Energy-efficient Blood Pressure Monitoring based on Single-site Photoplethysmogram on Wearable Devices

TL;DR

This paper presents an energy-efficient, cuffless blood pressure monitoring method using a single-site PPG sensor and AI on wearable devices, achieving accurate results with minimal energy consumption.

Contribution

It introduces the first edge AI-based blood pressure monitoring solution using a single-site PPG sensor on wearable devices, emphasizing energy efficiency and accuracy.

Findings

Achieved MAE of 3.42 mmHg for SBP and 1.92 mmHg for DBP.

The system consumes 2.1 mJ per reading, suitable for wearable devices.

Processing time is 42.2 ms with 18.2 KB RAM usage.

Abstract

The paper proposes accurate Blood Pressure Monitoring (BPM) based on a single-site Photoplethysmographic (PPG) sensor and provides an energy-efficient solution on edge cuffless wearable devices. Continuous PPG signal preprocessed and used as input of the Artificial Neural Network (ANN), and outputs systolic BP (SBP), diastolic BP (DBP), and mean arterial BP (MAP) values for each heartbeat. The improvement of the BPM accuracy is obtained by removing outliers in the preprocessing step and the whole-based inputs compared to parameter-based inputs extracted from the PPG signal. Performance obtained is $3.42 \pm 5.42$ mmHg (MAE $\pm$ RMSD) for SBP, $1.92 \pm 3.29$ mmHg for DBP, and $2.21 \pm 3.50$ mmHg for MAP which is competitive compared to other studies. This is the first BPM solution with edge computing artificial intelligence as we have learned so far. Evaluation experiments on real hardware show that the solution takes 42.2 ms, 18.2 KB RAM, and 2.1 mJ average energy per reading.