SIFPBPNet is a dual‑path neural network designed for cuffless blood‑pressure estimation from photoplethysmography (PPG) signals. It separates steady‑state and instantaneous features through a Steady‑state Feature Path (SFP) that uses a Graph Attention Network to learn individual‑specific long‑term patterns, and an Instantaneous Feature Path (IFP) that captures short‑term dynamics and fuses them with the steady‑state prior via cross‑attention. On a large wearable dataset, the model achieves mean absolute errors of 8.57 mmHg for systolic and 5.97 mmHg for diastolic BP, outperforming existing methods and showing that the SFP module can be added to other backbones for 2.8–13.1 % MAE reduction.
arXiv:2606. 11125v1 Announce Type: cross 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.
arXiv:2607. 27076v1 Announce Type: new Abstract: Continuous cuffless blood pressure (BP) monitoring remains challenging due to motion artifacts, physiological variability, and the limited robustness of conventional pulse transit time (PTT) models under dynamic conditions.
arXiv:2607. 23406v1 Announce Type: cross Abstract: Continuous cuffless blood pressure (BP) monitoring is essential for connected health systems and wearable devices, enabling early detection, longitudinal tracking, and personalized management of cardiovascular disease.
arXiv:2609.13190v1 Announce Type: new Abstract: Continuous cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) offers a promising solution for personalized healthcare. However, e...
arXiv:2605.10871v3 Announce Type: replace-cross Abstract: We present Attractor-Vascular Coupling Theory (AVCT), a theory-guided framework for deriving interpretable blood pressure (BP) predictors fro...
The paper presents a hybrid Transformer framework that estimates non‑invasive continuous blood pressure from ECG/PPG‑derived feature sequences. It models 10‑step sequences of six physiological descriptors and two demographic covariates, combining Transformer, Kolmogorov‑Arnold Network, and XGBoost modules, and uses a dynamic fusion decoder to predict diastolic and systolic BP. On a large MIMIC‑III dataset, the model achieved mean errors of 0.41 mmHg (diastolic) and –1.60 mmHg (systolic) with high accuracy within 10 mmHg for most predictions.
PPG-Bench is an open‑source benchmark that evaluates five publicly available photoplethysmography (PPG) foundation models across nine datasets and 26 tasks, covering cardiovascular state estimation, activity, sleep, screening, and identification. The benchmark tests models under four downstream regimes—linear probing, random forests, frozen MLP probes, and end‑to‑end finetuning—while also comparing them to three controls: a random/constant baseline, a deterministic pulse‑rate‑variability feature set, and a generic time‑series foundation model (MOMENT). Results show that over a third of task‑regime combinations yield no advantage for any PPG foundation model over the baseline, and in most cases no PPG‑specific model outperforms the simple controls, indicating that current PPG foundation models lack generalised, transferable representations.
The Cross-View Attention Fusion Network (CVAF‑Net) is a dual‑view deep learning model that estimates cardiac output from short photoplethysmography (PPG) segments by combining raw PPG signals with a structured prior‑guided feature sequence map through cross‑view attention. Evaluated on simulated, vasoconstriction, and real‑world activity datasets, CVAF‑Net achieved a mean absolute error of 0.19 L/min on simulated data and as low as 1.20 L/min in real settings, outperforming most benchmarks while reducing computational cost by twelvefold compared to a leading Transformer model. Plausibility checks confirmed physiologically consistent correlations with age, heart rate, and systemic vascular resistance.
The paper introduces a fluctuation‑aware evaluation framework for photoplethysmography (PPG)‑based blood pressure (BP) estimation that uses time‑series change‑point detection to identify abrupt BP shifts, rather than relying on arbitrary BP thresholds. It demonstrates that state‑of‑the‑art models suffer significant performance drops around these change points and that periodic test‑time calibration is inadequate. To mitigate this, the authors propose a targeted re‑calibration strategy triggered by detected change points, improving robustness without altering model architectures.
The paper introduces a fluctuation‑aware evaluation framework for photoplethysmography (PPG)‑based blood pressure (BP) estimation that uses time‑series change‑point detection to identify abrupt BP shifts, rather than relying on simple BP thresholds. It demonstrates that many state‑of‑the‑art models degrade significantly around these change points and that periodic test‑time calibration is inadequate. To mitigate this, the authors propose a targeted re‑calibration strategy triggered by detected change points, improving robustness without altering model architectures.
The study evaluates how acquisition context and photoplethysmography (PPG) signals contribute to session‑calibrated blood pressure tracking using a wearable‑state model on 653 AuroraBP participants. Adding contextual information reduced mean absolute errors (MAEs) for systolic and diastolic BP by 0.436 mmHg and 0.126 mmHg, respectively, while PPG alone provided modest improvements. Exploratory follow‑ups with sensor‑history ensembles and pulse‑rate fusion yielded only slight gains, and a separate intraoperative model (VitalDB) showed limited PPG benefit.
The paper introduces Phy‑BP, a physics‑constrained deep learning framework for contactless blood pressure monitoring using triaxial bodyseismography (BSG). It employs an adaptive quality‑control algorithm to select cardiogenic‑rich BSG segments and embeds a 3‑D wave‑propagation physical model into the neural network to align multi‑axis features, enhancing robustness to real‑world distortions. Experiments on a 162‑hour hospital dataset from 21 subjects demonstrate that Phy‑BP can filter low‑quality measurements and maintain accurate BP estimation even with limited training data.