Journal of electrocardiology最新文献

{"title":"High precision ECG digitization using artificial intelligence","authors":"Anthony Demolder MD, PhD ,&nbsp;Viera Kresnakova MSc, PhD ,&nbsp;Michal Hojcka MSc, PhD ,&nbsp;Vladimir Boza MSc, PhD ,&nbsp;Andrej Iring MSc ,&nbsp;Adam Rafajdus MEng ,&nbsp;Simon Rovder MInf ,&nbsp;Timotej Palus MSc ,&nbsp;Martin Herman ,&nbsp;Felix Bauer BSc ,&nbsp;Viktor Jurasek ,&nbsp;Robert Hatala MD, PhD ,&nbsp;Jozef Bartunek MD, PhD ,&nbsp;Boris Vavrik MSc ,&nbsp;Robert Herman MD, PhD","doi":"10.1016/j.jelectrocard.2025.153900","DOIUrl":"10.1016/j.jelectrocard.2025.153900","url":null,"abstract":"<div><h3>Background</h3><div>Digitization of paper-based electrocardiograms (ECGs) enables long-term preservation, fast transmission, and advanced analysis. Traditional methods for digitizing ECGs face significant challenges, particularly in real-world scenarios with varying image quality. State-of-the-art solutions often require manual input and are limited by their dependence on high-quality scans and standardized layouts.</div></div><div><h3>Methods</h3><div>This study introduces a fully automated, deep learning-based approach for high precision ECG digitization. In the normalization phase, a standardized grid structure is detected, and image distortions are corrected. Next, the reconstruction phase uses deep learning techniques to extract and digitize the leads, followed by post-processing to refine the signal. This approach was evaluated using the publicly available PMcardio ECG Image Database (PM-ECG-ID), comprising 6000 ECG images reflecting diverse real-world scenarios and smartphone-based image acquisitions. Performance was assessed using Pearson's correlation coefficient (PCC), root mean squared error (RMSE), and signal-to-noise ratio (SNR).</div></div><div><h3>Results</h3><div>The ECG digitization solution demonstrated an average PCC consistently exceeding 0.91 across all leads, SNR above 12.5 dB and RMSE below 0.10 mV. The time to ECG digitization was consistently less than 7 s. The average failure rate was 6.62 % across leads, with most failures occurring under extreme conditions such as severe blurring or significant image degradation. The solution maintained robust performance even under challenging scenarios, such as low-resolution images, distorted grids, and overlapping signals.</div></div><div><h3>Conclusion</h3><div>Our deep learning-based approach for ECG digitization delivers high-precision signals, effectively addressing real-world challenges. This fully automated method enhances the accessibility and utility of ECG data by enabling convenient digitization via smartphones, unlocking advanced AI-driven analysis.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153900"},"PeriodicalIF":1.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electrocardiographic abnormalities in chagasic patients compared to the general population: A systematic review with updated meta-analysis","authors":"Bruno Felipe Santos de Oliveira ,&nbsp;Cárita Victória Carvalho de Santana ,&nbsp;Luiz Filippe Vago Pereira,&nbsp;Gabriele Eliza Assis,&nbsp;Ana Beatriz Cazé,&nbsp;Jackson Pedro Barros-Pereira,&nbsp;Rafaela Góes Bispo,&nbsp;Roque Aras Júnior","doi":"10.1016/j.jelectrocard.2025.153893","DOIUrl":"10.1016/j.jelectrocard.2025.153893","url":null,"abstract":"<div><h3>Introduction</h3><div>Chagas disease (CD) remains a serious public health issue. It can progress from the acute phase to the chronic phase, manifesting as a cardiomyopathy with some typical electrocardiogram abnormality.</div></div><div><h3>Objectives</h3><div>This systematic review with meta-analysis aims to evaluate the overall prevalence of cardiac arrhythmias in patients with CD and discriminative values to clinical and epidemiological variables for specific arrhythmias.</div></div><div><h3>Methods</h3><div>Articles that included the prevalence of electrocardiographic abnormalities in CD compared to other groups were searched in the following databases: MEDLINE/PubMed, Embase and Cochrane Library. The results obtained were pooled in meta-analyses</div></div><div><h3>Results</h3><div>A total of 322.608 participants from 88 studies were included. The meta-analyses with single electrocardiographic changes showed a significant association with positive CD serology compared to non-chagasic individuals, (OR: 2.86 95 % CI 2.53; 3.23; I² = 85 %). Significant associations were found to complete right bundle branch block [CRBBB], CRBBB + left anterior fascicular block [LAFB], first-degree atrioventricular block [AVB], incomplete right bundle branch block [IRBBB], second-degree AVB, LAFB, supraventricular ectopic beats, third-degree AVB, ventricular ectopic beats and atrial fibrillation or flutter. For the presence of a single electrocardiographic alterations, the discriminative capacity variables showed: sensitivity 0.511 (0.505, 0.517), specificity 0.622 (0.620, 0.624), Positive Predictive Value (PPV) 0.101 (0.099, 0.103), Negative Predictive Value (NPV) 0.939 (0.937, 0.940), Positive Likelihood Ratio (PLR) 1.352 (1.334, 1.370) and Negative Likelihood Ratio (NLR) 0.786 (0.776, 0.797).</div></div><div><h3>Conclusion</h3><div>Our findings show a significant association between CD and several electrocardiographic abnormalities, which highlights the need for ongoing surveillance and targeted therapeutic interventions to improve clinical outcomes for patients with chagasic cardiomyopathy.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153893"},"PeriodicalIF":1.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Narrow complex tachycardia with cycle length alternans","authors":"Swasthi S. Kumar MD,&nbsp;Sudipta Mondal MD, DM,&nbsp;Jyothi Vijay MD, DM,&nbsp;Narayanan Namboodiri MD, DM","doi":"10.1016/j.jelectrocard.2025.153898","DOIUrl":"10.1016/j.jelectrocard.2025.153898","url":null,"abstract":"<div><div>An elderly lady without any comorbidities, presented with paroxysmal palpitations and was documented to have an adenosine-responsive narrow complex tachycardia (NCT). Baseline electrocardiogram (ECG) showed normal sinus rhythm with no preexcitation. Tachycardia ECG showed a regularly irregular short RP NCT at the rate of around 150/min with alternating cycle lengths of 320 ms and 360 ms.</div><div>What is the likely diagnosis?</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153898"},"PeriodicalIF":1.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ECG based human activity-specific cardiac pattern detection using machine-learning and deep-learning models","authors":"Kusum Tara ,&nbsp;Md Hasibul Islam ,&nbsp;Takenao Sugi","doi":"10.1016/j.jelectrocard.2025.153899","DOIUrl":"10.1016/j.jelectrocard.2025.153899","url":null,"abstract":"<div><div>Monitoring cardiac patterns under relaxed, cognitive, and physical stressors is crucial for identifying early signs of cardiac stress or abnormalities. This study analyzes ECG signals recorded during diverse activities such as sitting, math-reasoning, walking, jogging, and hand-biking, simulating these stressors. A deep-learning image-based convolutional neural network (CNN) model utilizing bispectrum-based contours was proposed to classify cardiac patterns by capturing the non-linear dynamics of cardiac behavior. Two approaches were employed: a feature-based random forest (RF) machine-learning model using time-domain, frequency-domain, and statistical features, and an image-based CNN model utilizing Continuous wavelet transform (CWT) based scalograms and bispectrum-based contours. Feature selection techniques, including Pearson correlation and least absolute shrinkage and selection operator (LASSO) regularization, were used to identify significant features for RF model input. RF model achieved 96.80 % accuracy and an F1-score of 92.22 %. CNN model outperformed it, achieving 98.44 % accuracy and a 96.11 % F1-score with CWT scalograms, and 99.16 % accuracy and a 97.89 % F1-score with bispectrum-based contours. Key features such as stress index and SNS-to-PNS ratio increased with cognitive and physical stressors, highlighting autonomic responses. Based on the results of analysis, the proposed CNN model with bispectrum-based contours demonstrated superior accuracy and reliability, showcasing significant potential for monitoring cardiac functions across diverse activities.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153899"},"PeriodicalIF":1.3,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Irregular rhythm with wide-QRS complexes and repolarization abnormalities in the emergency department: A nightmare ECG","authors":"Antonino Micari M.D,&nbsp;Giulia Cavolina M.D,&nbsp;Pasquale Crea M.D. Ph.D","doi":"10.1016/j.jelectrocard.2025.153896","DOIUrl":"10.1016/j.jelectrocard.2025.153896","url":null,"abstract":"<div><div>We present the ECG findings of a 49-year-old woman recorded in the emergency department, which reveal a wide-QRS, irregular rhythm. The ECG shows a broad terminal wave in the right precordial leads, along with a convex ST segment elevation, and is associated with a right axis deviation. While the initial presentation may appear complex, several diagnostic possibilities must be considered, as each could suggest a distinct management for this clinical case.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153896"},"PeriodicalIF":1.3,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electrocardiogram markers of all-cause dementia and dementia subtypes","authors":"Jonas L. Isaksen ,&nbsp;Claus Graff ,&nbsp;Jørgen K. Kanters","doi":"10.1016/j.jelectrocard.2025.153897","DOIUrl":"10.1016/j.jelectrocard.2025.153897","url":null,"abstract":"","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153897"},"PeriodicalIF":1.3,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring mortality representation and the impact of COVID-19 in Modena: insights from “An ECG-based machine-learning approach for mortality risk assessment in a large European population”","authors":"P. Giovanardi ,&nbsp;C. Vernia ,&nbsp;M. Doneda ,&nbsp;on behalf of the whole research team","doi":"10.1016/j.jelectrocard.2025.153890","DOIUrl":"10.1016/j.jelectrocard.2025.153890","url":null,"abstract":"","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153890"},"PeriodicalIF":1.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new VCG signal compression technique based on discrete Karhunen-Loeve expansion and tunable quality wavelet transform","authors":"Ronak Vimal,&nbsp;A. Kumar,&nbsp;Aditya Tiwari","doi":"10.1016/j.jelectrocard.2025.153894","DOIUrl":"10.1016/j.jelectrocard.2025.153894","url":null,"abstract":"<div><div>This paper presents a novel two-stage compression technique for vectorcardiogram (VCG) signals, combining Discrete Karhunen-Loeve (K-L) Expansion and Tunable Q-Factor Wavelet Transform (TQWT). In the first stage, VCG signals undergo discrete K-L expansion and a secondary rotation to reduce variance caused by physiological factors, such as respiration and varying heart orientations among patients. This process effectively simplifies the dataset by leveraging eigenvector-based transformation, while standardizing the data across different VCG records. In the second stage, the standardized data is processed using TQWT, with finely tuned parameters (Q-factor of 4, redundancy factor of 1.2, and 6 stages), followed by quantization and Run-Length Encoding (RLE). The RLE method efficiently compresses the long sequences of zeros generated during the process, further enhancing the data reduction. The proposed method was rigorously evaluated using the PTB Diagnostic ECG Database, demonstrating remarkable compression efficiency. When compared with standard approaches like Discrete K-L Transform and Discrete Cosine Transform (DCT), the method achieved a superior average compression ratio of 15.43. Key evaluation metrics further highlight its efficacy, including an average Percent Root Difference (PRD) of 7.39 %, Fidelity of 99.72 %, Peak Signal-to-Noise Ratio (PSNR) of 37.38 dB, and a Quality Score (QS) of 2.13 %. Moreover, the method's rapid processing speed of 0.076 s per record makes it well-suited for real-time applications. This innovative approach provides an effective solution for VCG signal compression, enhancing the storage and transmission efficiency, while preserving high signal fidelity for clinical use.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"89 ","pages":"Article 153894"},"PeriodicalIF":1.3,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine-learning computer-assisted ECG analysis to predict myocardial fibrosis in patients with hypertrophic cardiomyopathy","authors":"Dafne Viliani ,&nbsp;Alberto Cecconi ,&nbsp;Beatriz López-Melgar ,&nbsp;Álvaro Montes Muñiz ,&nbsp;Pablo Martínez-Vives ,&nbsp;Sofia Cuenca ,&nbsp;Pablo Lozano Jiménez ,&nbsp;Yolanda Carrión García ,&nbsp;Carmen De Benavides ,&nbsp;Susana Hernández ,&nbsp;Paloma Caballero ,&nbsp;Guillermo J Ortega ,&nbsp;Luis Jesús Jiménez-Borreguero ,&nbsp;Fernando Alfonso","doi":"10.1016/j.jelectrocard.2025.153892","DOIUrl":"10.1016/j.jelectrocard.2025.153892","url":null,"abstract":"<div><h3>Aims</h3><div>The application of computer assisted techniques to the electrocardiogram (ECG) analysis is showing promising results. Our main aim was to apply a machine learning approach to the ECG analysis in patients with hypertrophic cardiomyopathy (HCM), to identify predictors of macroscopic fibrosis, a marker of ventricular arrhythmias and sudden cardiac death.</div></div><div><h3>Methods</h3><div>136 patients diagnosed with HCM were included. The main clinical and echocardiographic variables were collected. All patients underwent cardiac magnetic resonance (CMR) and the presence of macroscopic fibrosis was assessed on late gadolinium enhancement (LGE) sequences. From the 12‑lead digitized ECGs of each patient 468 morphological variables were quantified with a dedicated software.</div></div><div><h3>Results</h3><div>The mean age of the population was 62.6 ± 14.1 years, and in 82 patients (60.3 %) LGE was observed. After preselecting significant ECG variables from the univariate analysis, a multivariate regression was performed, obtaining a predictive model composed of five parameters: the duration of the QRS in I, the duration of the QT interval in V3<em>,</em> the duration of the T wave in aVF<em>,</em> the peak-to peak amplitude of the QRS in V1, and the amplitude of the S wave in V4. A random forest algorithm confirmed that the duration of the QRS was the strongest predictor of fibrosis.</div></div><div><h3>Conclusion</h3><div>In patients with HCM the addition of a computer-assisted ECG analysis can help to identify predictors of LGE, being the duration of the QRS the strongest one. Our findings can be especially useful when access to CMR is scarce, to select patients at higher risk.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"90 ","pages":"Article 153892"},"PeriodicalIF":1.3,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing postoperative arrhythmia diagnosis: An observational study of atrial ECG recording techniques","authors":"Matija Bakoš ,&nbsp;Dražen Belina ,&nbsp;Toni Matić ,&nbsp;Tomo Svaguša","doi":"10.1016/j.jelectrocard.2025.153895","DOIUrl":"10.1016/j.jelectrocard.2025.153895","url":null,"abstract":"<div><div>Temporary atrial and ventricular electrodes are frequently utilized for diagnosing and treating cardiac arrhythmias in children during the early postoperative period following cardiac surgery. Traditionally, lead I electrodes (right and left hand) are connected to atrial wires to facilitate arrhythmia diagnosis, resulting in high atrial signal display. In the manuscript we described an alternative method involving connecting atrial wires to the right and left leg electrodes, leaving lead I without the atrial ECG signal. This approach serves as a reference lead for postoperative arrhythmia detection, offering potential diagnostic clarity in selected clinical scenarios.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"89 ","pages":"Article 153895"},"PeriodicalIF":1.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}