Improving outcomes of childbirth and addressing disparity between ethnic groups with Causal Artificial Intelligence (AI) – PhD Public Health Ref: 5887

Supervisors

Dr Anna Laws - University of Exeter - Faculty of Health and Life Sciences

Dr Michael Allen - University of Exeter - Faculty of Health and Life Sciences

Professor Yinghui Wei - University of Exeter - Faculty of Health and Life Sciences

NIHR Applied Research Collaboration (ARC) South West is inviting applications for a PhD studentship to commence on 21 September 2026 or as soon as possible thereafter.  For eligible students the studentship will cover Home tuition fees plus an annual tax-free stipend of at least £21,805 for 3 years full-time. We welcome applicants who wish to study less than full-time, provided they complete their studies before March 2031. The student would be based in the ARC South West in the Faculty of Health and Life Sciences at St Luke’s Campus in Exeter. A training and development budget will also be provided to support the activity of the student.

2. Problem or issue to be investigated.

Infant outcomes in pregnancy vary markedly by ethnic group. In England, infant mortality rates are twice as high among Black infants (6.8 per 1000 live births) and around one and a half times as high among Asian or Asian British infants (5.4 per 1000 live births) than for White infants (3.2 per 1000 live births).

3. Research questions/aims and objectives.

Research question: What factors, present before or during pregnancy and childbirth, does Causal AI identify as influencing infant outcome? Which are modifiable? Which modifiable factors could reduce ethnic disparities in infant outcomes?

Aim: This PhD will develop and apply advanced Causal AI methods to a maternity dataset covering the Liverpool area to identify modifiable care factors that could help reduce the pronounced ethnic inequalities in infant outcomes during pregnancy and birth.

Objectives:

·         Build a causal model to develop a data-driven understanding of the direct and indirect causes of poor infant outcomes.

·         Find the strength of the causal effect of each factor and so identify which factors have the potential to make the biggest changes to outcomes.

·         Validate the results with expert knowledge from obstetricians.

·         Identify the modifiable factors which are actionable of follow-up. These will have an optimal balance of having a significant effect on outcomes and being achievable for the relevant patients.

In the UK, about one in seven newborns each year are unwell enough to need care in a neonatal unit. Among so many mothers, there is wide variation in the factors that may contribute to poor outcomes for babies. These factors can include the mother’s health before pregnancy, the number and type of tests and checks during pregnancy, and the course of labour and any interventions during childbirth. The complexity and inconsistency of the data make it difficult to identify the true causes of poor outcomes.

An emerging field in health data science is Causal Artificial Intelligence (AI). In traditional analysis it is possible to find statistical links between factors but not to identify which factors cause changes in others. Existing AI methods can learn to recognise combinations of several factors and accurately calculate an outcome for each patient, but the rules used are too complex to be interpreted by humans. The novel aspect of Causal AI is that the model is designed to clearly explain the logic of why each outcome is predicted. This in- built cause-and-effect setup will prove important for patient and clinician trust in the model.

2. Problem or issue to be investigated.

Infant outcomes in pregnancy vary markedly by ethnic group. In England, infant mortality rates are twice as high among Black infants (6.8 per 1000 live births) and around one and a half times as high among Asian or Asian British infants (5.4 per 1000 live births) than for White infants (3.2 per 1000 live births).

3. Research questions/aims and objectives.

Research question: What factors, present before or during pregnancy and childbirth, does Causal AI identify as influencing infant outcome? Which are modifiable? Which modifiable factors could reduce ethnic disparities in infant outcomes?

Aim: This PhD will develop and apply advanced Causal AI methods to a maternity dataset covering the Liverpool area to identify modifiable care factors that could help reduce the pronounced ethnic inequalities in infant outcomes during pregnancy and birth.

Objectives:

1. Build a causal model to develop a data-driven understanding of the direct and indirect causes of poor infant outcomes.

2. Find the strength of the causal effect of each factor and so identify which factors have the potential to make the biggest changes to outcomes.

3. Validate the results with expert knowledge from obstetricians.

4. Identify the modifiable factors which are actionable of follow-up. These will have an optimal balance of having a significant effect on outcomes and being achievable for the relevant patients.

4. Proposed methodology and methods.

The data available covers over 30,000 pregnancies in the Liverpool area and has details on over 200 aspects of each, including the mother’s pre-pregnancy health, the birth, and the immediate neonatal care. The principal indicators of outcome are: the number of days receiving assistance with breathing through ventilation in neonatal care (including days intubated); and infant death.

Causal AI is a key emerging area that the Engineering and Physical Sciences Research Council (EPSRC) has identified as needing development in the UK, and is supporting in application to health through the CHAI (Causality in Healthcare AI) network, of which the University of Exeter is a member.

Three main aspects of Causal AI will be used here.

1. Causal discovery. Causal discovery methods work by comparing how strongly each variable works as a predictor of the measured outcome. Then a group of the strongest links can be built up to show how all of the factors connect.

2. Directed Acyclic Graphs (DAGs) are flow charts that display the causal model using arrows to show the direction of each factor’s effect on other factors. DAGs are easy to understand for people without any knowledge of Causal AI methods.

3. Causal inference. The strength of the effect of each factor on each other can be found using standard methods to combine the values in the original data with the structure of the causal model.

Causal discovery and inference methods are well-established and readily applicable to idealised data. However, a major focus of this project will be on ensuring that these tools perform reliably with real-world data and that the resulting causal models align with expert knowledge. The skills developed in applying Causal AI methods will be highly transferable to other datasets and future projects within PenARC and beyond. Similar data from the South West could be introduced to extend the Liverpool findings and The Maternity Services Data Set (MSDS) could be used to identify the national impact.

5. Dissemination and impact plans.

Results will be published in academic paper(s) and/or at conferences with a clinical target audience and CHAI events and including a plain English summary for the public. We will also maintain an open-access online book with details of the full process from the original data to main results, where each section would have a plain English summary for the public. We will ask obstetricians how best to share the identified actionable factors.

6. Patient and public involvement and engagement Patient and Public Involvement and Engagement (PPIE) would be invaluable for judging which factors would be practical to modify for most people, and a PPIE group would best understand the balance of a practically-modifiable factor with a small effect or a difficult- to change factor with a large effect. The group will also advise on whether the plain- English results would be understandable for the public.

7. Research inclusion.

Care will be taken to ensure that the PPIE involves people from the groups affected by the research. This is likely to include people from the ethnic minority backgrounds considered, and to include representation from any important differences identified, for example whether the place of birth was a midwife-led or obstetrician-led unit.

“The studentship will be awarded on the basis of academic merit. Students who pay international tuition fees are eligible to apply. However, these candidates should note the following:

• The award covers only part of the international tuition fee, approximately £27,000.
• It does not include a stipend for living expenses.
• International applicants will need to cover additional costs, including:
• Student visa fees
• Immigration Health Surcharge
• Relocation expenses associated with moving to the UK to undertake a PhD.

International fee-paying applicants should ensure they have sufficient funds to meet these costs before applying.

The conditions for eligibility of home fees status are complex and you will need to seek advice if you have moved to or from the UK (or Republic of Ireland) within the past 3 years or have applied for settled status under the EU Settlement Scheme.”

Entry requirements

Applicants for this studentship must have obtained, or be about to obtain, a First or Upper Second Class UK Honours degree, or the equivalent qualifications gained outside the UK, in an appropriate area of healthcare data science or an area with strong quantitative and programming elements, such as physics, mathematics, statistics or computer science.

 If English is not your first language you will need to meet the English language requirements and provide proof of proficiency. Click here for more information.

Doctoral Award Person Specification

Essential

·         Hold a 1st or 2:1 bachelor’s degree, or equivalent If not, you will usually need to have a relevant master’s degree

·         Have prior research experience or training to prepare for a PhD

·         Not already hold a relevant PhD or equivalent

·         Show strong academic and professional skills needed to complete a PhD

Desirable

·         Demonstrate originality and independent critical thinking in proposing research with real-world benefits for patients, the public, and the health and social care system

·         Knowledge of the priorities in the area of research interest

·         Demonstrate an alignment with NIHR strategic priorities, where applicable.

Successful applicants will become members of the NIHR Academy, and further information about this can be found here https://www.nihr.ac.uk/career-development/research-career-funding-programmes/supporting-career-development/opportunities-infrastructure.

How to apply

Apply now

To apply, please click the ‘Apply Now’ button above. In the application process you will be asked to upload several documents [you are not required to have all of these, please choose which items you would find helpful for shortlisting]. 

•             CV

•             Letter of application (outlining your academic interests, prior research experience and reasons for wishing to undertake the project).

•             Transcript(s) giving full details of subjects studied and grades/marks obtained (this should be an interim transcript if you are still studying)

•             Two references from referees familiar with your academic work. If your referees prefer, they can email the reference direct to PGRApplicants@exeter.ac.uk quoting the studentship reference number.

•             If you are not a national of a majority English-speaking country you will need to submit evidence of your proficiency in English.

The closing date for applications is midnight on 28th July 2026.  Interviews will be held virtually in August.

All application documents must be submitted in English. Certified translated copies of academic qualifications must also be provided.

Please quote reference 5887 on your application and in any correspondence about this studentship.

NIHR are committed to equality, diversity and inclusion in everything we do. Diverse people and communities shape our research, and we strive to make opportunities to participate in research an integral part of everyone’s experience of health and social care services. We develop researchers from multiple disciplines, specialisms, geographies and backgrounds, and work to address barriers to career progression arising from characteristics such as sex, race or disability. Please let us know if you need any reasonable adjustments made to the application process and we will be happy to explore whether this is possible. 

Potential applicants working in community, social care and public health are welcome to contact us to explore their suitability.

For general information about this studentship, reasonable adjustments and the application process, please contact PGRApplicants@exeter.ac.uk. Project specific queries should be directed to Dr Anna Laws (a.laws2@exeter.ac.uk). Queries about the award itself can be directed to arcsouthwest@exeter.ac.uk 

Summary