Machine Learning for Dynamic and Short-Term Prediction of Preeclampsia Using Routine Clinical Data - PubMed
5 days ago
- #preeclampsia
- #healthcare
- #machine learning
- Machine learning models were developed for dynamic, short-term prediction of preeclampsia using routine EHR data.
- The study included pregnancies from three hospitals, focusing on predicting preeclampsia onset within 1, 2, and 4 weeks.
- Key predictors included blood pressure, maternal characteristics, and routine laboratory test results.
- Model performance peaked at 34 weeks' gestation with high predictive accuracy.
- Blood pressure was the most informative predictor, while lab measures contributed more in earlier gestation.
- The approach showed potential for earlier intervention and adaptability across diverse healthcare settings.