Scottish researchers have developed a new model that quickly and precisely identifies the maternal risk of a serious condition causing high blood pressure during and after pregnancy.

Developed by a team at the University of Strathclyde, researchers say their potentially lifesaving model follows from a long-term collaborative study investigating more than 8,800 pregnant women across 11 countries.

The new risk-prediction model, called PIERS-ML(Pre-eclampsia Integrated Estimate of Risk – Machine Learning) has been developed with artificial intelligence and seeks to account for variables of countries’ GDP.

As a result, the research team says it is likely the “most generalisable” model for pre-eclampsia developed so far.

The PIERS-ML model was able to identify nearly 40% of women with pre-eclampsia for whom care should be altered.

Pre-eclampsia is estimated to affect between 2% and 4% of pregnancies and is a leading cause of maternal morbidity and mortality worldwide.

While the majority of pre-eclampsia cases in the UK are mild, around 1 in 10 affected people in the UK experience life-threatening or life-changing complications, such as stroke.

Pre-eclampsia is estimated to cause 46,000 maternal deaths and half a million stillbirths and newborn deaths a year, nearly all occurring in low and middle-income countries.

Dr Tunde Csobán, lead author on the paper and research assistant at the University of Strathclyde’s Mathematics and Statistics Department, said:

“Pre-eclampsia presents considerable, often fatal, risks to women and their children.

“There is an urgent need for an effective means of assessing these risks, so they can be managed and support can be offered.”

The study recruited 8,843 women from 53 maternity units in 11 low, middle and high-income countries and categorised maternal risk in relation to health system, demographic and clinical data.

The model does not include maternal symptoms, after studies of previous models found that this subjective measure – with ‘variable definitions and inconsistent documentation’ in health records’ – represented a weakness.

Instead results of tests were like ‘mean platelet volume’ commonly reported for all pregnancies where women are experiencing high blood pressure, were included.

The team found that the PIERS-ML model improves identification of women with pre-eclampsia who are at lowest and greatest risk of severe adverse outcomes within just two days of assessment.

Moreover, the researchers report that the model can support effective provision of more accurate guidance for patients, their families and maternity care providers.

Dr Kimberley Kavanagh, co-author on the study and senior lecturer at the University of Strathclyde’s Mathematics and Statistics department, said:

“The model we have developed has been rigorously tested and shown to deliver fast, precise predictions of the risks, in a way which can be adapted to the individual circumstances of women around the world.”

Dr Kavanagh added that the research team hopes to make the model available as an app to be utilised in clinical settings to “potentially save many lives”.

Almost two decades in the making, Professor Peter von Dadelszen, collaborator and principal investigator and Professor of Global Women’s Health at King’s College London, said:

“The longer a woman remains pregnant, generally the better the outcome is for the baby but in pre-eclampsia, the placental problems that are underlying the process are getting worse.

“We started developing a model that would objectively measure the risks of pre-eclampsia in 2001. We have now taken the data we obtained from the previous versions, fullPIERS and miniPIERS, and came up with the machine learning approach that produced the best model.

“One of the innovative things we have done with the modelling is to include the countries’ GDPs and their national maternal mortality ratios. Including these variables means that the model automatically adjusts according to where a woman is living and makes it a globally relevant model.

“This is a very important research paper and is probably the most generalisable model there is for pre-eclampsia. It’s fantastic to see how well it works.”

Read more: The app for more ‘dementia friendly' communities; ‘Bold action' needed for children's health; Funding boost to support new parents' mental health; Medics warn pollution is risking children's health

Sign up to our bulletin for key health & social care updates straight to your inbox and you can follow healthandcare.scot on Google News.