POS-2026-3009: OpenPREGnosis-Longitudinal: Expanding and Validating Pregnancy Identification Algorithms

Pregnancy outcomes in England show that women from ethnic minority backgrounds face higher risks of complications, including high blood pressure, preterm birth, stillbirth, and maternal death. For example, black women are three times more likely to die during or after pregnancy than women of other ethnicities. These risks get worse with increased age and socioeconomic deprivation of the mother, and for mothers with pre-existing health conditions.

This study will build on our existing work that aimed to create a computer tool to identify pregnancies in patient’s health records and look at how changes in healthcare in the COIVD-19 pandemic impacted outcomes for the mother and child. Here, we aim to extend this algorithm to include a longer period of data to check its ability to identify pregnancies across different time periods, including before and after the pandemic.

This extension will also allow us to capture information on longer-term patterns in pre-conception care and identify rarer outcomes. Additionally, we will be able to answer a set of high priority research questions (identified through patient and public involvement and engagement) set across the pregnancy journey through to longer-term outcomes for the mother after birth, such as high-blood pressure, type-2 diabetes, or heart disease.

The findings will create a reliable tool that is available for all researchers to use. The research we do will also provide important evidence to reduce differences between different groups and improve outcomes for all women and babies, including helping to identify who is most at risk and when, and supporting earlier detection and targeted support.