Computer analysis of electrocardiograms(ECGs)was introduced more than 50 years ago,with the aim to improve efficiency and clinical workflow.[1,2]However,inaccuracies have been documented in the literature.[3,4]Researc...Computer analysis of electrocardiograms(ECGs)was introduced more than 50 years ago,with the aim to improve efficiency and clinical workflow.[1,2]However,inaccuracies have been documented in the literature.[3,4]Research indicates that emergency department(ED)clinician interruptions occur every 4-10 min,which is significantly more common than in other specialties.[5]This increases the cognitive load and error rates and impacts patient care and clinical effi ciency.[1,2,5]De-prioritization protocols have been introduced in certain centers in the United Kingdom(UK),removing the need for clinician ECG interpretation where ECGs have been interpreted as normal by the machine.展开更多
BACKGROUND As cardiovascular mortality continues to increase globally,percutaneous coronary intervention(PCI)with stent placement stands out as a cutting-edge and highly effective treatment for severe cardiovascular d...BACKGROUND As cardiovascular mortality continues to increase globally,percutaneous coronary intervention(PCI)with stent placement stands out as a cutting-edge and highly effective treatment for severe cardiovascular diseases.However,the inherent invasiveness of any endovascular procedure introduces the risk of coronary vessel and myocardial damage.AIM To evaluate the utility of a novel electrocardiographic metric in detecting subtle myocardial injuries after coronary stenting.METHODS This investigation was conducted in 2021 at the Kyiv Heart Institute of the Ministry of Healthcare of Ukraine.The study involved 23 patients who underwent PCI,each subjected to a meticulous preoperative examination.A paired measurement approach was employed,encompassing 3-minutes electrocardiogram(ECG)recordings both before and several hours following the operation,using a compact ECG device.Each pair of ECG underwent a thorough analysis,scrutinizing 240 primary and computed ECG parameters.RESULTS The analysis delineated a distinct subgroup exhibiting significant myocardial damage post-stenting.This subgroup was characterized by an older average age and more stents than their counterparts.Notably,a concurrent reduction in the psychoemotional state index was observed alongside the ECG alterations in these patients,suggesting a correlation between myocardial damage and psychoemotional distress.Introducing a new electrocardiographic index has illuminated the often-subtle myocardial damage incurred during PCI.CONCLUSION The newly devised electrocardiographic metric is a significant advancement in the early detection of myocardial damage following PCI,able to capture not only physiological but also psychoemotional changes.展开更多
With the rapid advancement and widespread adoption of new artificial intelligence(AI)technologies,personalized medicine and more accurate diagnosis using medical imaging are now possible.Among its many applications,AI...With the rapid advancement and widespread adoption of new artificial intelligence(AI)technologies,personalized medicine and more accurate diagnosis using medical imaging are now possible.Among its many applications,AI has shown remarkable potential in the analysis of electrocardiograms(ECGs),which provide essential insights into the electrical activity of the heart and allowing early detection of ischemic heart disease(IHD).Notably,single-lead ECG(SLECG)analysis has emerged as a key focus in recent research due to its potential for widespread and efficient screening.This editorial focuses on the latest research progress of AI-enabled SLECG utilized in the diagnosis of IHD.展开更多
Objective:To investigate the effect of 12-lead electrocardiogram and 24-hour dynamic electrocardiogram in detecting pacemaker dysfunction and changes in cardiac function indexes in patients with pacemaker implantation...Objective:To investigate the effect of 12-lead electrocardiogram and 24-hour dynamic electrocardiogram in detecting pacemaker dysfunction and changes in cardiac function indexes in patients with pacemaker implantation.Methods:A total of 136 patients with pacemaker implantation in the First Clinical Medical College of Three Gorges University,Institute of Cardiovascular Disease of Three Gorges University and Yicang Central People’s Hospital from January 2023 to December 2024 were selected as the research objects.All patients received 12-lead electrocardiogram and 24-hour holter 3–14 days after implantation.Results:The overall detection rate of various types of pacemaker dysfunction by Holter was significantly higher than that by conventional ECG(27.21%vs.5.15%,χ^(2)=24.402,P<0.001).The overall arrhythmia detection rate of Holter was significantly higher than that of conventional electrocardiogram(57.35%vs.10.29%,χ^(2)=67.277,P<0.001).The time domain indexes of heart rate variability obtained by 24-hour continuous monitoring of Holter were significantly improved compared with those of conventional electrocardiogram(P<0.05).Conclusions:Compared with 12-lead electrocardiogram,24-hour holter monitoring can more accurately detect pacemaker dysfunction and arrhythmia in patients with pacemaker implantation,and provide more comprehensive data of heart rate variability,which is helpful for clinicians to better evaluate the cardiac function of patients and adjust treatment plans.展开更多
BACKGROUND Arm-implanted totally implantable venous access devices(peripherally inserted central catheter port)have become an important vascular access for colorectal cancer chemotherapy,but traditional anatomical lan...BACKGROUND Arm-implanted totally implantable venous access devices(peripherally inserted central catheter port)have become an important vascular access for colorectal cancer chemotherapy,but traditional anatomical landmark positioning techniques have issues with inaccurate positioning and high complication rates.AIM To evaluate the clinical value of image pre-measurement combined with intracavitary electrocardiogram(IC-ECG)positioning technology in arm port implantation for colorectal cancer patients.METHODS A retrospective analysis was conducted on 216 colorectal cancer patients who received arm port implantation in our hospital from January 2024 to December 2024.Patients were divided into an experimental group(image pre-measurement combined with IC-ECG positioning technology,n=103)and a control group(traditional anatomical landmark positioning technique,n=113).Technical success rate,operation time,catheter tip position accuracy,number of intraoperative catheter adjustments,X-ray exposure time,and postoperative complication rates were compared between the two groups.RESULTS The experimental group demonstrated superior outcomes compared to the control group across all key measures.Technical success rate was higher(98.4%vs 92.7%,P<0.05)with significantly reduced operation time(23.6±5.2 minutes vs 31.5±7.8 minutes,P<0.01).Catheter tip positioning accuracy improved substantially(97.6%vs 85.4%,P=0.002)while X-ray exposure time decreased by 71.8%(5.3±2.1 seconds vs 18.7±4.5 seconds,P<0.001).Threemonth complication rates were markedly lower in the experimental group(4.1%vs 14.6%,P=0.008),including significant reductions in catheter-related thrombosis(0.8%vs 4.9%),displacement(1.6%vs 5.7%),and occlusion(1.6%vs 4.1%).Multivariate analysis identified traditional technique as the strongest risk factor(odds ratio=4.27,P<0.001),while the combined IC-ECG approach was protective(odds ratio=0.34 for displacement,P=0.018).Long-term outcomes favored the experimental group with higher chemotherapy completion rates(97.1%vs 88.5%,P=0.014)and longer catheter dwelling time(189.5±45.3 days vs 162.7±53.8 days,P<0.001).CONCLUSION Image pre-measurement combined with intracavitary electrocardiogram positioning technology in arm port implantation for colorectal cancer patients can significantly improve catheter tip positioning accuracy,reduce operation time and X-ray exposure.展开更多
Myocardial infarction(MI)is one of the leading causes of death globally among cardiovascular diseases,necessitating modern and accurate diagnostics for cardiac patient conditions.Among the available functional diagnos...Myocardial infarction(MI)is one of the leading causes of death globally among cardiovascular diseases,necessitating modern and accurate diagnostics for cardiac patient conditions.Among the available functional diagnostic methods,electrocardiography(ECG)is particularly well-known for its ability to detect MI.However,confirming its accuracy—particularly in identifying the localization of myocardial damage—often presents challenges in practice.This study,therefore,proposes a new approach based on machine learning models for the analysis of 12-lead ECG data to accurately identify the localization of MI.In particular,the learning vector quantization(LVQ)algorithm was applied,considering the contribution of each ECG lead in the 12-channel system,which obtained an accuracy of 87%in localizing damaged myocardium.The developed model was tested on verified data from the PTB database,including 445 ECG recordings from both healthy individuals and MI-diagnosed patients.The results demonstrated that the 12-lead ECG system allows for a comprehensive understanding of cardiac activities in myocardial infarction patients,serving as an essential tool for the diagnosis of myocardial conditions and localizing their damage.A comprehensive comparison was performed,including CNN,SVM,and Logistic Regression,to evaluate the proposed LVQ model.The results demonstrate that the LVQ model achieves competitive performance in diagnostic tasks while maintaining computational efficiency,making it suitable for resource-constrained environments.This study also applies a carefully designed data pre-processing flow,including class balancing and noise removal,which improves the reliability and reproducibility of the results.These aspects highlight the potential application of the LVQ model in cardiac diagnostics,opening up prospects for its use along with more complex neural network architectures.展开更多
Background:The electrocardiogram(ECG)is a valuable,noninvasive tool for monitoring heart-related conditions,providing critical insights.However,the interpretation of ECG data alongside patient information demands subs...Background:The electrocardiogram(ECG)is a valuable,noninvasive tool for monitoring heart-related conditions,providing critical insights.However,the interpretation of ECG data alongside patient information demands substantial medical expertise and resources.While deep learning methods help streamline this process,they often fall short in integrating patient data with ECG readings and do not provide the nuanced clinical suggestions and insights necessary for accurate diagnosis.Methods:Although recent advancements in multi-modal large language modeling have propelled their application scope beyond the natural language processing domain,their applicability to ECG processing remains largely unexplored,partly due to the lack of text–ECG data.To this end,we develop ECG-Language Model(ECG-LM),the first multi-modal large language model able to process natural language and understand ECG signals.The model employs a specialized ECG encoder that transforms raw ECG signals into a high-dimensional feature space,which is then aligned with the textual feature space derived from the large language model.To address the scarcity of text–ECG data,we generated text–ECG pairs by leveraging detailed ECG pattern descriptions from medical guidelines,creating a robust dataset for pre-training ECG-LM.Additionally,we fine-tune ECG-LM with public clinical conversation datasets and build an additional supervised fine-tuning dataset based on real clinical data from the hospital,aiming to provide a more comprehensive and customized user experience.Results:ECG-LM outperforms existing few-shot and zero-shot solutions in cardiovascular disease detection across all 3 tasks(diagnostic,rhythm,and form)while also demonstrating strong potential in ECG-related question answering.Conclusions:The results across various tasks demonstrate that ECG-LM effectively captures the intricate features of ECGs,showcasing its versatility in applications such as disease prediction and advanced question answering.展开更多
Cardiovascular diseases(CVDs)continue to present a leading cause ofmortalityworldwide,emphasizing the importance of early and accurate prediction.Electrocardiogram(ECG)signals,central to cardiac monitoring,have increa...Cardiovascular diseases(CVDs)continue to present a leading cause ofmortalityworldwide,emphasizing the importance of early and accurate prediction.Electrocardiogram(ECG)signals,central to cardiac monitoring,have increasingly been integratedwithDeep Learning(DL)for real-time prediction of CVDs.However,DL models are prone to performance degradation due to concept drift and to catastrophic forgetting.To address this issue,we propose a realtime CVDs prediction approach,referred to as ADWIN-GFR that combines Convolutional Neural Network(CNN)layers,for spatial feature extraction,with Gated Recurrent Units(GRU),for temporal modeling,alongside adaptive drift detection and mitigation mechanisms.The proposed approach integratesAdaptiveWindowing(ADWIN)for realtime concept drift detection,a fine-tuning strategy based on Generative Features Replay(GFR)to preserve previously acquired knowledge,and a dynamic replay buffer ensuring variance,diversity,and data distribution coverage.Extensive experiments conducted on the MIT-BIH arrhythmia dataset demonstrate that ADWIN-GFR outperforms standard fine-tuning techniques,achieving an average post-drift accuracy of 95.4%,amacro F1-score of 93.9%,and a remarkably low forgetting score of 0.9%.It also exhibits an average drift detection delay of 12 steps and achieves an adaptation gain of 17.2%.These findings underscore the potential of ADWIN-GFR for deployment in real-world cardiac monitoring systems,including wearable ECG devices and hospital-based patient monitoring platforms.展开更多
Cardiovascular diseases are the world’s leading cause of death;therefore cardiac health of the human heart has been a fascinating topic for decades.The electrocardiogram(ECG)signal is a comprehensive non-invasive met...Cardiovascular diseases are the world’s leading cause of death;therefore cardiac health of the human heart has been a fascinating topic for decades.The electrocardiogram(ECG)signal is a comprehensive non-invasive method for determining cardiac health.Various health practitioners use the ECG signal to ascertain critical information about the human heart.In this article,swarm intelligence approaches are used in the biomedical signal processing sector to enhance adaptive hybrid filters and empirical wavelet transforms(EWTs).At first,the white Gaussian noise is added to the input ECG signal and then applied to the EWT.The ECG signals are denoised by the proposed adaptive hybrid filter.The honey badge optimization(HBO)algorithm is utilized to optimize the EWT window function and adaptive hybrid filter weight parameters.The proposed approach is simulated by MATLAB 2018a using the MIT-BIH dataset with white Gaussian,electromyogram and electrode motion artifact noises.A comparison of the HBO approach with recursive least square-based adaptive filter,multichannel least means square,and discrete wavelet transform methods has been done in order to show the efficiency of the proposed adaptive hybrid filter.The experimental results show that the HBO approach supported by EWT and adaptive hybrid filter can be employed efficiently for cardiovascular signal denoising.展开更多
Electrocardiograms (ECG) of Eremias multiocellata were studied at 5-35℃ in body temperature. Electrocardiogram wave intervals (R-R,P-R,QRS,T-P,and R-T) shortened while heart rate increased with the increasing of bod...Electrocardiograms (ECG) of Eremias multiocellata were studied at 5-35℃ in body temperature. Electrocardiogram wave intervals (R-R,P-R,QRS,T-P,and R-T) shortened while heart rate increased with the increasing of body temperature. The average heart rate was 14.6/min at 5℃,whereas it was 201/min at 35℃. The duration of wave intervals of ECG and the heart rate were related significantly to the body temperature (P<0.001). Among the components of a cardiac cycle the cardiac rest period (TP intervals) and the atria-ventricular conduction time (PR interval) were affected mostly by body temperature. In the other hand the ventricular depolarization and repolarization (QRS and R-T intervals) were relatively less affected by the body temperature. The increasing of heart rate with body temperature was mainly caused by the shortening of ECG wave intervals,and the T-P interval (the cardiac rest period) was shortened more noticeably than other intervals.展开更多
文摘Computer analysis of electrocardiograms(ECGs)was introduced more than 50 years ago,with the aim to improve efficiency and clinical workflow.[1,2]However,inaccuracies have been documented in the literature.[3,4]Research indicates that emergency department(ED)clinician interruptions occur every 4-10 min,which is significantly more common than in other specialties.[5]This increases the cognitive load and error rates and impacts patient care and clinical effi ciency.[1,2,5]De-prioritization protocols have been introduced in certain centers in the United Kingdom(UK),removing the need for clinician ECG interpretation where ECGs have been interpreted as normal by the machine.
基金Supported by The National Research Foundation of Ukraine,No.2023.04/0094。
文摘BACKGROUND As cardiovascular mortality continues to increase globally,percutaneous coronary intervention(PCI)with stent placement stands out as a cutting-edge and highly effective treatment for severe cardiovascular diseases.However,the inherent invasiveness of any endovascular procedure introduces the risk of coronary vessel and myocardial damage.AIM To evaluate the utility of a novel electrocardiographic metric in detecting subtle myocardial injuries after coronary stenting.METHODS This investigation was conducted in 2021 at the Kyiv Heart Institute of the Ministry of Healthcare of Ukraine.The study involved 23 patients who underwent PCI,each subjected to a meticulous preoperative examination.A paired measurement approach was employed,encompassing 3-minutes electrocardiogram(ECG)recordings both before and several hours following the operation,using a compact ECG device.Each pair of ECG underwent a thorough analysis,scrutinizing 240 primary and computed ECG parameters.RESULTS The analysis delineated a distinct subgroup exhibiting significant myocardial damage post-stenting.This subgroup was characterized by an older average age and more stents than their counterparts.Notably,a concurrent reduction in the psychoemotional state index was observed alongside the ECG alterations in these patients,suggesting a correlation between myocardial damage and psychoemotional distress.Introducing a new electrocardiographic index has illuminated the often-subtle myocardial damage incurred during PCI.CONCLUSION The newly devised electrocardiographic metric is a significant advancement in the early detection of myocardial damage following PCI,able to capture not only physiological but also psychoemotional changes.
基金Supported by National Natural Science Foundation of China,No.82170327 and No.82370332Tianjin Key Medical Discipline(Specialty)Construction Project,No.TJYXZDXK-029A.
文摘With the rapid advancement and widespread adoption of new artificial intelligence(AI)technologies,personalized medicine and more accurate diagnosis using medical imaging are now possible.Among its many applications,AI has shown remarkable potential in the analysis of electrocardiograms(ECGs),which provide essential insights into the electrical activity of the heart and allowing early detection of ischemic heart disease(IHD).Notably,single-lead ECG(SLECG)analysis has emerged as a key focus in recent research due to its potential for widespread and efficient screening.This editorial focuses on the latest research progress of AI-enabled SLECG utilized in the diagnosis of IHD.
文摘Objective:To investigate the effect of 12-lead electrocardiogram and 24-hour dynamic electrocardiogram in detecting pacemaker dysfunction and changes in cardiac function indexes in patients with pacemaker implantation.Methods:A total of 136 patients with pacemaker implantation in the First Clinical Medical College of Three Gorges University,Institute of Cardiovascular Disease of Three Gorges University and Yicang Central People’s Hospital from January 2023 to December 2024 were selected as the research objects.All patients received 12-lead electrocardiogram and 24-hour holter 3–14 days after implantation.Results:The overall detection rate of various types of pacemaker dysfunction by Holter was significantly higher than that by conventional ECG(27.21%vs.5.15%,χ^(2)=24.402,P<0.001).The overall arrhythmia detection rate of Holter was significantly higher than that of conventional electrocardiogram(57.35%vs.10.29%,χ^(2)=67.277,P<0.001).The time domain indexes of heart rate variability obtained by 24-hour continuous monitoring of Holter were significantly improved compared with those of conventional electrocardiogram(P<0.05).Conclusions:Compared with 12-lead electrocardiogram,24-hour holter monitoring can more accurately detect pacemaker dysfunction and arrhythmia in patients with pacemaker implantation,and provide more comprehensive data of heart rate variability,which is helpful for clinicians to better evaluate the cardiac function of patients and adjust treatment plans.
基金Supported by the Affiliated Hospital of Xuzhou Medical University,No.2024ZH04Xuzhou Municipal Science and Technology Bureau,No.KC23282.
文摘BACKGROUND Arm-implanted totally implantable venous access devices(peripherally inserted central catheter port)have become an important vascular access for colorectal cancer chemotherapy,but traditional anatomical landmark positioning techniques have issues with inaccurate positioning and high complication rates.AIM To evaluate the clinical value of image pre-measurement combined with intracavitary electrocardiogram(IC-ECG)positioning technology in arm port implantation for colorectal cancer patients.METHODS A retrospective analysis was conducted on 216 colorectal cancer patients who received arm port implantation in our hospital from January 2024 to December 2024.Patients were divided into an experimental group(image pre-measurement combined with IC-ECG positioning technology,n=103)and a control group(traditional anatomical landmark positioning technique,n=113).Technical success rate,operation time,catheter tip position accuracy,number of intraoperative catheter adjustments,X-ray exposure time,and postoperative complication rates were compared between the two groups.RESULTS The experimental group demonstrated superior outcomes compared to the control group across all key measures.Technical success rate was higher(98.4%vs 92.7%,P<0.05)with significantly reduced operation time(23.6±5.2 minutes vs 31.5±7.8 minutes,P<0.01).Catheter tip positioning accuracy improved substantially(97.6%vs 85.4%,P=0.002)while X-ray exposure time decreased by 71.8%(5.3±2.1 seconds vs 18.7±4.5 seconds,P<0.001).Threemonth complication rates were markedly lower in the experimental group(4.1%vs 14.6%,P=0.008),including significant reductions in catheter-related thrombosis(0.8%vs 4.9%),displacement(1.6%vs 5.7%),and occlusion(1.6%vs 4.1%).Multivariate analysis identified traditional technique as the strongest risk factor(odds ratio=4.27,P<0.001),while the combined IC-ECG approach was protective(odds ratio=0.34 for displacement,P=0.018).Long-term outcomes favored the experimental group with higher chemotherapy completion rates(97.1%vs 88.5%,P=0.014)and longer catheter dwelling time(189.5±45.3 days vs 162.7±53.8 days,P<0.001).CONCLUSION Image pre-measurement combined with intracavitary electrocardiogram positioning technology in arm port implantation for colorectal cancer patients can significantly improve catheter tip positioning accuracy,reduce operation time and X-ray exposure.
基金funded by the Ministry of Science and Higher Education of the Republic of Kazakhstan,grant numbers AP14969403 and AP23485820.
文摘Myocardial infarction(MI)is one of the leading causes of death globally among cardiovascular diseases,necessitating modern and accurate diagnostics for cardiac patient conditions.Among the available functional diagnostic methods,electrocardiography(ECG)is particularly well-known for its ability to detect MI.However,confirming its accuracy—particularly in identifying the localization of myocardial damage—often presents challenges in practice.This study,therefore,proposes a new approach based on machine learning models for the analysis of 12-lead ECG data to accurately identify the localization of MI.In particular,the learning vector quantization(LVQ)algorithm was applied,considering the contribution of each ECG lead in the 12-channel system,which obtained an accuracy of 87%in localizing damaged myocardium.The developed model was tested on verified data from the PTB database,including 445 ECG recordings from both healthy individuals and MI-diagnosed patients.The results demonstrated that the 12-lead ECG system allows for a comprehensive understanding of cardiac activities in myocardial infarction patients,serving as an essential tool for the diagnosis of myocardial conditions and localizing their damage.A comprehensive comparison was performed,including CNN,SVM,and Logistic Regression,to evaluate the proposed LVQ model.The results demonstrate that the LVQ model achieves competitive performance in diagnostic tasks while maintaining computational efficiency,making it suitable for resource-constrained environments.This study also applies a carefully designed data pre-processing flow,including class balancing and noise removal,which improves the reliability and reproducibility of the results.These aspects highlight the potential application of the LVQ model in cardiac diagnostics,opening up prospects for its use along with more complex neural network architectures.
基金sponsored by Tsinghua-Toyota Joint Research Institute Inter-disciplinary Program.
文摘Background:The electrocardiogram(ECG)is a valuable,noninvasive tool for monitoring heart-related conditions,providing critical insights.However,the interpretation of ECG data alongside patient information demands substantial medical expertise and resources.While deep learning methods help streamline this process,they often fall short in integrating patient data with ECG readings and do not provide the nuanced clinical suggestions and insights necessary for accurate diagnosis.Methods:Although recent advancements in multi-modal large language modeling have propelled their application scope beyond the natural language processing domain,their applicability to ECG processing remains largely unexplored,partly due to the lack of text–ECG data.To this end,we develop ECG-Language Model(ECG-LM),the first multi-modal large language model able to process natural language and understand ECG signals.The model employs a specialized ECG encoder that transforms raw ECG signals into a high-dimensional feature space,which is then aligned with the textual feature space derived from the large language model.To address the scarcity of text–ECG data,we generated text–ECG pairs by leveraging detailed ECG pattern descriptions from medical guidelines,creating a robust dataset for pre-training ECG-LM.Additionally,we fine-tune ECG-LM with public clinical conversation datasets and build an additional supervised fine-tuning dataset based on real clinical data from the hospital,aiming to provide a more comprehensive and customized user experience.Results:ECG-LM outperforms existing few-shot and zero-shot solutions in cardiovascular disease detection across all 3 tasks(diagnostic,rhythm,and form)while also demonstrating strong potential in ECG-related question answering.Conclusions:The results across various tasks demonstrate that ECG-LM effectively captures the intricate features of ECGs,showcasing its versatility in applications such as disease prediction and advanced question answering.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R196)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Cardiovascular diseases(CVDs)continue to present a leading cause ofmortalityworldwide,emphasizing the importance of early and accurate prediction.Electrocardiogram(ECG)signals,central to cardiac monitoring,have increasingly been integratedwithDeep Learning(DL)for real-time prediction of CVDs.However,DL models are prone to performance degradation due to concept drift and to catastrophic forgetting.To address this issue,we propose a realtime CVDs prediction approach,referred to as ADWIN-GFR that combines Convolutional Neural Network(CNN)layers,for spatial feature extraction,with Gated Recurrent Units(GRU),for temporal modeling,alongside adaptive drift detection and mitigation mechanisms.The proposed approach integratesAdaptiveWindowing(ADWIN)for realtime concept drift detection,a fine-tuning strategy based on Generative Features Replay(GFR)to preserve previously acquired knowledge,and a dynamic replay buffer ensuring variance,diversity,and data distribution coverage.Extensive experiments conducted on the MIT-BIH arrhythmia dataset demonstrate that ADWIN-GFR outperforms standard fine-tuning techniques,achieving an average post-drift accuracy of 95.4%,amacro F1-score of 93.9%,and a remarkably low forgetting score of 0.9%.It also exhibits an average drift detection delay of 12 steps and achieves an adaptation gain of 17.2%.These findings underscore the potential of ADWIN-GFR for deployment in real-world cardiac monitoring systems,including wearable ECG devices and hospital-based patient monitoring platforms.
文摘Cardiovascular diseases are the world’s leading cause of death;therefore cardiac health of the human heart has been a fascinating topic for decades.The electrocardiogram(ECG)signal is a comprehensive non-invasive method for determining cardiac health.Various health practitioners use the ECG signal to ascertain critical information about the human heart.In this article,swarm intelligence approaches are used in the biomedical signal processing sector to enhance adaptive hybrid filters and empirical wavelet transforms(EWTs).At first,the white Gaussian noise is added to the input ECG signal and then applied to the EWT.The ECG signals are denoised by the proposed adaptive hybrid filter.The honey badge optimization(HBO)algorithm is utilized to optimize the EWT window function and adaptive hybrid filter weight parameters.The proposed approach is simulated by MATLAB 2018a using the MIT-BIH dataset with white Gaussian,electromyogram and electrode motion artifact noises.A comparison of the HBO approach with recursive least square-based adaptive filter,multichannel least means square,and discrete wavelet transform methods has been done in order to show the efficiency of the proposed adaptive hybrid filter.The experimental results show that the HBO approach supported by EWT and adaptive hybrid filter can be employed efficiently for cardiovascular signal denoising.
文摘Electrocardiograms (ECG) of Eremias multiocellata were studied at 5-35℃ in body temperature. Electrocardiogram wave intervals (R-R,P-R,QRS,T-P,and R-T) shortened while heart rate increased with the increasing of body temperature. The average heart rate was 14.6/min at 5℃,whereas it was 201/min at 35℃. The duration of wave intervals of ECG and the heart rate were related significantly to the body temperature (P<0.001). Among the components of a cardiac cycle the cardiac rest period (TP intervals) and the atria-ventricular conduction time (PR interval) were affected mostly by body temperature. In the other hand the ventricular depolarization and repolarization (QRS and R-T intervals) were relatively less affected by the body temperature. The increasing of heart rate with body temperature was mainly caused by the shortening of ECG wave intervals,and the T-P interval (the cardiac rest period) was shortened more noticeably than other intervals.
