Deep Neural Networks Generalization and Fine-Tuning for 12-lead ECG Classification
Ivannikov Institute for System Programming of the Russian Academy of Sciences（俄罗斯科学院伊万尼科夫系统编程研究所）；Russian-Armenian University（俄罗斯-亚美尼亚大学）；Novgorod State University（诺夫哥罗德国立大学）
Numerous studies are aimed at diagnosing heart diseases based on 12-lead electrocardiographic (ECG) records using deep learning methods. These studies usually use specific datasets that differ in size and parameters, such as patient metadata, number of doctors annotating ECGs, types of devices for ECG recording, data preprocessing techniques, etc. It is well-known that high-quality deep neural networks trained on one ECG dataset do not necessarily perform well on another dataset or clinical settings. In this paper, we propose a methodology to improve the quality of heart disease prediction regardless of the dataset by training neural networks on a variety of datasets with further fine-tuning for the specific dataset. To show its applicability, we train different neural networks on a large private dataset TIS containing various ECG records from multiple hospitals and on a relatively small public dataset PTB-XL. We demonstrate that training the networks on a large dataset and fine-tuning it on a small dataset from another source outperforms the networks trained only on one small dataset. We also show how the ability of a deep neural networks to generalize allows to improve classification quality of more diseases.
MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
The Ohio State University（俄亥俄州立大学）；Imperial College London（伦敦帝国理工学院）；The University of Hong Kong（香港大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Physikalisch Technische Bundesanstalt（德国联邦物理技术研究院）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希赫兹研究所）；University of Oldenburg（奥尔登堡大学）
Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity remains a central challenge in the field. Self-supervised learning represents a promising way to alleviate this issue. In this work, we put forward the first comprehensive assessment of self-supervised representation learning from clinical 12-lead ECG data. To this end, we adapt state-of-the-art self-supervised methods based on instance discrimination and latent forecasting to the ECG domain. In a first step, we learn co…
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…
MEETI: A Multimodal ECG Dataset from MIMIC-IV-ECG with Signals, Images, Features and Interpretations
HeartVoice Medical Technology（HeartVoice医疗科技）；Saw Swee Hock School of Public Health and Institute of Data Science（Saw Swee Hock公共卫生学院和数据科学研究所）；National University of Singapore（新加坡国立大学）；Department of Cardiology, Peking University People’s Hospital（北京大学人民医院心内科）；College of Integrative Chinese and Western Medicine, Anhui University of Chinese Medicine（安徽中医药大学整合中西医学学院）；National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
University of Saskatchewan（萨斯喀彻温大学）；University of Isfahan（伊斯法罕大学）；University of North Dakota（北达科他大学）
Non-invasive fetal electrocardiogram (FECG) is used to monitor the electrical pulse of the fetal heart. Decomposing the FECG signal from maternal ECG (MECG) is a blind source separation problem, which is hard due to the low amplitude of FECG, the overlap of R waves, and the potential exposure to noise from different sources. Traditional decomposition techniques, such as adaptive filters, require tuning, alignment, or pre-configuration, such as modeling the noise or desired signal. to map MECG to FECG efficiently. The high correlation between maternal and fetal ECG parts decreases the performan…
An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domains
National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院）；Department of Cardiology, Massachusetts General Hospital（麻省总医院心内科）；Department of Biomedical Informatics, School of Medicine, Emory University（埃默里大学医学院生物医学信息学系）；Department of Biomedical Engineering, Georgia Institute of Technology（佐治亚理工学院生物医学工程系）；Harvard Medical School（哈佛医学院）；Department of Neurology, Beth Israel Deaconess Medical Center（贝斯以色列医疗中心神经科）；Department of Computing, Data Science Institute, Imperial College London（伦敦帝国学院计算系、数据科学研究所）；Zhongshan School of Medicine, Sun Yat-sen University（中山医学院，孙逸仙大学）；Institute of Medical Technology, Peking University Health Science Center（北京大学医学技术研究所，北京大学医学部）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
Electrocardiographic signal is a subject to multiple noises, caused by various factors. It is therefore a standard practice to denoise such signal before further analysis. With advances of new branch of machine learning, called deep learning, new methods are available that promises state-of-the-art performance for this task. We present a novel approach to denoise electrocardiographic signals with deep recurrent denoising neural networks. We utilize a transfer learning technique by pretraining the network using synthetic data, generated by a dynamic ECG model, and fine-tuning it with a real dat…
University of Sfax（斯法克斯大学）；National Engineering School of Sfax (ENIS)（斯法克斯国家工程学院）；Faculty of Science of Sfax (FSS)（斯法克斯科学学院）
The interpretation of the electrocardiogram (ECG) gives clinical information and helps in assessing heart function. There are distinct ECG patterns associated with a specific class of arrythmia. The convolutional neural network is currently one of the most commonly employed deep learning algorithms for ECG processing. However, deep learning models require many hyperparameters to tune. Selecting an optimal or best hyperparameter for the convolutional neural network algorithm is a highly challenging task. Often, we end up tuning the model manually with different possible ranges of values until a…
Personalized Deep Learning for Short-Term Forecasting of Impending Atrial Fibrillation from Continuous Wearable ECG Signals
Seoul National University（首尔大学）；CHA Bundang Medical Center and CHA University School of Medicine（CHA板桥医疗中心和CHA大学医学院）；SEERS Technology Co., Ltd（SEERS科技有限公司）；Department of Internal Medicine, Seoul National University College of Medicine and Seoul National University Hospital（首尔大学医学院内科学系和首尔大学医院）
National Institute of Health Data Science, Peking University（北京大学健康数据科学国家研究院）；Department of Cardiology, Peking University People’s Hospital（北京大学人民医院心内科）；Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术学院）；Tianjin Key Laboratory of lonic-Molecular Function of Cardiovascular Disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical University（天津医科大学第二医院心脏研究所心内科离子-分子心血管功能天津市重点实验室）
Label-Efficient Deep Learning for ECG Delineation: A Multi-Dataset Benchmark against Widely Used Delineation Tools
VUNO Inc.（VUNO公司）；Ajou University（亚洲大学）；C&Thoth Co., Ltd.（C&Thoth有限公司）；Chonnam National University Graduate School（全南大学研究生院）；Chonnam National University Hospital（全南大学医院）；Chonnam National University Medical School（全南大学医学院）
School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；Peng Cheng Laboratory（鹏城实验室）；School of Physics and Astronomy, University of Manchester（曼彻斯特大学物理与天文学院）；Northeastern University（东北大学）
Supervised deep learning has been widely used in the studies of automatic ECG classification, which largely benefits from sufficient annotation of large datasets. However, most of the existing large ECG datasets are roughly annotated, so the classification model trained on them can only detect the existence of abnormalities in a whole recording, but cannot determine their exact occurrence time. In addition, it may take huge time and economic cost to construct a fine-annotated ECG dataset. Therefore, this study proposes weakly supervised deep learning models for detecting abnormal ECG events an…
AnyECG: Evolved ECG Foundation Model for Holistic Health Profiling
National Institute of Health Data Science, Peking University（北京大学健康数据科学国家研究院）；Institute of Medical Technology, Health Science Center of Peking University（北京大学医学技术研究所）；Department of Internal Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology（同济大学同济医学院内科部）；Department of Cardiology, Peking University People’s Hospital（北京大学人民医院心内科）；Department of Epidemiology and Biostatistics, School of Public Health, Peking University（北京大学公共卫生学院流行病与生物统计学系）；Peking University Center for Public Health and Epidemic Preparedness & Response（北京大学公共卫生与突发卫生事件应对中心）；Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education（北京大学主要疾病流行病学重点实验室）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；HeartVoice Medical Technology（心声医疗技术）
Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction
Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford（生物医学工程研究所，工程科学系，牛津大学）；Imperial College London（伦敦帝国学院）；University of Sheffield（谢菲尔德大学）；Novo Nordisk Research Centre Oxford (NNRCO)（牛津诺和硕研究中心（NNRCO））；Royal Society（皇家学会）
Masked Transformer for Electrocardiogram Classification
Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College（中国医学科学院北京协和医学院国家心血管病中心阜外医院）
本文提出 MTECG 方法，将掩码自编码器应用于 ECG 时间序列的自监督表示学习，并在多个数据集上显著提升了分类的宏 F1 分数。
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）
School of Electrical Engineering and Robotics, Queensland University of Technology（昆士兰科技大学电气工程与机器人学院）；Centre for Accident Research & Road Safety Queensland, Queensland University of Technology（昆士兰科技大学昆士兰事故研究与道路安全中心）；School of Information Technology, Deakin University（迪肯大学信息技术学院）
Stress and driving are a dangerous combination which can lead to crashes, as evidenced by the large number of road traffic crashes that involve stress. Motivated by the need to address the significant costs of driver stress, it is essential to build a practical system that can classify driver stress level with high accuracy. However, the performance of an accurate driving stress levels classification system depends on hyperparameter optimization choices such as data segmentation (windowing hyperparameters). The configuration setting of hyperparameters, which has an enormous impact on the syste…
radarODE: An ODE-Embedded Deep Learning Model for Contactless ECG Reconstruction from Millimeter-Wave Radar
School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学先进科技学院）；Department of Electrical Engineering and Electronics, University of Liverpool（利物浦大学电子工程与电子系）；Institute of Deep Perception Technology, JITRI（深度感知技术研究所）；Multimedia Lab (MMLab), Department of Information Engineering, the Chinese University of Hong Kong（信息工程系，香港中文大学多媒体实验室）；Thrust of Artificial Intelligence and Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou)（人工智能与智能交通方向，香港科技大学（广州））
A new method using deep transfer learning on ECG to predict the response to cardiac resynchronization therapy
Michigan Technological University（密歇根理工大学）；The First Affiliated Hospital of Nanjing Medical University（南京医科大学第一附属医院）；The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University（南京医科大学附属淮安第一人民医院）；Health Research Institute, Michigan Technological University（密歇根理工大学健康研究院）
In order to exploit representations of time-series signals, such as physiological signals, it is essential that these representations capture relevant information from the whole signal. In this work, we propose to use a Transformer-based model to process electrocardiograms (ECG) for emotion recognition. Attention mechanisms of the Transformer can be used to build contextualized representations for a signal, giving more importance to relevant parts. These representations may then be processed with a fully-connected network to predict emotions. To overcome the relatively small size of datasets w…
Classification of Infant Sleep/Wake States: Cross-Attention among Large Scale Pretrained Transformer Networks using Audio, ECG, and IMU Data
University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beckman Institute for Advanced Science and Technology（贝克曼高级科学技术研究院）；Worcester Polytechnic Institute（伍斯特理工学院）
NEF-NET+: Adapting Electrocardio panorama in the wild
Information Hub, Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）信息中心）；School of Biomedical Engineering, Sun Yat-sen University, Shenzhen（中山大学医学院深圳校区）；College of Computer Science and Technology, Zhejiang University, Hangzhou（浙江大学计算机科学与技术学院）；Department of Electrical and Electronic Engineering, University of Hong Kong, Pokfulam（香港大学电子与电气工程系）
