TransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation via Solo PPG Signal Capturing

2024-04-15

arXiv.org

AI Summary

To address the reliance on multi-sensor setups and susceptibility to motion artifacts in cuffless continuous blood pressure (BP) monitoring, this paper proposes a high-accuracy, single-channel photoplethysmography (PPG)-only method for systolic (SBP) and diastolic blood pressure (DBP) estimation. We introduce the MIMIC-IV clinical physiological database—the first application of this large-scale ICU dataset to cuffless BP estimation—and design a PPG-optimized Transformer architecture. The model incorporates multi-head self-attention to capture long-range pulse wave rhythm dependencies, coupled with robust signal preprocessing and noise-aware feature learning. Evaluated on MIMIC-IV, our method achieves root-mean-square errors (RMSE) of 2.21 mmHg for SBP and 1.84 mmHg for DBP, with mean absolute errors (MAE) of 1.37 mmHg and 1.06 mmHg, respectively—meeting clinical acceptability criteria (AAMI/ISO standards). This work eliminates the need for auxiliary sensors such as ECG, thereby overcoming a critical dependency bottleneck in practical cuffless BP monitoring.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Hardware-aware ML
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Recent statistics indicate that approximately 1.3 billion individuals worldwide suffer from hypertension, a leading cause of premature death globally. Blood Pressure (BP) serves as a critical health indicator for accurate and timely diagnosis and/or treatment of hypertension. Traditional BP measurement methods rely on cuff-based approaches, which lack real-time, continuous, and reliable BP estimates, crucial for the timely diagnosis/treatment of hypertension. Driven by recent advancements in Artificial Intelligence (AI) and Deep Neural Networks (DNNs), there has been a surge of interest in developing data-driven and cuff-less BP estimation solutions. In this context, current literature predominantly focuses on coupling Electrocardiography (ECG) and Photoplethysmography (PPG) sensors, though this approach is constrained by reliance on multiple sensor types. An alternative, utilizing standalone PPG signals, presents challenges due to the absence of auxiliary sensors (ECG), requiring the use of morphological features while addressing motion artifacts and high-frequency noise. To address these issues, the paper introduces the TransfoRhythm framework, a Transformer-based DNN architecture built upon the recently released physiological database, MIMIC-IV. Leveraging the Multi-Head Attention (MHA) mechanism, TransfoRhythm identifies dependencies and similarities across data segments, forming a robust framework for cuff-less BP estimation solely using PPG signals. To our knowledge, this paper represents the first study to apply the MIMIC IV dataset for cuff-less BP estimation. TransfoRhythm achieves highly accurate results with a Root Mean Square Error (RMSE) of [2.21, 1.84] and a Mean Absolute Error (MAE) of [1.37, 1.06] for systolic and diastolic blood pressures, respectively.

Problem

• Cuff-less blood pressure estimation
• Solo PPG signal usage
• Transformer-based DNN architecture

Innovation

• Transformer-based DNN architecture
• Solo PPG signal utilization
• Multi-Head Attention mechanism