跳到正文
原文
Medical Xpress·· 13 天前AI 评分45

研究人员开发更精确的电子健康记录识别先兆子痫方法

Researchers develop more precise way to identify preeclampsia from electronic health records

AI 导读

研究人员利用电子健康记录(EHRs)开发了一种更有效的先兆子痫识别方法,该方法能更准确地捕捉现有方法可能遗漏的病例及其不良后果。通过分析超过21,000次妊娠的数据,新方法在识别严重高血压等不良结果方面比传统方法更有效,识别率提高了近一倍。这有助于提高先兆子痫研究的准确性和可靠性。

正文
preeclampsia
Credit: Unsplash/CC0 Public Domain

Researchers at King's College London have found a more effective method for identifying preeclampsia from electronic health records (EHRs), allowing them to capture cases and associated adverse outcomes that existing methods may miss.

The study suggests that use of data in EHRs could be optimized to improve the accuracy of maternity care research.

Preeclampsia is a pregnancy condition that causes high blood pressure. It typically develops after 20 weeks of pregnancy and can cause serious complications for both mother and baby. Diagnosing preeclampsia early is important for risk management, and a large part of prenatal care is focused on detection of the condition through routine checks of blood pressure and protein in the urine, known as proteinuria. These measurements are stored in a digital record, known as an EHR, along with the patient's other medical history.

EHRs offer a powerful resource for population research, providing vast amounts of data on millions of people from diverse populations. However, identifying conditions like preeclampsia in EHRs can be challenging because it has complex diagnostic criteria and health records are not always collected in a consistent way. As a result, cases can be missed when researchers use computational tools to mine data that utilize standard diagnostic codes based on outdated definitions, or simplified fields within EHRs.

In the new study, published in The Lancet Digital Health, researchers explored how effectively a diagnosis of preeclampsia, as well as the risks associated with the condition, could be identified retrospectively using the clinical data available in EHRs. They used data from over 21,000 pregnancies collected as part of the eLIXIR Born in South London cohort, which combines information from routine maternity and neonatal health records with mental health and primary care data.

The researchers looked at three ways of identifying preeclampsia in the health records. These included: clinician-recorded diagnoses where clinicians had entered 'preeclampsia' either as free text or using a drop-down menu in medical notes; International Classification of Diseases, 10th Revision (ICD-10) codes, an internationally recognized system used to classify diseases and diagnoses in health records; and an approach that combined the clinician-recorded data with ICD-10 codes.

They also tested the broad definition of preeclampsia using structured components from the available data. This included blood pressure measurements, protein levels in urine, other laboratory results, and maternal signs and symptoms, consistent with how preeclampsia is defined by the International Society for the Study of Hypertension in Pregnancy (ISSHP).

The team found that this "digital" approach was more effective at identifying adverse outcomes than the three other approaches tested. Using the team's definition, 7.7% of pregnancies were identified as having preeclampsia, compared with 4.5% using clinician-recorded data, 3.7% using ICD-10 codes and 5.8% using the combination of both.

There were also differences in the number of adverse outcomes linked to preeclampsia identified between the different approaches. These differences were particularly clear for severe hypertension, for which the researchers' digital approach identified 68% of cases involving severe hypertension, compared with 26% using clinically recorded data, 28% using ICD-10 codes and 33% using both.

The research was carried out by Dr. Milly Wilson as part of her Ph.D. work at King's. Wilson also completed the master's in Women's Health at King's, where she is now working as a postdoctoral researcher.

Wilson, postdoctoral researcher at King's and lead author of the paper, said, "Electronic health records are increasingly used in health research. To ensure research is accurate and reliable, there needs to be a consistent way of identifying, diagnosing and recording cases of preeclampsia."

The findings highlight the importance of making better use of clinical information in EHRs to support research aimed at improving the care of preeclampsia.

"Our work shows that by using a digital approach to identify women satisfying a broad definition of preeclampsia, we can capture more women at high risk of adverse outcomes. We hope our research shows that by looking at all information in the health record, researchers and clinicians can help build a more comprehensive and accurate picture of what happened during pregnancy," said Wilson, postdoctoral researcher at King's and lead author of the paper.

"This is the first step toward real-time evaluation of women with the complex condition of preeclampsia, to facilitate timely intervention and optimize outcomes for mothers and babies," said Dr. Laura Magee, professor of Women's Health at King's and senior author of the paper.

More information

Milly G Wilson et al., Operationalising the broad definition of pre-eclampsia: a retrospective cohort study, The Lancet Digital Health (2026). DOI: 10.1016/j.landig.2026.101047

Who's behind this story?

Gaby Clark

Gaby Clark

MA in English, copy editor since 2021 with experience in higher education and health content. Dedicated to trustworthy science news. Full profile →

Andrew Zinin

Andrew Zinin

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Citation: Researchers develop more precise way to identify preeclampsia from electronic health records (2026, November 6) retrieved 6 November 2026 from https://medicalxpress.com/news/2026-11-precise-preeclampsia-electronic-health.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

来源:Medical Xpress · medicalxpress.com