University researchers to develop AI-based learning system to identify factors behind pregnancy complications in black women
RESEARCHERS from Loughborough University are to develop a machine learning system capable of identifying factors that contribute to harm during pregnancy and birth for mothers from black ethnic groups.
Mothers from a black ethnic group are five times more likely to die in the UK as a result of pregnancy complications than white women and are around 83% more likely to suffer a ‘near miss’ in childbirth. Research also shows some ethnic groups have a 121% increased risk of stillbirth and a 50% increased risk of neonatal death*.
At present there is no accurate picture of the causes contributing to these statistics. Research points to biological factors, such as obesity or the birth history of mothers, as one cause of poor outcomes in maternity.
Similarly, social and economic factors such as language barriers and unemployment, are thought to play a role. Finally, the quality of care given to mothers and families – including poor communication with the mother on health issues – is likely to contribute.
Now a team of researchers, led by Dr Patrick Waterson from the University’s Human Factors and Complex Systems Group in the School of Design and Creative Arts and Dr Georgina Cosma, an expert in Artificial Intelligence and Data Science from the Department of Computer Science, will collaborate with the Healthcare Safety Investigation Branch (HSIB) to identify patterns and trends in their maternity investigation reports.
The HSIB has carried out more than 2,000 investigations over the last few years into things that go wrong during pregnancy and birth.
Speaking about the project, Dr Cosma said: “We will develop an AI-based system for analysing maternity investigation reports and extracting data, based on a set of codes, that is able to identify factors which contribute to harm during pregnancy and birth.”
Dr Waterson added: “The system will use ‘machine learning’ to probe deeper into how different factors – regional, biological, clinical, care quality – interact, influence one another and lead to harm.
Ultimately, the AI-based computer program will help us design specific ways in which maternal care for these at risk groups be improved.”
The involvement of black ethnic mothers and families will also be an essential part of the project.
Two groups will be established to maximise the involvement of patients and the general public.
One will be HSIB’s Citizens’ Partnership group, the other will be made up of mothers from different ethnic groups from across the UK.
“Ultimately, we believe the outcomes from our research have the potential to transform the NHS’s ability to reduce maternal harm amongst mothers from black ethnic groups,” Dr Waterson added. “And in the longer term, our research could improve patient safety for all mothers, regardless of ethnicity.”
The team will ensure that the AI tools are implemented in an ethical manner, with embedded bias management and mitigation strategies.
Kevin Stewart, HSIB’s Medical Director said: We are delighted to be working with Loughborough University to better understand the factors that lead to poor outcomes and experiences for some women from black ethnic groups.
“We believe our data, gathered from so many of our maternity investigations, will help develop the learning required to automate analysis and identification of themes.”
The project, ‘I-SIRch - Using Artificial Intelligence to Improve the Investigation of Factors Contributing to Adverse Maternity Incidents involving Black Mothers and Families’, will begin in January and run for two years.
It is being funded by NHSX and the Health Foundation, as part of a research competition – supported by National Institute for Health Research (NIHR) – to understand and enable opportunities to use AI to address inequalities and to optimise datasets, and improve AI development, testing and deployment.