Machine Learning Model Accurately Predicts Pregnant Women at Risk for Preeclampsia

THURSDAY, March 12, 2026 (HealthDay News) -- A machine learning model based on electronic health record data can provide updated predictions of preeclampsia risk, according to a study published online March 6 in JAMA Network Open.Haoyang Li, Ph.D., from Weill Cornell Medicine in New York City, and colleagues used longitudinal electronic health record data (58,839 pregnancies) to develop and validate a machine learning model for dynamic, short-term prediction of preeclampsia onset.The researchers found that individuals who developed preeclampsia were older (median age, 33.0 to 35.0 versus 31.0 to 34.0 years across cohorts) and more frequently Black (range, 14.8 to 41.8 percent versus 6.5 to 21.8 percent). Predictive performance increased with gestational age (from 28 to 34 weeks of gestation), with a peak at 34 weeks of gestation (areas under the receiver operating characteristic curves, 0.863 at training and 0.808 to 0.834 at validation). Positive predictive values also increased from 28 weeks (0.001 to 0.002) and peaked at 36 weeks (0.046 to 0.057). Negative predictive values were >0.993. The most informative predictor was blood pressure, while laboratory measures (albumin, alkaline phosphatase, and hematologic indexes) contributed to earlier gestation, and demographic and obstetric factors showed more importance later."Dynamic short-term prediction of preeclampsia was feasible using routinely available clinical and laboratory data," the authors write. "These results suggest that this approach provided opportunities for earlier intervention and would be adaptable across diverse health care settings."Several authors disclosed ties to the biopharmaceutical industry.Abstract/Full Text (subscription or payment may be required).Sign up for our weekly HealthDay newsletter

Machine Learning Model Accurately Predicts Pregnant Women at Risk for Preeclampsia

Related Stories