The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnos...The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnosis increases the patient’s chances of recovery.However,issues like overfitting and inconsistent accuracy across datasets remain challenges.In a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib detection.The aim was to create a robust detection mechanism that consistently performs well.Metrics such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for evaluation.The findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated categories.It demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib detection.These insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG signals.The comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib detection.Moreover,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.展开更多
Regulation of gut microbiota and its impact on human health is the theme of intensive research.The incidence and prevalence of atrial fibrillation(AF)are continuously escalating as the global population ages and chron...Regulation of gut microbiota and its impact on human health is the theme of intensive research.The incidence and prevalence of atrial fibrillation(AF)are continuously escalating as the global population ages and chronic disease survival rates increase;however,the mechanisms are not entirely clarified.It is gaining awareness that alterations in the assembly,structure,and dynamics of gut microbiota are intimately engaged in the AF progression.Owing to advancements in next-generation sequencing technologies and computational strategies,researchers can explore novel linkages with the genomes,transcriptomes,proteomes,and metabolomes through parallel meta-omics approaches,rendering a panoramic view of the culture-independent microbial investigation.In this review,we summarized the evidence for a bidirectional correlation between AF and the gut microbiome.Furthermore,we proposed the concept of“gut-immune-heart”axis and addressed the direct and indirect causal roots between the gut microbiome and AF.The intricate relationship was unveiled to generate innovative microbiota-based preventive and therapeutic interventions,which shed light on a definite direction for future experiments.展开更多
Background: Atrial fibrillation commonly occurs following cardiac surgery, particularly after coronary artery bypass grafting. Magnesium, known for its stabilizing effect on cell membranes, has shown promise in preven...Background: Atrial fibrillation commonly occurs following cardiac surgery, particularly after coronary artery bypass grafting. Magnesium, known for its stabilizing effect on cell membranes, has shown promise in preventing postoperative atrial fibrillation. This study aimed to assess the impact of intravenous magnesium infusion in preventing atrial fibrillation after off-pump coronary artery bypass grafting, where maintaining stable cell membranes is crucial in averting this complication. Methods: A cross-sectional study was conducted at the Department of Cardiac Surgery, Bangabandhu Sheikh Mujib Medical University, from March 2020 to February 2022. Sixty-six patients who underwent off-pump coronary artery bypass grafting were enrolled and divided into two groups. Group A (n = 33) received intravenous magnesium sulfate (10 mmol/2.47gm) for three days after surgery, while Group B (n = 33) did not receive magnesium sulfate. Postoperative atrial fibrillation occurrence in the Intensive Care Unit (ICU) within three days after surgery was evaluated using convenient sampling. Statistical analysis was performed with SPSS version 26.0, utilizing independent Student’s t-test for continuous data and Chi-square and Fisher’s exact test for categorical data. A p-value of ≤0.05 was considered statistically significant. Results: No significant differences in age or gender were observed between the two groups. Group B exhibited significantly lower magnesium levels than Group A on the 0<sup>th</sup>, 1<sup>st</sup>, 2<sup>nd</sup>, and 3<sup>rd</sup> days post-surgery. Additionally, Group B experienced a higher incidence of postoperative atrial fibrillation, longer ICU stays, and two mortalities. The study did not detect any adverse effects associated with magnesium infusion. Conclusion: It has been demonstrated that administering magnesium intravenously after off-pump coronary artery bypass grafting can lower the chances of developing atrial fibrillation. This demonstrates the potential advantages of using magnesium as a preventative measure for postoperative atrial fibrillation in such cases.展开更多
We investigate the use of complex network similarity for the identification of atrial fibrillation. The similarity of the network is estimated via the joint recurrence plot and Hamming distance. Firstly, we transform ...We investigate the use of complex network similarity for the identification of atrial fibrillation. The similarity of the network is estimated via the joint recurrence plot and Hamming distance. Firstly, we transform multi-electrodes epicardium signals recorded from dogs into the recurrence complex network. Then, we extract features representing its similarity. Finally, epicardium signals are classified utilizing the classification and regression tree with extracted features. The method is validated using 1000 samples including 500 atrial fibrillation cases and 500 normal sinus ones. The sensitivity, specificity and accuracy of the identification are 98.2%, 98.8% and 98.5% respectively. This experiment indicates that our approach may lay a foundation for the prediction of the onset of atrial fibrillation.展开更多
Objectives: To assess the impact of atrial fibrillation on stroke severity and short-term (1 month) mortality. Materials and Methods: Totally 200 patients admitted to Ain Shams University Specialized Hospital were rec...Objectives: To assess the impact of atrial fibrillation on stroke severity and short-term (1 month) mortality. Materials and Methods: Totally 200 patients admitted to Ain Shams University Specialized Hospital were recruited and diagnosed clinically to have acute ischemic stroke within 3 days. Patients with hemorrhagic infarctions were excluded. History taking about previous heart disease was taken, full general and neurological examinations were done. Full metabolic profile, full cardiac investigations, carotid duplex, MRI brain stroke protocol with initial clinical evaluation and after 1 month re-evaluation using (NIHSS ) scale. Results: All patients underwent transthoracic echocardiography which revealed absence of “A” wave corresponding to atrial fibrillation in 33 patients (16.5%). Those Patients with atrial fibrillation had a median NIHSS score of 11.00 with IQR of 6.00 - 18.50 at admission and 6.00 with IQR of 2.00 - 14.50 after one month. Patients with atrial fibrillation showed significantly higher NIHSS at admission than patients in sinus rhythm, P < 0.05. Magnetic resonance imaging findings showed that MRA showed significant intracranial vessel stenosis in 117 (79.1%) patients. 51 (34.4%) patients had lacunar infarction, 65 (43.9%) patients had partial anterior circulation infarction, 25 (16.2%) patients had posterior circulation infarction and 7 (4.7%) patients had total anterior circulation infarction. 111 (75%) patients showed leucoaraiosis. Conclusion: Atrial fibrillation was found not to have significantly statistical effect on stroke severity and short term mortality.展开更多
Multiple wavelet hypothesis and fibrillatory conduction are believed to be atrial fibrillation's pathogenesis. Radio frequency ablation(RFA) technique, a therapy for atrial fibrillation(AF), applies radio frequenc...Multiple wavelet hypothesis and fibrillatory conduction are believed to be atrial fibrillation's pathogenesis. Radio frequency ablation(RFA) technique, a therapy for atrial fibrillation(AF), applies radio frequency(RF) energy to targeted tissue to make it transmural. Research on AF ablation has already been conducted in China. Currently, there are single-electrode and dual-electrode ablation electrodes. It is discovered that the latter can reduce the treatment time and maintain the ablation shape of the tissue. Clinical application has shown that it has become the first-line treatment option for part of indications patients with AF.展开更多
文摘The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnosis increases the patient’s chances of recovery.However,issues like overfitting and inconsistent accuracy across datasets remain challenges.In a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib detection.The aim was to create a robust detection mechanism that consistently performs well.Metrics such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for evaluation.The findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated categories.It demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib detection.These insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG signals.The comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib detection.Moreover,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.
基金National Key Research and Development Program of China(2022YFC2303100)Central Plains Talent Program-Central Plains Youth Top Talents,the Young and Middle-aged Academic Leaders of Henan Provincial Health Commission(HNSWJW-2022013)+1 种基金Funding for Scientific Research and Innovation Team of the First Affiliated Hospital of Zhengzhou University(QNCXTD2023002 and ZYCXTD2023002)Research Project of Jinan Microecological Biomedicine Shandong Laboratory(JNL-2022001A and JNL-2022015B).
文摘Regulation of gut microbiota and its impact on human health is the theme of intensive research.The incidence and prevalence of atrial fibrillation(AF)are continuously escalating as the global population ages and chronic disease survival rates increase;however,the mechanisms are not entirely clarified.It is gaining awareness that alterations in the assembly,structure,and dynamics of gut microbiota are intimately engaged in the AF progression.Owing to advancements in next-generation sequencing technologies and computational strategies,researchers can explore novel linkages with the genomes,transcriptomes,proteomes,and metabolomes through parallel meta-omics approaches,rendering a panoramic view of the culture-independent microbial investigation.In this review,we summarized the evidence for a bidirectional correlation between AF and the gut microbiome.Furthermore,we proposed the concept of“gut-immune-heart”axis and addressed the direct and indirect causal roots between the gut microbiome and AF.The intricate relationship was unveiled to generate innovative microbiota-based preventive and therapeutic interventions,which shed light on a definite direction for future experiments.
文摘Background: Atrial fibrillation commonly occurs following cardiac surgery, particularly after coronary artery bypass grafting. Magnesium, known for its stabilizing effect on cell membranes, has shown promise in preventing postoperative atrial fibrillation. This study aimed to assess the impact of intravenous magnesium infusion in preventing atrial fibrillation after off-pump coronary artery bypass grafting, where maintaining stable cell membranes is crucial in averting this complication. Methods: A cross-sectional study was conducted at the Department of Cardiac Surgery, Bangabandhu Sheikh Mujib Medical University, from March 2020 to February 2022. Sixty-six patients who underwent off-pump coronary artery bypass grafting were enrolled and divided into two groups. Group A (n = 33) received intravenous magnesium sulfate (10 mmol/2.47gm) for three days after surgery, while Group B (n = 33) did not receive magnesium sulfate. Postoperative atrial fibrillation occurrence in the Intensive Care Unit (ICU) within three days after surgery was evaluated using convenient sampling. Statistical analysis was performed with SPSS version 26.0, utilizing independent Student’s t-test for continuous data and Chi-square and Fisher’s exact test for categorical data. A p-value of ≤0.05 was considered statistically significant. Results: No significant differences in age or gender were observed between the two groups. Group B exhibited significantly lower magnesium levels than Group A on the 0<sup>th</sup>, 1<sup>st</sup>, 2<sup>nd</sup>, and 3<sup>rd</sup> days post-surgery. Additionally, Group B experienced a higher incidence of postoperative atrial fibrillation, longer ICU stays, and two mortalities. The study did not detect any adverse effects associated with magnesium infusion. Conclusion: It has been demonstrated that administering magnesium intravenously after off-pump coronary artery bypass grafting can lower the chances of developing atrial fibrillation. This demonstrates the potential advantages of using magnesium as a preventative measure for postoperative atrial fibrillation in such cases.
文摘We investigate the use of complex network similarity for the identification of atrial fibrillation. The similarity of the network is estimated via the joint recurrence plot and Hamming distance. Firstly, we transform multi-electrodes epicardium signals recorded from dogs into the recurrence complex network. Then, we extract features representing its similarity. Finally, epicardium signals are classified utilizing the classification and regression tree with extracted features. The method is validated using 1000 samples including 500 atrial fibrillation cases and 500 normal sinus ones. The sensitivity, specificity and accuracy of the identification are 98.2%, 98.8% and 98.5% respectively. This experiment indicates that our approach may lay a foundation for the prediction of the onset of atrial fibrillation.
文摘Objectives: To assess the impact of atrial fibrillation on stroke severity and short-term (1 month) mortality. Materials and Methods: Totally 200 patients admitted to Ain Shams University Specialized Hospital were recruited and diagnosed clinically to have acute ischemic stroke within 3 days. Patients with hemorrhagic infarctions were excluded. History taking about previous heart disease was taken, full general and neurological examinations were done. Full metabolic profile, full cardiac investigations, carotid duplex, MRI brain stroke protocol with initial clinical evaluation and after 1 month re-evaluation using (NIHSS ) scale. Results: All patients underwent transthoracic echocardiography which revealed absence of “A” wave corresponding to atrial fibrillation in 33 patients (16.5%). Those Patients with atrial fibrillation had a median NIHSS score of 11.00 with IQR of 6.00 - 18.50 at admission and 6.00 with IQR of 2.00 - 14.50 after one month. Patients with atrial fibrillation showed significantly higher NIHSS at admission than patients in sinus rhythm, P < 0.05. Magnetic resonance imaging findings showed that MRA showed significant intracranial vessel stenosis in 117 (79.1%) patients. 51 (34.4%) patients had lacunar infarction, 65 (43.9%) patients had partial anterior circulation infarction, 25 (16.2%) patients had posterior circulation infarction and 7 (4.7%) patients had total anterior circulation infarction. 111 (75%) patients showed leucoaraiosis. Conclusion: Atrial fibrillation was found not to have significantly statistical effect on stroke severity and short term mortality.
基金the Shanghai Science and Technology Research Projects Fund(No.11441900200)the National Key Technology R&D Program(No.2012BAI15B07)
文摘Multiple wavelet hypothesis and fibrillatory conduction are believed to be atrial fibrillation's pathogenesis. Radio frequency ablation(RFA) technique, a therapy for atrial fibrillation(AF), applies radio frequency(RF) energy to targeted tissue to make it transmural. Research on AF ablation has already been conducted in China. Currently, there are single-electrode and dual-electrode ablation electrodes. It is discovered that the latter can reduce the treatment time and maintain the ablation shape of the tissue. Clinical application has shown that it has become the first-line treatment option for part of indications patients with AF.
文摘心房颤动(Atrial Fibrillation,AF)是一种常见的心律失常疾病,会严重影响患者的日常生活,甚至引发包括中风、血栓堵塞等的并发症。因此,对房颤早期准确的诊疗非常重要。但是,算法对大规模的心率数据运行效率较低,因此房颤的诊断仍面临一定的挑战。针对上述挑战,文章提出了一种新型的基于深度学习的房颤检测架构BiLSTM-Attention。该架构包含双向长短期记忆网络(Bi-directional Long Short-Term Memory,BiLSTM)和Attention机制。在BiLSTM-Attention中,BiLSTM用于访问心率序列中的前项和后项数据,Attention机制用于给数据特征分配不同的权重,最终通过顶部全连接层分类房颤。在MIT-BIHAF数据库上对该架构进行了交叉验证,取得了98.54%的准确率。实验结果表明,BiLSTM-Attention架构在测试数据集上表现良好,为进一步探索智慧医疗迈出了坚实的一步。
