Detecting Rises in SBP from PPG for Identifying Autonomic Dysreflexia

Autonomic dysreflexia (AD) is a life-threatening and prevalent post-secondary health condition affecting individuals with spinal cord injury (SCI). Reliable and timely identification of AD requires continuous monitoring of changes in the blood pressure (BP), and alarming the patient of rapid BP elevations. However, conventional methods for identifying AD, including clinical observation and patient’s self-report, lack timeliness in addressing the immediate threat of acute hypertension, leading to cardiovascular damages in SCI patients. To address this issue, we target the problem of detecting onsets of rapid systolic BP (SBP) elevations from photoplethysmogram (PPG) signals, and present a batched Residual Network-Long Short Term Memory (ResNet-LSTM) deep learning model as a solution. Results indicate that the model achieves an accuracy of 74.38% and F-1 score of 72.99% on 356 leave-out testing subjects. With only one sensor required for providing input signals, the proposed method holds promise for implementing low-cost continuous monitoring systems, for the timely detection of onsets of AD in SCI patients.