Welcome Your IET account
premature baby

AI tool assesses premature birth risk from vapours

University of Warwick researchers have developed a tool, using machine learning, which can accurately predict premature births in almost three-quarters of women with an asymptomatic high risk.

Premature birth is the leading cause of infant death in the UK, but there are few accurate tools available to predict a pre-term birth.

“There are a number of different factors that could cause a woman to go into pre-term labour. Because of that, prediction is quite difficult,” said Dr Lauren Lacey, an obstetrics and gynaecology registrar at University Hospitals Coventry and Warwickshire NHS Trust.

“There are lots of things we can look at: the patient’s history, the examination, ultrasound scan, various other biomarkers that are used in clinical practice. No single test fits all.”

Lacey led the development of this new technology, which focuses on the analysis of volatile organic compounds (VOCs) present in the vagina as a result of bacterial vaginosis. This condition is associated with increased risk of premature birth.

The team of researchers trained a model to identify patterns of VOCs which could indicate bacterial vaginosis.

They analysed vaginal swabs from 216 asymptomatic women attending a clinic who had either a history of pre-term birth or a medical condition increasing the risk of pre-term birth. Analysis of swabs from the second trimester – compared with the eventual outcome of the birth – showed the technology was accurate in 66 per cent of cases. However, this rose to 73 per cent for swabs taken in the third trimester.

Seven in 10 women with a positive result delivered pre-term, while nine in 10 women with a negative result delivered at full term. The researchers hope that the tool could form an element of a care pathway to determine who may deliver pre-term; even the less accurate test taken earlier in pregnancy could allow interventions to be put in place to reduce risk.

“VOC technology is really interesting because it reflects both the microbiome and the host response, whereas other technologies look for a specific biomarker,” Lacey said. “It’s the beginning of looking at the association of VOCs with pre-term delivery.”

The next stage of research could see a small VOC analysis device stored at a hospital to analyse samples on site. Eventually, the technology could lead to a cost-effective, non-invasive, point-of-care maternity ward test for women at risk of premature delivery, improving outcomes for both mother and infant.

Professor James Covington, who is based at Warwick’s School of Engineering, said that such technology could become commonplace in the identification of disease in the near future: “There is a strong interest around the world in the use of vapours emanating from biological waste for the diagnosis and monitoring of disease. These approaches can non-invasively measure the health of a person, detect an infection, or warn of an impending medical need.”

Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.

Recent articles

Info Message

We use cookies to give you the best online experience. Please let us know if you agree to all of these cookies.


Learn more about IET cookies and how to control them