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

TL;DR

This work addresses the need for continuous cuff-less blood pressure estimation using a single PPG signal. It introduces TransfoRhythm, a regressive time-series transformer that employs Multi-Head Attention, NLP-inspired embedding, and a time-frame compressor to predict SBP and DBP from MIMIC-IV waveform-derived PPG features. The approach achieves superior accuracy, with SBP/DBP MAE around 1.37/1.06 mmHg and RMSE around 2.21/1.84 mmHg, and meets AAMI and BHS standards while exhibiting minimal bias in Bland-Altman analyses. The study demonstrates the feasibility and clinical potential of transformer-based architectures for cuff-less BP estimation from standalone PPG signals, while noting the need for broader validation beyond MIMIC-IV.

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.

Figures (9)

• Figure 1: This block diagram depicts the streamlined process for estimating systolic and diastolic blood pressures. Features are extracted from the dataset (top left), combined with positional encoding, and form an embedded input matrix. This matrix is then inputted into the model block, which integrates a multi-head attention mechanism. The output of the model is further refined in the position-wise block. Finally, the Time compressor and flattening blocks are applied to reduce the time frame and yield the estimated systolic and diastolic blood pressure values.
• Figure 2: Time distribution of records depicted in the graph. The $x-axis$ represents the record's length, ranging from a few minutes to a maximum of 17 hours. The darker shades of blue indicate a higher number of observations. The majority of patients have records with a time duration of less than 1.5 hours.
• Figure 3: Distribution of patient data based on SBP and DBP values. The $x-axis$ represents the blood pressure value, while the $y-axis$ depicts the data frequency for systolic blood pressure (left) and diastolic blood pressure (right). Each bar corresponds to the number of records of corresponding pressure. The density of the bars reveals the concentration of observations, highlighting that most patients fall within the normal range.
• Figure 4: A comparison of the signal before and after preprocessing. The photo demonstrates the exceptional noise filtering achieved, resulting in a clean and smooth signal. Furthermore, the peaks and feet are accurately preserved, showcasing the effectiveness of the preprocessing techniques employed.
• Figure 5: Characterization of features on the signal. In the PPG signal, the peak is defined as the maximum value of a PPG wave, while d.notch is defined as the minimum value between two consecutive peaks. In the SD PPG signal, amp peak refers to the maximum amplitude, while amp foot refers to the minimum amplitude between two consecutive waves.