DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals

2026-06-09

AI Summary

This work addresses limitations in current cuffless blood pressure estimation methods based on photoplethysmography (PPG), which often rely on amplitude shortcuts and suboptimal integration of demographic information, thereby hindering the learning of individualized vascular characteristics. The authors propose a novel Transformer-based architecture that leverages self-attention to model long-range dependencies across multiple cardiac cycles. Demographic data are incorporated via FiLM (Feature-wise Linear Modulation) conditional modulation embedded within each Transformer sublayer, enabling personalized adaptation. Additionally, a morphological auxiliary task is introduced to guide the model toward PPG waveform features associated with arterial stiffness and wave reflection. Evaluated on the PulseDB dataset, the proposed method achieves mean absolute errors of 4.56 mmHg for systolic and 2.62 mmHg for diastolic blood pressure—representing reductions of 47% and 50%, respectively, over existing baselines.

Abstract

Blood pressure (BP) is a key marker for cardiovascular risk assessment and therapeutic decision-making, and Photoplethysmography (PPG) enables low-cost, wearable-friendly cuffless BP estimation. However, even with recent progress, many PPG-based models are trained with BP regression alone and may rely on amplitude-dominated shortcuts. In addition, demographic covariates that systematically modulate vascular compliance are often incorporated only via late fusion, limiting subject-specific representation learning. We propose a Transformer-based network for cuffless BP estimation from PPG signal, leveraging self-attention to capture long-range dependencies across multiple cardiac cycles. To account for subject-specific vascular differences, the model is conditioned on demographics via FiLM-style feature modulation applied through the attention and feed-forward sublayers of Transformer blocks. In addition, we add an auxiliary morphology head to guide the model to attend to BP-relevant waveform morphology associated with arterial stiffness and wave reflection. Under calibration-based evaluation protocols on the large-scale PulseDB dataset, the proposed method achieves MAE of 4.56 mmHg for systolic BP and 2.62 mmHg for diastolic BP, reducing errors by 47% and 50% compared with prior demographic-enhanced PPG baselines. The resulting lightweight, single-sensor model supports scalable and clinically grounded cuffless BP estimation in calibration-enabled deployment settings.

Problem

• cuffless blood pressure estimation
• PPG signals
• demographic conditioning
• vascular compliance
• subject-specific representation

Innovation

• Demographic Conditioning
• Morphology-Enhanced Transformer
• Cuffless Blood Pressure Estimation
• PPG Signal
• FiLM-style Modulation