UK/EU students

PhD Studentship - Can artificial intelligence processing of clinical information optimise ambulance care of patients with suspected stroke

Value of award

100% of home tuition fees paid and annual living expenses at UKRI rate (currently £15,609 per year). This award is only open to home (UK) students. A research training support grant of £5000 per year is available to cover research costs and local/national/international travel (conferences and exchanges).

Number of awards


Start date and duration

September 2021 for 3 years full time.

Application closing date

20 April 2021.


The NIHR Applied Research Collaboration North East North Cumbria is offering a 3 year full time applied methodological (digital health science) doctoral fellowship hosted by the Newcastle University Stroke Research Group and the NIHR Newcastle MedTech and In vitro diagnostics Co-operative (MIC).

The main purpose is to examine whether an artificial intelligence approach can combine information routinely collected during emergency ambulance assessment of patients with suspected stroke to improve the accuracy of clinical triage. Using data from previous clinical studies, further analysis will consider interactions between information routinely collected by ambulance practitioners and additional biomarkers, and examine whether identification of different patient subgroups can be enhanced by sophisticated integration of these different information sources. The intention is to build a more efficient clinical care pathway using information immediately available to ambulance practitioners. 

This work addresses an important question for patients, clinicians and healthcare systems. Suspected stroke is a common, time-critical, medical emergency but there are many other conditions which produce the same symptoms, and patients often end up on the wrong care pathway. Ambulance staff recognise possible stroke by looking for typical symptoms such as arm weakness using the ‘Face Arm Speech Test’, but also routinely collect other demographic and health information which could be used to improve the accuracy of their assessment. As there are many possible combinations of information, and many alternative diagnoses for patients with stroke-like symptoms, this may be an ideal opportunity for development of an artificial intelligence algorithm to assist ambulance staff by determining the probability that stroke is the underlying condition. There is no portable test to identify stroke, but ongoing studies are evaluating the performance of novel biomarker technologies, the results of which could be combined with clinical information to improve stratification into key subgroups requiring different care pathways and specialist treatments.

The Newcastle University Stroke Research Group is an established multidisciplinary team with a global reputation due to publications in high impact journals (Lancet, JAMA, Stroke) and presentations at key international scientific meetings. Our team have regularly been awarded funding by NIHR, Medical Research Council, Health Foundation, Innovate UK and the Stroke Association. One of our main interests is accurate stratification of patients along different emergency care pathways to improve access to specialist treatments in hospital, using both clinical information and novel diagnostics. Our research involves close working with NHS hospital and ambulance services in order to improve patient outcomes and service efficiency.

The NIHR Newcastle MIC is one of 11 centres across England generating high quality evidence that demonstrates the potential value of new medical tests, including advancing methodological approaches for the use of clinical and test data. The MIC methodologists have expertise in machine learning and related techniques. The team receive project funding from NIHR, Innovate UK and industry partners.


Newcastle University, via the NIHR Applied Research Collaboration (ARC) North East and North Cumbria (NENC).

NIHR ARC NENC is one of 15 regional ARCS funded by the National Institute for Health research (NIHR) to bring together those needed to support research to improve health and care. Our vision is to deliver ‘better, fairer health and care at all ages and in all places’ through collaborative production and implementation of high quality applied health research in our seven themes. Our doctoral fellows are distributed across themes and universities according to the topic and required supervision. They are a crucial part of our ARC capacity building strategy.

Name of supervisor(s)

Chris Price (Lead)

Lisa Shaw

Clare Lendrem

Peter McMeekin (Northumbria University)

Eligibility Criteria

Candidates should be trained to Masters level in statistics, health informatics, digital health science or a related field, with an awareness of how artificial intelligence approaches can be used in a health care setting, particularly on a time-critical care pathway. The ideal candidate will have experience of working on health related projects, and also be able to independently engage with service providers (ambulance paramedics, doctors, nurses) to understand the most suitable algorithm content for integration with other aspects of care. Basic awareness of AI approaches to healthcare data processing is required, but training can be provided in the most relevant analsyis techniques.

If your first language is not English you need an overall IELTS score of 6.5 (at least 5.5 in all sub-skills) or equivalent language qualification.

This award is only open to home (UK) students.

How to apply

You must apply through the University’s online postgraduate application system by creating an account. To do this please select ‘How to Apply’ and choose the ‘Apply now’ button.

All relevant fields should be completed, but fields marked with a red asterisk must be completed. The following information will help us to process your application. You should:

*You will not be able to submit your application until you have submitted your degree transcript/s.


For further information please email Professor Christopher Price.

Eligible Courses