Risk-based computer models can predict spontaneous preterm deliveries

A newly developed predictive model could help predict the risk of impending preterm delivery, avoiding the harmful and costly effects of overtreatment or misdiagnosis.

Premature. Image Credit: M.Moira / Shutterstock.com

Improve the prediction of impending preterm birth

Premature labor is a difficult incident to diagnose due to the nonspecific nature of the symptoms. Current diagnostic methods are inadequate because overtreatment of symptoms is common and costly for patients. However, the health impacts incurred if preterm labor is not treated effectively also pose a problem for the successful delivery as well as long term effects for the mother.

A new study published by Sarah Stock at the University of Edinburgh, UK, and her colleagues at the journal PLOS Medicine, offers a new way to meet the challenge of diagnosing symptoms of preterm labor. This was accomplished by developing a computer risk prediction model that improves the prediction of impending preterm births.

First, the researchers identified clinical risk factors for preterm labor by analyzing individual data from participants in five prospective European cohort studies, including 1783 pregnant European women, and used them to develop a model to predict the risk of preterm labor. spontaneous premature birth.

Next, the model was validated in a prospective cohort study of 2,924 women with signs and symptoms of preterm labor in 26 obstetric units run by consultants in the UK. This allowed researchers to validate the accuracy of the model by comparing predicted and observed outcomes between data sets.

The results showed that the best predictive model included combinations of key symptoms. Superficially, analysis of the concentration of fetal fibronectin in vaginal fluid alongside clinical risk factors surpassed predictions of impending spontaneous preterm delivery and was more cost-effective than fetal fibronectin alone.

The risk prediction model has shown promising performance in predicting spontaneous preterm delivery within seven days of testing and can be used as part of a decision support tool to help guide decisions management for women at risk of preterm labor. It is easily achievable, with the potential for immediate benefit to women, babies and health services, avoiding unnecessary admissions and treatment. “

Predict the unpredictable – model shows potential to limit adverse health effects during spontaneous preterm birth

The implementation of such predictive models could help identify the most important factors leading to the clinical diagnosis of adverse events, such as spontaneous preterm delivery.

Nonetheless, the study noted limitations in data collection and subsequent analysis that may limit the representative implications of this study.

The data collected was primarily focused on Caucasian and British European patients, with a few non-white participants offering limited insight into ethnic or regional differences. The inclusion of other populations can therefore help improve the accuracy of the model. In addition, the missing data in the risk predictor development cohort also requires further study, as the risk prediction model improves clinical outcomes in practice.

The development of more precise and applicable predictive models could provide key guidelines for successful clinical treatments, avoiding potential misdiagnosis or overtreatment, which could have adverse health consequences.

The vast majority of women with signs and symptoms of preterm labor do not deliver early, but many are hospitalized unnecessarily for preterm labor. The risk predictor developed by our research team will help women understand their chances of giving birth early, so that they can decide whether or not they should be admitted and treated.

We are now working to link the predictor to maternity records, so that it can easily be used in the care of women and be continuously improved as more and more women use it. “

Dr Stock

The extension of predictive models and the use of computer-based risk predictions beyond preterm delivery may also provide support for other clinical treatments. This can include the diagnosis of neurodegenerative and cardiovascular diseases, which can present a range of symptoms and often require specific treatments to be treated successfully.