1
|
Cai J, Song J, Peng B. Enhancing ECG Heartbeat classification with feature fusion neural networks and dynamic minority-biased batch weighting loss function. Physiol Meas 2024; 45:075002. [PMID: 38936397 DOI: 10.1088/1361-6579/ad5cc0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2024] [Accepted: 06/27/2024] [Indexed: 06/29/2024]
Abstract
Objective.This study aims to address the challenges of imbalanced heartbeat classification using electrocardiogram (ECG). In this proposed novel deep-learning method, the focus is on accurately identifying minority classes in conditions characterized by significant imbalances in ECG data.Approach.We propose a feature fusion neural network enhanced by a dynamic minority-biased batch weighting loss function. This network comprises three specialized branches: the complete ECG data branch for a comprehensive view of ECG signals, the local QRS wave branch for detailed features of the QRS complex, and theRwave information branch to analyzeRwave characteristics. This structure is designed to extract diverse aspects of ECG data. The dynamic loss function prioritizes minority classes while maintaining the recognition of majority classes, adjusting the network's learning focus without altering the original data distribution. Together, this fusion structure and adaptive loss function significantly improve the network's ability to distinguish between various heartbeat classes, enhancing the accuracy of minority class identification.Main results.The proposed method demonstrated balanced performance within the MIT-BIH dataset, especially for minority classes. Under the intra-patient paradigm, the accuracy, sensitivity, specificity, and positive predictive value for Supraventricular ectopic beat were 99.63%, 93.62%, 99.81%, and 92.98%, respectively, and for Fusion beat were 99.76%, 85.56%, 99.87%, and 84.16%, respectively. Under the inter-patient paradigm, these metrics were 96.56%, 89.16%, 96.84%, and 51.99%for Supraventricular ectopic beat, and 96.10%, 77.06%, 96.25%, and 13.92%for Fusion beat, respectively.Significance.This method effectively addresses the class imbalance in ECG datasets. By leveraging diverse ECG signal information and a novel loss function, this approach offers a promising tool for aiding in the diagnosis and treatment of cardiac conditions.
Collapse
Affiliation(s)
- Jiajun Cai
- School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, Sichuan, People's Republic of China
| | - Junmei Song
- Department of Cardiovascular Ultrasound & Noninvasive Cardiology, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu 610072, People's Republic of China
- Ultrasound in Cardiac Electrophysiology and Biomechanics Key Laboratory of Sichuan Province, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu 610072, People's Republic of China
| | - Bo Peng
- School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, Sichuan, People's Republic of China
- Tianfu Jincheng Laboratory, City of Future Medicine, Chengdu 641400, Sichuan, People's Republic of China
| |
Collapse
|
2
|
Moreno-Sánchez PA, García-Isla G, Corino VDA, Vehkaoja A, Brukamp K, van Gils M, Mainardi L. ECG-based data-driven solutions for diagnosis and prognosis of cardiovascular diseases: A systematic review. Comput Biol Med 2024; 172:108235. [PMID: 38460311 DOI: 10.1016/j.compbiomed.2024.108235] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Revised: 02/07/2024] [Accepted: 02/25/2024] [Indexed: 03/11/2024]
Abstract
Cardiovascular diseases (CVD) are a leading cause of death globally, and result in significant morbidity and reduced quality of life. The electrocardiogram (ECG) plays a crucial role in CVD diagnosis, prognosis, and prevention; however, different challenges still remain, such as an increasing unmet demand for skilled cardiologists capable of accurately interpreting ECG. This leads to higher workload and potential diagnostic inaccuracies. Data-driven approaches, such as machine learning (ML) and deep learning (DL) have emerged to improve existing computer-assisted solutions and enhance physicians' ECG interpretation of the complex mechanisms underlying CVD. However, many ML and DL models used to detect ECG-based CVD suffer from a lack of explainability, bias, as well as ethical, legal, and societal implications (ELSI). Despite the critical importance of these Trustworthy Artificial Intelligence (AI) aspects, there is a lack of comprehensive literature reviews that examine the current trends in ECG-based solutions for CVD diagnosis or prognosis that use ML and DL models and address the Trustworthy AI requirements. This review aims to bridge this knowledge gap by providing a systematic review to undertake a holistic analysis across multiple dimensions of these data-driven models such as type of CVD addressed, dataset characteristics, data input modalities, ML and DL algorithms (with a focus on DL), and aspects of Trustworthy AI like explainability, bias and ethical considerations. Additionally, within the analyzed dimensions, various challenges are identified. To these, we provide concrete recommendations, equipping other researchers with valuable insights to understand the current state of the field comprehensively.
Collapse
Affiliation(s)
| | - Guadalupe García-Isla
- Department of Electronics Information and Bioengineering, Politecnico di Milano, Italy
| | - Valentina D A Corino
- Department of Electronics Information and Bioengineering, Politecnico di Milano, Italy
| | - Antti Vehkaoja
- Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
| | | | - Mark van Gils
- Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
| | - Luca Mainardi
- Department of Electronics Information and Bioengineering, Politecnico di Milano, Italy
| |
Collapse
|
3
|
Li F, Wang P, Wang Li X. Deep learning-based regional ECG diagnosis platform. Pacing Clin Electrophysiol 2024; 47:139-148. [PMID: 38029363 DOI: 10.1111/pace.14891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 11/06/2023] [Accepted: 11/15/2023] [Indexed: 12/01/2023]
Abstract
OBJECTIVE To enable the intelligent diagnosis of a variety of common Electrocardiogram (ECG), we investigate the deep learning-based ECG diagnosis system. METHODS From January 2015 to December 2019, four consecutive years of 100,120 conventional 12-lead ECG data were collected in our hospital. Utilizing this dataset, we constructed a deep learning model designed to intelligently diagnose prevalent ECG anomalies by employing a multi-task learning framework. The system performance was evaluated using various metrics, including sensitivity, specificity, negative predictive value, positive predictive value, and so forth. Additionally, we employed an ECG intelligent diagnostic platform for clinical application to undertake real-time online analysis of 2500 conventional 12-lead ECG samples in June 2020, aiming to validate our model. At this stage, we compared the performance of our model against the traditional manual identification method. RESULTS The efficacy of the ECG intelligent diagnostic model was notably high for common and straightforward ECG patterns, such as sinus rhythm (F1 = 98.01%), sinus tachycardia (F1 = 96.26%), sinus bradycardia (F1 = 94.88%), and a normal electrocardiogram (F1 = 91.71%), as well as for Premature Ventricular Contractions (F1 = 91.62%). Nevertheless, when diagnosing rarer and more intricate ECG anomalies, the system requires an increased number of samples to refine the deep learning models. During the validation stage, our model exhibited better efficiency in terms of accuracy, labor time and labor cost when compared to the manual identification approach. CONCLUSIONS Our deep learning-driven intelligent ECG diagnostic model clearly demonstrates significant clinical utility. The integrated artificial intelligence diagnosis system not only has the potential to augment physicians in their diagnostic processes but also offers a viable avenue to reduce associated labor costs.
Collapse
Affiliation(s)
- Fang Li
- Department of Cardiology, The First Affiliated Hospital of Huzhou University, Huzhou, Zhejiang Province, China
| | - Ping Wang
- Department of Cardiology, The First Affiliated Hospital of Huzhou University, Huzhou, Zhejiang Province, China
| | - Xiao Wang Li
- Department of Cardiology, The First Affiliated Hospital of Huzhou University, Huzhou, Zhejiang Province, China
| |
Collapse
|
4
|
Feng P, Fu J, Wang N, Zhou Y, Zhou B, Wang Z. Semantic-aware alignment and label propagation for cross-domain arrhythmia classification. Knowl Based Syst 2023. [DOI: 10.1016/j.knosys.2023.110323] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
|
5
|
Sinha N, Kumar Tripathy R, Das A. ECG beat classification based on discriminative multilevel feature analysis and deep learning approach. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103943] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
6
|
Zhang J, Yin H, Zhang J, Yang G, Qin J, He L. Real-time mental stress detection using multimodality expressions with a deep learning framework. Front Neurosci 2022; 16:947168. [PMID: 35992909 PMCID: PMC9389269 DOI: 10.3389/fnins.2022.947168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 07/11/2022] [Indexed: 11/13/2022] Open
Abstract
Mental stress is becoming increasingly widespread and gradually severe in modern society, threatening people’s physical and mental health. To avoid the adverse effects of stress on people, it is imperative to detect stress in time. Many studies have demonstrated the effectiveness of using objective indicators to detect stress. Over the past few years, a growing number of researchers have been trying to use deep learning technology to detect stress. However, these works usually use single-modality for stress detection and rarely combine stress-related information from multimodality. In this paper, a real-time deep learning framework is proposed to fuse ECG, voice, and facial expressions for acute stress detection. The framework extracts the stress-related information of the corresponding input through ResNet50 and I3D with the temporal attention module (TAM), where TAM can highlight the distinguishing temporal representation for facial expressions about stress. The matrix eigenvector-based approach is then used to fuse the multimodality information about stress. To validate the effectiveness of the framework, a well-established psychological experiment, the Montreal imaging stress task (MIST), was applied in this work. We collected multimodality data from 20 participants during MIST. The results demonstrate that the framework can combine stress-related information from multimodality to achieve 85.1% accuracy in distinguishing acute stress. It can serve as a tool for computer-aided stress detection.
Collapse
Affiliation(s)
- Jing Zhang
- College of Biomedical Engineering, Sichuan University, Chengdu, China
| | - Hang Yin
- College of Biomedical Engineering, Sichuan University, Chengdu, China
| | - Jiayu Zhang
- College of Biomedical Engineering, Sichuan University, Chengdu, China
| | - Gang Yang
- College of Biomedical Engineering, Sichuan University, Chengdu, China
| | - Jing Qin
- Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong SAR, China
| | - Ling He
- College of Biomedical Engineering, Sichuan University, Chengdu, China
- *Correspondence: Ling He,
| |
Collapse
|
7
|
Petmezas G, Stefanopoulos L, Kilintzis V, Tzavelis A, Rogers JA, Katsaggelos AK, Maglaveras N. State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint). JMIR Med Inform 2022; 10:e38454. [PMID: 35969441 PMCID: PMC9425174 DOI: 10.2196/38454] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2022] [Revised: 06/03/2022] [Accepted: 07/03/2022] [Indexed: 11/13/2022] Open
Abstract
Background Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals. Objective This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications. Methods The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches. Results We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models. Conclusions We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.
Collapse
Affiliation(s)
- Georgios Petmezas
- Lab of Computing, Medical Informatics and Biomedical-Imaging Technologies, The Medical School, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Leandros Stefanopoulos
- Lab of Computing, Medical Informatics and Biomedical-Imaging Technologies, The Medical School, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Vassilis Kilintzis
- Lab of Computing, Medical Informatics and Biomedical-Imaging Technologies, The Medical School, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Andreas Tzavelis
- Department of Biomedical Engineering, Northwestern University, Evanston, IL, United States
| | - John A Rogers
- Department of Material Science, Northwestern University, Evanston, IL, United States
| | - Aggelos K Katsaggelos
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, United States
| | - Nicos Maglaveras
- Lab of Computing, Medical Informatics and Biomedical-Imaging Technologies, The Medical School, Aristotle University of Thessaloniki, Thessaloniki, Greece
| |
Collapse
|
8
|
Feng P, Fu J, Ge Z, Wang H, Zhou Y, Zhou B, Wang Z. Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection. Inf Sci (N Y) 2022. [DOI: 10.1016/j.ins.2021.09.046] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
9
|
Li G, Tan Z, Xu W, Xu F, Wang L, Chen J, Wu K. A particle swarm optimization improved BP neural network intelligent model for electrocardiogram classification. BMC Med Inform Decis Mak 2021; 21:99. [PMID: 34330266 PMCID: PMC8322832 DOI: 10.1186/s12911-021-01453-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2021] [Accepted: 02/22/2021] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND As proven to reflect the work state of heart and physiological situation objectively, electrocardiogram (ECG) is widely used in the assessment of human health, especially the diagnosis of heart disease. The accuracy and reliability of abnormal ECG (AECG) decision depend to a large extent on the feature extraction. However, it is often uneasy or even impossible to obtain accurate features, as the detection process of ECG is easily disturbed by the external environment. And AECG got many species and great variation. What's more, the ECG result obtained after a long time past, which can not reach the purpose of early warning or real-time disease diagnosis. Therefore, developing an intelligent classification model with an accurate feature extraction method to identify AECG is of quite significance. This study aimed to explore an accurate feature extraction method of ECG and establish a suitable model for identifying AECG and the diagnosis of heart disease. METHODS In this research, the wavelet combined with four operations and adaptive threshold methods were applied to filter the ECG and extract its feature waves first. Then, a BP neural network (BPNN) intelligent model and a particle swarm optimization (PSO) improved BPNN (PSO-BPNN) intelligent model based on MIT-BIH open database was established to identify ECG. To reduce the complexity of the model, the principal component analysis (PCA) was used to minimize the feature dimension. RESULTS Wavelet transforms combined four operations and adaptive threshold methods were capable of ECG filtering and feature extraction. PCA can significantly deduce the modeling feature dimension to minimize the complexity and save classification time. The PSO-BPNN intelligent model was suitable for identifying five types of ECG and showed better effects while comparing it with the BPNN model. CONCLUSION In summary, it was further concluded that the PSO-BPNN intelligent model would be a suitable way to identify AECG and provide a tool for the diagnosis of heart disease.
Collapse
Affiliation(s)
- Guixiang Li
- National Engineering Research Center for Healthcare Devices, Guangdong Key Lab of Medical Electronic Instruments and Polymer Material Products, Guangdong Institute of Medical Instruments, Institute of Medicine and Health, Guangdong Academy of Sciences, Guangzhou, 510500, China.,Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, 510500, China
| | - Zhongwei Tan
- National Engineering Research Center for Healthcare Devices, Guangdong Key Lab of Medical Electronic Instruments and Polymer Material Products, Guangdong Institute of Medical Instruments, Institute of Medicine and Health, Guangdong Academy of Sciences, Guangzhou, 510500, China
| | - Weikang Xu
- National Engineering Research Center for Healthcare Devices, Guangdong Key Lab of Medical Electronic Instruments and Polymer Material Products, Guangdong Institute of Medical Instruments, Institute of Medicine and Health, Guangdong Academy of Sciences, Guangzhou, 510500, China
| | - Fei Xu
- National Engineering Research Center for Healthcare Devices, Guangdong Key Lab of Medical Electronic Instruments and Polymer Material Products, Guangdong Institute of Medical Instruments, Institute of Medicine and Health, Guangdong Academy of Sciences, Guangzhou, 510500, China
| | - Lei Wang
- Department of Artificial Intelligence, College of Information and Communication Engineering, Hainan University, Haikou, 570228, China.
| | - Jun Chen
- National Engineering Research Center for Healthcare Devices, Guangdong Key Lab of Medical Electronic Instruments and Polymer Material Products, Guangdong Institute of Medical Instruments, Institute of Medicine and Health, Guangdong Academy of Sciences, Guangzhou, 510500, China. .,Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, 510500, China.
| | - Kai Wu
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, 510006, China. .,Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, 510500, China. .,Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, 510370, China. .,The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou, 510370, China. .,National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, 510006, China. .,Key Laboratory of Biomedical Engineering of Guangdong Province, South China University of Technology, Guangzhou, 510006, China. .,Department of Nuclear Medicine and Radiology, Institute of Development, Aging and Cancer, Tohoku University, Sendai, 980-8575, Japan.
| |
Collapse
|