Machine-learning prediction of hypertensive disorders of pregnancy based on home blood pressure monitoring
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Hypertensive disorders of pregnancy (HDP) cause adverse maternal and fetal outcomes, and establishing an early prediction method for HDP is needed. Existing methods based on serum markers require blood sampling. Therefore, we aimed to develop and validate a noninvasive machine-learning prediction method for HDP based on home blood pressure monitoring (HBPM).
Methods
In a development cohort, HBPM data from 443 pregnant women including 65 HDPs were divided into training data (n=365) and test data (n=78) to develop a logistic regression-based prediction model. Normal blood pressure variations depending on season and gestational age were subtracted. At each time point, four features were calculated for the last four weeks of data: average systolic blood pressure (SBP), average diastolic blood pressure (DBP), correlation coefficient between SBP and DBP, and upward trend of SBP against day. In a validation cohort, HBPM data from 264 pregnant women including 33 HDPs were collected prospectively and used to validate the model.
Results
The area under the receiver operating characteristic curve was 0.949, 0.884, and 0.845 for the training, test, and validation data, respectively. Sensitivity, specificity, positive predictive value, and negative predictive value were 0.769, 0.889, 0.543, and 0.957 for the development cohort, and 0.758, 0.766, 0.316, and 0.957 for the validation cohort.
Conclusions
Our machine-learning prediction method for HDP based on HBPM showed high negative predictive values and may contribute to reducing medical consultations.
