A project proposal to develop new artificial intelligence (AI) technology to calculate women’s risk of pre-eclampsia has been successful in the latest round of the UK Government’s Artificial Intelligence in Health and Care Award.

King’s College London, in partnership with the University of Strathclyde, has received almost £150,000 share of the funding over one year. Approximately £110,000 will fund innovative AI research at Strathclyde with the remainder used to support app development activities and outreach.

The researchers aim to develop, with industry partners, an app for determining individual women’s risk of pre-eclampsia, and its potential severity, including post-birth complications.

They plan to combine two existing forms of a calculating tool known as PIERS (Pre-eclampsia Integrated Estimate of Risk Score), into an integrated system which is favourable to women, their midwives and doctors, and engineers.

Project Principal Investigator, Professor Peter von Dadelszen, Professor of Global Women’s Health, King’s College London, said: “Developing, validating, and implementing the PIERS models has been a 20- year journey to date. During that time, our thinking about approaches, such as developing distinct models for well-resourced and resource-constrained settings, and the methods used to develop and test models has evolved.

“This award provides the opportunity provide individual pregnant women with high blood pressure, their families, and their care providers accurate information about their risks so that optimal shared decisions can be made about place of care and timing of birth. This matters because pre-eclampsia carries increased risks of maternal death, stillbirth, and newborn death, as well as ‘near miss’ events when deaths are narrowly avoided.

“This is true whether a woman lives in London or Lusaka, Glasgow or Garissa – it is a matter of distributed, equitable, and excellent care”.

Dr Kimberley Kavanagh, a Senior Lecturer in Strathclyde’s Department of Mathematics and Statistics, is a partner in the project. She said: “Pre-eclampsia is the most dangerous form of high blood pressure in pregnancy. It is responsible for the deaths of more than 70,000 women and 500,000 babies every year worldwide and costs the NHS alone £300 million annually.

“Most of the one in 30 pregnant women who develop pre-eclampsia have mild disease that goes away soon after birth. However, about one in 10 of UK women with pre-eclampsia experience complications that threaten or alter their lives, such as stroke.”

Dr Paul Murray, a Senior Lecturer in Strathclyde’s Department of Electronic & Electrical Engineering and also a partner in the project, said: “We previously developed tools which clearly identify the women who are at most, and least, risk for developing life-threatening and life-altering complications of pre-eclampsia. What is needed is a single tool that uses all available data to best identify women in these groups.”

The existing versions of the tool are:

miniPIERS, which includes details about an individual woman, including prior births and weeks into pregnancy, her symptoms, such as headache, her blood pressure, the amount of protein in her urine and the amount of oxygen in her blood. It is particularly useful for women while they are outpatients

fullPIERS, which is broadly similar to miniPIERS but adds the strength of laboratory tests to improve accuracy and is useful once women are admitted to hospital.

The development of panPIERS will be carried out with the use of AI and existing large data sets. It will produce a new AI-driven panPIERS model, which will use data relating to more than 20,000 women who participated in previous published research projects. AI will be used to develop the proposed panPIERS tool, which will include ethnicity, socio-economic status and details of the woman’s current pregnancy. The researchers will evaluate the AI tool based on how it performs initially and how effective it is for monitoring the woman’s progress over the following days.

The project will also develop a novel panPIERS digital health app, designed with patients, midwives and doctors, to inform individual women and their care providers of an accurate estimate of risks when pre-eclampsia is either suspected or confirmed.

The researchers will share results with women and their families and medical journal papers will be published. During the planned follow-on step of commercialisation, the researchers plan formal tests of the panPIERS app, including clinical trials.

The AI Award is making £140 million available over four years to accelerate the testing and evaluation of artificial intelligence technologies which meet the aims set out in the NHS Long Term Plan.

Dr Indra Joshi, Director of AI at NHSX, said: “With this latest round of AI Award winners, we now have an incredible breadth of expertise across a wide range of clinical and operational areas. Through this award, the University of Strathclyde and King’s College London will be at the forefront of applying artificial intelligence in new ways to transform health and care.”

Dan Bamford, Deputy Director AI Award, Accelerated Access Collaborative, said: “Congratulations to the University of Strathclyde and King’s College London on their success as one of our winners in Round 2 of the AI Award. We look forward to working with them as they develop and test their technology further, so that more patients can benefit from this cutting-edge artificial intelligence.”

Partners in the study also include King’s College London’s School of Biomedical Engineering and Imaging Sciences, the University of Birmingham and the charity, APEC (Action on Pre-eclampsia).

The research is linked to Strathclyde’s HealthTech cluster, one of the University’s six clusters of research capability and innovation focus. The cluster draws on interdisciplinary expertise in health, engineering, life sciences and social sciences, with industry-facing themes in Medical Diagnostics and Wearables, Digital Health, and Advanced Rehabilitation, as well as an underpinning focus on Healthcare AI, Machine Learning, Data Science and Data Analytics.

The cluster is characterised by deep research capability, excellent facilities and outstanding research talent, complemented by translational research programmes that exchange knowledge to large Tier 1 companies and their innovation-led supply-chain partners and other SMEs. The cluster enables agile collaborative research and innovation programmes which accelerate the creation and adoption of new knowledge.

The cluster forms part of a wider health technologies ecosystem along with the Health and Care Futures initiative, which has a focus on the NHS, Social Care and the Third Sector. It is also aligned to Health and Wellbeing, which is among the University’s seven strategic themes and focuses on researchers and citizens.