Electrocardiogram is a useful diagnostic signal that can detect cardiac abnormalities by measuring the electrical activity generated by the heart. Due to its rapid, non-invasive, and richly informative characteristics, ECG has many emerging applications. In this paper, we study novel deep learning technologies to effectively manage and analyse ECG data, with the aim of building a diagnostic model, accurately and quickly, that can substantially reduce the burden on medical workers. Unlike the existing ECG models that exhibit a high misdiagnosis rate, our deep learning approaches can automatically extract the features of ECG data through end-to-end training. Specifically, we first devise EfficientECG, an accurate and lightweight classification model for ECG analysis based on the existing EfficientNet model, which can effectively handle high-frequency long-sequence ECG data with various leading types. On top of that, we next propose a cross-attention-based feature fusion model of EfficientECG for analysing multi-lead ECG data with multiple features (e.g., gender and age). Our evaluations on representative ECG datasets validate the superiority of our model against state-of-the-art works in terms of high precision, multi-feature fusion, and lightweights.
Amplitude-Phase Fusion for Enhanced Electrocardiogram Morphological Analysis
Fudan University（复旦大学）；Shanghai Institute of Cardiovascular Diseases, Zhongshan Hospital, Fudan University（复旦大学附属中山医院上海市心血管病研究所）；Zhongshan Hospital, Fudan University（复旦大学附属中山医院）；University of Shanghai for Science and Technology（上海理工大学）
Deep Neural Network Architectures for Electrocardiogram Classification: A Comprehensive Evaluation
Independent Researcher（独立研究者）；Department of Materials Engineering, Xi'an Polytechnic University（材料工程系，西安理工大学）；Tandon School of Engineering, New York University（工程学院，纽约大学）；College of Computing, Georgia Institute of Technology（计算学院，佐治亚理工学院）
Multimodal wearable physiological data in daily life have been used to estimate self-reported stress labels. However, missing data modalities in data collection makes it challenging to leverage all the collected samples. Besides, heterogeneous sensor data and labels among individuals add challenges in building robust stress detection models. In this paper, we proposed a modality fusion network (MFN) to train models and infer self-reported binary stress labels under both complete and incomplete modality conditions. In addition, we applied personalized attention (PA) strategy to leverage persona…
Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification
Xi’an Institute of Optics and Precision Mechanics, CAS（西安光学精密机械研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Southwest Jiaotong University（西南交通大学）；Zhongnan Hospital of Wuhan University（武汉大学中南医院）；Xi’an Jiaotong University（西安交通大学）；National Key Laboratory of Information Systems Engineering（信息系统工程国家重点实验室）
本文提出通道强制融合（CIF）方法，通过跨通道信息融合增强信噪比并减少冗余，结合时间卷积网络（TCN）构建结构透明、高效的医学时间序列分类框架，在多个 EEG 和 ECG 数据集上超越现有 SOTA 方法并提升分类过程透明性。
Multi-Feature Fusion and Compressed Bi-LSTM for Memory-Efficient Heartbeat Classification on Wearable Devices
School of Electrical and Electronic Engineering, University College Dublin（都柏林大学学院电气与电子工程学院）；School of Electrical and Electronic Engineering, California Institute of Technology（加州理工学院电气与电子工程学院）
Electrocardiogram (ECG) is an authoritative source to diagnose and counter critical cardiovascular syndromes such as arrhythmia and myocardial infarction (MI). Current machine learning techniques either depend on manually extracted features or large and complex deep learning networks which merely utilize the 1D ECG signal directly. Since intelligent multimodal fusion can perform at the stateof-the-art level with an efficient deep network, therefore, in this paper, we propose two computationally efficient multimodal fusion frameworks for ECG heart beat classification called Multimodal Image Fus…
Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension
School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院）；Centre for Machine Intelligence, University of Sheffield（谢菲尔德大学智能中心）；Department of Electrical & Computer Science Engineering, IITRAM Ahmedabad（印度阿赫迈德亚布德IITRAM电子与计算机科学工程系）；Digital Environment Research Institute, Queen Mary University of London（伦敦玛丽女王大学数字环境研究院）；Nepal Applied Mathematics and Informatics Institute for research (NAAMII), Nepal（尼泊尔应用数学与信息技术研究所）；Department of Computing, Imperial College London（伦敦帝国学院计算机系）；School of Medicine and Population Health, University of Sheffield（谢菲尔德大学医学与人口健康学院）；Department of Clinical Radiology, Sheffield Teaching Hospitals（谢菲尔德教学医院放射科）；National Institute for Health and Care Research (NIHR), Sheffield Biomedical Research Centre（英国国家健康与护理研究所（NIHR）谢菲尔德生物医学研究中心）
Leveraging Foundational Models and Simple Fusion for Multi-modal Physiological Signal Analysis
Computer and Communication Engineering Department, Alexandria University（亚历山大大学计算机与通信工程系）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
IBM Research - Africa（IBM非洲研究院）；University of Oxford（牛津大学）；Guangdong Cardiovascular Institute（广东省心血管病研究所）
Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detection of MI and information regarding its occurrence-time in particular, would enable timely interventions that may improve patient outcomes, thereby reducing the global rise in CVD deaths. Electrocardiogram (ECG) recordings are currently used to screen MI patients. However, manual inspection of ECGs is time-consuming and prone to subjective bias. Machine learning methods have been adopted for automated ECG diagnosis, but most approaches require extraction of ECG beats or consider leads independentl…
Ventricular Fibrillation (VF), one of the most dangerous arrhythmias, is responsible for sudden cardiac arrests. Thus, various algorithms have been developed to predict VF from Electrocardiogram (ECG), which is a binary classification problem. In the literature, we find a number of algorithms based on signal processing, where, after some robust mathematical operations the decision is given based on a predefined threshold over a single value. On the other hand, some machine learning based algorithms are also reported in the literature; however, these algorithms merely combine some parameters an…
School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；Department of Electrocardiogram, The First Affiliated Hospital of University of Science and Technology of China (Anhui Provincial Hospital)（中国科学技术大学附属第一医院（安徽省立医院）心电图科）
Automatic arrhythmia detection using 12-lead electrocardiogram (ECG) signal plays a critical role in early prevention and diagnosis of cardiovascular diseases. In the previous studies on automatic arrhythmia detection, most methods concatenated 12 leads of ECG into a matrix, and then input the matrix to a variety of feature extractors or deep neural networks for extracting useful information. Under such frameworks, these methods had the ability to extract comprehensive features (known as integrity) of 12-lead ECG since the information of each lead interacts with each other during training. How…
IIT Bhubaneswar（布巴内斯瓦尔印度理工学院）；University of Auckland（奥克兰大学）
Biophysical signals such as Electrocardiogram (ECG) and Photoplethysmogram (PPG) are key to the sensing of vital parameters for wellbeing. Coincidentally, ECG and PPG are signals, which provide a "different window" into the same phenomena, namely the cardiac cycle. While they are used separately, there are no studies regarding the exact correction of the different ECG and PPG events. Such correlation would be helpful in many fronts such as sensor fusion for improved accuracy using cheaper sensors and attack detection and mitigation methods using multiple signals to enhance the robustness, for …
S2M2ECG: Spatio-temporal bi-directional State Space Model Enabled Multi-branch Mamba for ECG
School of Physics and Technology（物理与技术学院）；Wuhan University（武汉大学）；Pratt School of Engineering（工程学院）；Duke University（杜克大学）；Faculty of Artificial Intelligence in Education（教育人工智能学院）；Central China Normal University（中部师范大学）；Huangpu Branch of Shanghai Ninth People’s Hospital（上海第九人民医院黄浦分院）
National Heart, Lung, and Blood Institute（美国国家心肺血液研究所）
The electrocardiogram (ECG) is routinely used in hospitals to analyze cardiovascular status and health of an individual. Abnormal heart rhythms can be a precursor to more serious conditions including sudden cardiac death. Classifying abnormal rhythms is a laborious process prone to error. Therefore, tools that perform automated classification with high accuracy are highly desirable. The work presented classifies five different types of ECG arrhythmia based on AAMI EC57 standard and using the MIT-BIH data set. These include non-ectopic (normal), supraventricular, ventricular, fusion, and unknow…
Chonnam National University（全南国立大学）；University of Arkansas（阿肯色大学）；West Virginia University（西弗吉尼亚大学）
Electrocardiogram (ECG) signal is one of the most effective sources of information mainly employed for the diagnosis and prediction of cardiovascular diseases (CVDs) connected with the abnormalities in heart rhythm. Clearly, single modality ECG (i.e. time series) cannot convey its complete characteristics, thus, exploiting both time and time-frequency modalities in the form of time-series data and spectrogram is needed. Leveraging the cutting-edge self-supervised learning (SSL) technique on unlabeled data, we propose SSL-based multimodality ECG classification. Our proposed network follows SSL …
MSW-Transformer: Multi-Scale Shifted Windows Transformer Networks for 12-Lead ECG Classification
Shantou University（汕头大学）；Sun Yet-sun University（中山大学）；The First Affiliated Hospital of Shantou University（汕头大学第一附属医院）；Shantou Institute of Ultrasonic Instruments Co., Ltd.（汕头超声仪器研究所有限公司）
