselves. Smart physical design of these homes will allow them to be adapted for changing care needs, including end of life care. This form of housing may enable early detection and intervention of illness and will facilitate earlier discharge of patients from hospital. The homes will be made available for social rent through housing associations and social enterprise.

Main Supervisor: Prof Jun Wei, Dr. Andrew Treweeke

Duration: 3

Based on initial findings, we will test the interaction of Apo-B derived peptide antigens with B-cell lines in vitro. Plasma samples from patients with coronary heart disease and control subjects will be used to test IgG antibodies against Apo-B derived antigens. The resultant antibody test could be useful for prediction of cardiac events and could aid the development of precision treatment.  These case-control samples will also be used to screen circulating antibodies against gut bacteria such as E Coli, Enterococus and bacteroidetes to determine whether translocation of gut bacteria is involved in developing coronary disease. Selected antigens derived from gut bacteria will also be used to stimulate B-cells to evaluate their role in developing systemic inflammation that may be involved in cardiovascular conditions.

Main Supervisor: Prof Ian Megson (PL)

Duration: 3

The project will use existing samples to assess the potential of novel biomarkers for predicting clinical outcome following administration of contrast agents to patients. A range of risk markers will be evaluated with a view to determining suitability of prophylactic measures and of identifying patients at risk before hospital discharge. The project will involve work with clinical samples and laboratory experiments to explore mechanism.

Main Supervisor: Dr Daniel Crabtree, Dr Trish Gorely, Prof Steve Leslie

Duration: 3

.This project will use a mixed method approach to assess the risks and benefits associated with transfer of cardiac rehabilitation into the community in a rural setting. Links to primary care settings and leisure facilities will be amongst the options evaluated and input will be sought from all stakeholders (patients, clinicians, physiotherapists, leisure staff, GPs) in a co-production approach. The use of technology to improve the experience will also be explored.