Accurate cuffless blood pressure measurement from single ppg waveform
ExpertoRhythm: Morphology-Aware Learning for Waveform Reconstruction and Cuffless Blood Pressure Estimation from Single-Channel PPG
Machine Learning
Summary
Measuring blood pressure without a cuff could be easier with wearable devices, but it’s hard to get accurate readings from the light-based signals these devices use. The authors created ExpertoRhythm, a smart computer program that looks closely at the shape of these signals to reconstruct the blood pressure waveform. This approach helps estimate systolic and diastolic blood pressure more accurately across different pressure levels. Their method performed well on a large dataset, meeting clinical standards for accuracy and consistency.
What this means in practice
- •For wearable device developers: Use single-channel PPG signals and this waveform reconstruction method to provide continuous cuffless blood pressure monitoring in health wearables.$Commercial implications: It enables accurate, real-time cuffless blood pressure measurement for consumer wearable health devices.
- •For telehealth service providers: Incorporate this method to remotely monitor patients' blood pressure continuously without needing specialized cuffs or devices.
Authors
Amir Arjomand, Kenneth B. Kent, Georgiy Krylov
Abstract
Continuous cuffless blood pressure (BP) monitoring from photoplethysmography (PPG) has strong potential for wearable health and telemonitoring, but accurate estimation remains difficult because PPG-to-BP mapping must preserve subtle waveform morphology and pressure-range-dependent dynamics. We introduce ExpertoRhythm, an attention-enhanced 1D U-Net that reconstructs the arterial blood pressure (ABP) waveform from a single-channel PPG signal and derives systolic and diastolic BP directly from the reconstructed waveform. The central contribution is a composite morphology-aware learning objective that integrates range-weighted SmoothL1 reconstruction with a window-range regularizer to emphasize high-dynamic BP segments and reduce amplitude under/over-shoot. On the UCI cuff-less BP dataset with 942 subjects, ExpertoRhythm achieves 2.46/1.46 mmHg MAE for systolic/diastolic BP (SBP/DBP), while obtaining a 30.4% average relative error reduction over pure MSE across waveform reconstruction and BP estimation metrics. Clinical-style evaluation further demonstrates low bias and strong agreement across the BP range, including high-pressure windows up to 200 mmHg, satisfying AAMI criteria and achieving BHS Grade A. These results suggest that morphology-aware waveform reconstruction from a single PPG channel can provide an accurate and practical pathway toward continuous cuffless BP monitoring in wearable and remote-care settings.