Mobile app could reliably determine risk of spontaneous preterm birth

Researchers have detailed improvements to a mobile app for rapidly determining individual women’s risks of spontaneous preterm birth. The app could allow for both earlier determination of preterm birth risk and provision of special treatments.

Like 0 Comment

Researchers from King’s College London (UK) have created a newly improved, user-friendly, mobile app for rapidly determining individual women’s risks of experiencing spontaneous preterm birth. The app could allow for both earlier determination of preterm birth risk and provision of special treatments to reduce emotional and financial burdens on families and the NHS.

Preterm birth – when a baby is born before 37 full weeks of pregnancy – can be associated with greater infant mortality and developmental problems, which result in significant emotional and financial burdens on families and healthcare providers.

Women who present with symptoms of threatened preterm labor often receive interventions – including repeated steroid administration to aid fetal lung development – to reduce the risk of preterm birth. Symptoms of threatened preterm labor are not indicative of definite preterm birth, however the severe risks associated with preterm birth can mean that many women are treated with unnecessary interventions for fear of not treating an individual who will experience preterm birth.

In response to the need for a clinical decision support tool for identifying women at increased risk of spontaneous preterm birth, researchers have developed QUiPP v2 – a mobile app capable of predicting women’s risk of preterm birth by integrating results from clinical tests, namely fetal fibronectin and cervical length tests, with factors such as previous experience of preterm birth or miscarriage. The app then generates a simple % risk score for an individual based on these data.

In the first of two studies recently published in Ultrasound in Obstetrics and Gynecology, researchers detail updates to their QUiPP v2 algorithm based on predictive models generated from data concerning 1032 women who had presented with symptoms of threatened preterm labor and were recruited to participate in one of four prospective studies between 2010 and 2017; the outcomes of these women were known as of May 2017. Data on a second cohort of 506 women, whose outcomes were known as of March 2018, were used to validate the predictive models and algorithm.

Three predictive models for preterm birth risk were generated based on availability of data: the first model generated risk scores based on risk factors and fetal fibronectin test results alone, the second utilized risk factors and cervical length measurements alone, and the third model employed all three parameters – risk factors, fetal fibronectin scores and cervical length measurements.

All three models were determined accurate at predicting women’s preterm birth risk. In the study, the authors concluded: “Validation of the new prediction models suggests that the QUiPP App v.2 app can reliably calculate risk of [spontaneous preterm birth] in women with [threatened preterm labor]. Use of the QUiPP App in practice could lead to better targeting of intervention, while providing reassurance and avoiding unnecessary intervention in women at low risk.”

In the second published study, researchers conducted a similar investigation to the first, but employed data pertaining to asymptomatic women who were at high-risk of experiencing preterm birth. Again, the predictive models were observed to be accurate at predicting preterm birth risk.

In the second study, the authors concluded: “Whilst further work is required to determine its role in identifying women requiring prophylactic interventions, it is a reliable and convenient screening tool for planning follow‐up or hospitalization for high‐risk women.”

Lead study author Jenny Carter (King’s College London) stated: “We are delighted to be able to share the findings of our work which shows that the QUiPP app is very reliable in predicting preterm birth in women at risk. This should mean that women who need treatments are offered them appropriately, and also that doctors and women can be reassured when these treatments are not needed, which reduces the possibility of negative effects and unnecessary costs for the NHS.”

The study authors have recently completed the Evaluation of the QUiPP app for Triage and Transfer (EQUIPTT) trial, carried out at Guys and St Thomas’ Hospital (London, UK), evaluating if and how use of the app by clinicians improves appropriate targeting of care for women who are concerned about preterm labor. Results of this trial are expected to be published later in 2020.

Researchers plan to continue to collect and integrate data from the Threatened Preterm Labour – Risk and Care Management (PETRA) study and the global Preterm Clinical Network Database, to further develop and improve their algorithm.


Sources:

Carter J, Seed PT, Watson HA et al. Development and validation of predictive models for QUiPP App v.2: tool for predicting preterm birth in women with symptoms of threatened preterm labor. Ultrasound Obstet Gynecol. 55(3), 357–367 (2020); Watson HA, Seed PT, Carter J et al. Development and validation of predictive models for QUiPP App v.2: tool for predicting preterm birth in asymptomatic high‐risk women. Ultrasound Obstet Gynecol. 55(3), 348–356 (2020); www.kcl.ac.uk/news/researchers-develop-app-determine-risk-preterm-birth

Go to the profile of Ilana Landau

Ilana Landau

Assistant Editor, Future Science Group

184 Contributions
2 Followers
0 Following

No comments yet.