The paper introduces a deep learning-based signal quality assessment model that differentiates clean from noisy ambulatory ECG recordings. It is trained on the Copenhagen Center for Health Technology-Contextualized Arrhythmia Database, the first ambulatory ECG database that includes both physical and patient-reported contextual data. The model maintains stable performance across other datasets such as MIT and PhysioNet/CinC Challenge 2021, and the study demonstrates how the model can be used to investigate complex ECG noise in conjunction with contextual information.
By Xiaopeng Mao, Marike Weisbjerg, Sadasivan Puthusserypady
arXiv:2407. 20893v2 Announce Type: replace-cross Abstract: Cardiac arrhythmia, a condition characterized by irregular heartbeats, often serves as an early indication of various heart ailments.
By Yinlong Xu, Zitai Kong, Yixuan Wu, Yue Wang, Xiaoqiang Liu, Yingzhou Lu, Jian Wu, Hongxia Xu
arXiv:2601. 00014v2 Announce Type: replace-cross Abstract: Heart failure (HF) affects 11.
By Eran Zvuloni, Ronit Almog, Michael Glikson, Shany Brimer Biton, Ilan Green, Izhar Laufer, Offer Amir, Joachim A. Behar
arXiv:2609.08992v1 Announce Type: new
Abstract: False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units. We propose a deep learning framework comb...
By Athanasios Papastathopoulos-Katsaros, Alexandra Stavrianidi, Zhandong Liu
arXiv:2606. 10802v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) typically require extensive datasets for effective training.
By Naoki Nonaka, Jun Seita
The paper introduces R‑U‑Net, an ECG delineation model that combines a ResNet‑18 encoder with a U‑Net decoder. It demonstrates that this decoder design outperforms a ResNet‑18 + fully convolutional network baseline across 16 in‑domain settings and improves cross‑domain performance by 8.1 mIoU. Ablation studies reveal that the decoder contributes more to performance gains than the evaluated semi‑supervised learning methods.
By Joseph Scharpf, William Han, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Ding Zhao
arXiv:2606. 02256v1 Announce Type: new Abstract: Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference on resource-constrained embedded systems.
By Nagarajan S, Kurian Polachan
arXiv:2607. 09680v1 Announce Type: cross Abstract: Continuous cardiac monitoring in wearable devices demands classifiers that are simultaneously accurate, energy-efficient, and deployable on resource-constrained hardware.
By Anh Tran, Khanh Tran, Cuong Do
Apnoea of prematurity is characterised by recurrent episodes of cessation of breathing and remains difficult to detect reliably using routinely monitored physiological signals in the Neonatal Intensive Care Unit (NICU). Existing bedside monitors rely primarily on respiratory rate and oxygen saturation thresholds, often generating high false-positive alarm rates and missing short or irregular events.
TinyCardioUNet is a lightweight UNet designed to translate inertial measurement unit (IMU) data into electrocardiography (ECG) signals. It processes all six IMU axes, refines its bottleneck with a graph neural network that captures inter‑axis dependencies, and reduces parameters via tensor decomposition with variational Bayesian rank selection. On a public dataset it achieves an RMSE of 0.098 and a Pearson correlation of 0.677 with only 36.0 k parameters, while maintaining robustness to additive noise.
By Seungwoo Han, Ingon Chanpornpakdi, Motoi Noda, Puwadej Leelasiri, Ibuki Hiruma, Toshihisa Tanaka
The paper introduces DPNet, a Mamba-based deep learning framework for denoising photoplethysmography (PPG) signals while preserving physiological information. It incorporates a scale‑invariant signal‑to‑distortion ratio loss and an auxiliary heart‑rate predictor to enhance waveform fidelity and maintain heart‑rate accuracy. Experiments on the BIDMC dataset show that DPNet outperforms conventional filtering and existing neural models in robustness against synthetic noise and real‑world motion artifacts, making it suitable for wearable healthcare systems.
By I Chiu, Yu-Tung Liu, Kuan-Chen Wang, Hung-Yu Wei, Yu Tsao
The paper presents a new labelled ICU dataset and benchmarks for detecting atrial fibrillation (AF) from electrocardiograms (ECGs). It compares three AI approaches—feature‑based classifiers, deep learning, and ECG foundation models—across Canadian ICU data and the 2021 PhysioNet challenge, finding that ECG foundation models with transfer learning achieve the highest F1 score (0.89). The study demonstrates the feasibility of automated AF monitoring in ICU settings and provides resources for further research.
By Sarah Nassar, Nooshin Maghsoodi, Sophia Mannina, Shamel Addas, Stephanie Sibley, Gabor Fichtinger, David Pichora, David Maslove, Purang Abolmaesumi, Parvin Mousavi