Deep Sequence Learning for Assessing Hypertension in Pregnancy from Doppler Signals

Measuring blood pressure during pregnancy is an essential component of antenatal care, and is critical for detecting adverse conditions such as pre-eclampsia. The standard approach for measuring blood pressure is via manual auscultation by a trained expert or via an oscillometric self-inflating cuff. While both methods can provide reasonably accurate blood pressure measurements when used correctly, non-expert use can lead to significant error. Moreover, such techniques are uncomfortable and can cause bruising, pain and consequential resistance to use / low compliance. In this work, we propose a low-cost onedimensional Doppler-based method for the detection of hypertension in pregnancy. Using a sample of 653 pregnant women of Mayan descent in highland Guatemala, we recorded up to 10 minutes of 1D Doppler data of the fetus, and blood pressure from both arms using an Omron M7 oscillometric cuff. A hierarchical LSTM network with attention mechanism was trained to classify hypertension in pregnancy, producing an area under the receiveroperator curve of 0.94. A projection of the data into lower dimensions indicates hypertensive cases are located at the periphery of the distribution of the output of the distribution. This work presents the first demonstration that blood pressure can be measured using Doppler (without occlusion) and may lead to a novel class of blood pressure monitors which allow rapid blood pressure estimation from multiple body locations. Moreover, the association of the predictor with the fetal blood flow indicates that hypertension in the mother has a significant effect on the fetal blood flow.