Automated Image Transcription for Perinatal Blood Pressure Monitoring Using Mobile Health Technology

This paper introduces a novel approach to address the challenges associated with transferring blood pressure (BP) data from oscillometric devices used in self-measured BP monitoring systems. The primary objective of this study is to improve the accessibility and usability of BP data for monitoring and managing BP during pregnancy and postpartum, particularly in low-resource settings. To this end, we developed an automated image transcription technique to effectively transcribe readings from BP devices. The photos of the BP devices were captured as part of perinatal mobile health (mHealth) monitoring systems, conducted in four studies across two countries. The Guatemala Set 1 and Guatemala Set 2 datasets include the data captured by a cohort of 49 lay midwives from 1697 and 584 pregnant women carrying singletons in the second and third trimesters in rural Guatemala during routine screening. Additionally, we designed an mHealth system in Georgia for postpartum women to monitor and report their BP at home with 23 and 49 African American participants contributing to the Georgia I3 and Georgia IMPROVE projects, respectively. We developed a deep learning-based model which operates in two steps: LCD localization using the You Only Look Once (YOLO) object detection model and digit recognition using a convolutional neural network-based model capable of recognizing multiple digits. We applied color correction and thresholding techniques to minimize the impact of reflection and artifacts. Three experiments were conducted based on the devices used for training the digit recognition model. Overall, our results demonstrate that the device-specific model with transfer learning and the device independent model outperformed the device-specific model without transfer learning. The mean absolute error (MAE) of image transcription on held-out test datasets using the device-independent digit recognition were 1.1 and 1.1 mmHg for systolic and diastolic BP in the Georgia IMPROVE and 1 and 0.6 mmHg in Guatemala Set 2 datasets. The MAE, far below the FDA requirement of 5 mmHg, makes the proposed model suitable for general use when used with appropriate error devices.