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.
By Yuexin Ma, Jingqi Hou, Yuxuan Kang, Zhaoying Liu
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...
By Myung-Kyu Yi, Jongshill Lee, Jeyeon Lee, In Young Kim
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.
By Shuailong Tang, Xiaoyu Li, Donglin Xie, Wei Chen, Guangpu Zhu, Yelei Li, Yali Zheng
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.
By Kindeep K. Dhatt, Tengyue Wu, Hanbang Hua, Yayun Du
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.
By Bo Wu, Haoling Wang, Zhuodiao Kuang, Kateryna Shapovalenko
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.
By Yuanyuan Zhang, Yida Zhang, Jiahui Li, Yuyan Wu, Fei Dou, Xiao Yin, Zhenlin An, Hae Young Noh, Wenzhan Song
The study investigates how adding ballistocardiography (BCG) signals to photoplethysmography (PPG) and arterial pressure wave (APW) signals affects the estimation of cardiovascular biomarkers. Using a unified whole‑body cardiovascular model, synthetic PPG, APW, and BCG signals were generated and analyzed with neural posterior estimation and simulation‑based inference. Results show that incorporating BCG significantly improves estimation accuracy, converting multimodal posterior distributions from PPG/APW alone into unimodal distributions, thereby enhancing the reliability of cardiovascular biomarker estimation.
By Shusaku Maeda, Masahiro Nakano, Tomoharu Iwata, Kenji Komiya, Ryo Nishikimi, Kunio Kashino
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.
arXiv:2602. 04266v2 Announce Type: replace-cross Abstract: Aortic valve disease (AVD) represents a major public health burden, while its diagnosis relies on echocardiography, which is limited by cost and specialist expertise, restricting scalable screening and risk stratification.
By Jiaze Wang, Qinghao Zhao, Zizheng Chen, Zhejun Sun, Deyun Zhang, Yuxi Zhou, Shenda Hong
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.
By Yunwon Tae, Minje Park, Gyunho Rho, Dongjoon Yoo, Sunghoon Joo
arXiv:2608. 07759v1 Announce Type: cross Abstract: Cardiovascular AI models can classify clean elec- trocardiogram (ECG) signals, but real wearable signals change because of motion, breathing, posture, sensor contact, and true clinical deterioration.
By Farouk Ganiyu Adewumi, Timothy Oladunni, Rochak Ghimire, Kosisochukwu Ogbuanya, Sanaa Reeves, Sandy Akoy
arXiv:2607. 23412v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are widely used for cardiovascular risk prediction, yet models often fail to transfer across hospitals because of protocol, population, and measurement differences.
By Jie Lin, Weijie Sun, Sunil V. Kalmady, Anita Khalafbeigi, Abram Hindle, Padma Kaul, Russell Greiner