Ludovico Lazzari , Stefano Donzelli , Carmine Marallo , Alessandra Tordini , Federica Di Meo , Chiara Marini , Vincenzo Pace , Pasquale Notarstefano , Giuseppe Ambrosio , Giovanni Carreras
{"title":"Development and validation of an ECG algorithm based on lead V3 morphology to determine the origin of outflow tract ventricular arrhythmias","authors":"Ludovico Lazzari , Stefano Donzelli , Carmine Marallo , Alessandra Tordini , Federica Di Meo , Chiara Marini , Vincenzo Pace , Pasquale Notarstefano , Giuseppe Ambrosio , Giovanni Carreras","doi":"10.1016/j.ijcard.2025.133446","DOIUrl":"10.1016/j.ijcard.2025.133446","url":null,"abstract":"<div><h3>Introduction</h3><div>Preoperatively distinguishing the origin of outflow tract ventricular arrhythmias (OTVAs) exhibiting a precordial transition around V3 is essential for effectively planning the ablation procedure; nonetheless, this proves challenging since neighboring anatomical structures exhibit similar VA morphologies. Several diagnostic criteria analyzing leads V1 and V2 have been proposed to overcome this limitation, whose accuracy has been reviewed; recently, interest has shifted to V3. We conducted a thorough analysis of leads V1 to V3 to evaluate the diagnostic accuracy of existing criteria and to develop a novel diagnostic algorithm.</div></div><div><h3>Methods</h3><div>We analyzed the ECGs of 51 patients with OTVAs originating from either ventricle who underwent successful catheter ablation. The indices yielding greater accuracy (derivation cohort) were used to guide ablation in a subsequent validation cohort (<em>n</em> = 31).</div></div><div><h3>Results</h3><div>Among all ECG parameters, V3 R-wave percentage (V3R%) and duration index (V3Rd), calculated from amplitude and duration, respectively, demonstrated the highest AUC. A V3R% ≥50 % identified LVOT origin (sensitivity = 80.8 %, specificity = 96 %, PPV = 95.5 %, NPV = 82.8 %), while RVOT origin was associated with a V3Rd <50 % (sensitivity = 80 %, specificity = 96.2 %, PPV = 95.2 %, NPV = 83.3 %). Combining both indices into a two-step algorithm resulted in an overall accuracy of 88.23 % in the derivation cohort and 90.32 % in the validation cohort, showing higher specificity and sensitivity than criteria based on leads V1 and V2, as well as the transition zone index, and slightly higher accuracy than the V2S/V3R ratio.</div></div><div><h3>Conclusions</h3><div>The proposed algorithm accurately identifies the site of origin of OTVAs in most cases, potentially simplifying the ablation strategy more effectively than existing criteria.</div></div>","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"436 ","pages":"Article 133446"},"PeriodicalIF":3.2,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
David B. Olawade , Afeez A. Soladoye , Bolaji A. Omodunbi , Nicholas Aderinto , Ibrahim A. Adeyanju
{"title":"Comparative analysis of machine learning models for coronary artery disease prediction with optimized feature selection","authors":"David B. Olawade , Afeez A. Soladoye , Bolaji A. Omodunbi , Nicholas Aderinto , Ibrahim A. Adeyanju","doi":"10.1016/j.ijcard.2025.133443","DOIUrl":"10.1016/j.ijcard.2025.133443","url":null,"abstract":"<div><h3>Background</h3><div>Coronary artery disease (CAD) is a major global cause of death, necessitating early, accurate prediction for better management. Traditional diagnostics are often invasive, costly, and less accessible. Machine learning (ML) offers a non-invasive alternative, but high-dimensional data and redundancy can hinder performance. This study integrates Bald Eagle Search Optimization (BESO) for feature selection to improve CAD classification using multiple ML models.</div></div><div><h3>Methods</h3><div>Two publicly available datasets, Framingham (4200 instances, 15 features) and <em>Z</em>-Alizadeh Sani (304 instances, 55 features), were used. The former predicts 10-year CAD risk, while the latter classifies current CAD status. Data preprocessing included missing value imputation, normalization, categorical encoding, and class balancing using SMOTE. We employed a 70–30 holdout validation strategy with empirical hyperparameter optimization, providing more reliable final model development than cross-validation. BESO was applied to optimize feature selection, significantly outperforming traditional methods like RFE and LASSO. Six ML models—KNN, logistic regression, SVM with linear, polynomial, and RBF kernels, and random forest—were trained and evaluated.</div></div><div><h3>Results</h3><div>Random Forest achieved the highest performance across both datasets. In the Framingham dataset, RF recorded 90 % accuracy, significantly outperforming traditional clinical risk scores (71–73 % accuracy). Linear models performed better on the <em>Z</em>-Alizadeh Sani dataset (90 % accuracy) than Framingham (66 %), indicating dataset characteristics strongly influence model efficacy.</div></div><div><h3>Conclusion</h3><div>BESO significantly enhances feature selection, with RF emerging as the optimal classifier (92 % accuracy) and substantially outperforming established clinical risk scores. This study highlights the potential of AI-driven CAD diagnosis, supporting early detection and improved patient outcomes. Future work should focus on prospective validation and clinical implementation.</div></div>","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"436 ","pages":"Article 133443"},"PeriodicalIF":3.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Predicting endothelialization failure after LAA closure: Promise and limits of preprocedural TTE","authors":"Ibrahim Akin","doi":"10.1016/j.ijcard.2025.133447","DOIUrl":"10.1016/j.ijcard.2025.133447","url":null,"abstract":"","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"436 ","pages":"Article 133447"},"PeriodicalIF":3.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Chronotropic incompetence and the importance of cardiopulmonary exercise testing following myocardial infarction","authors":"Garett J. Griffith","doi":"10.1016/j.ijcard.2025.133445","DOIUrl":"10.1016/j.ijcard.2025.133445","url":null,"abstract":"","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"437 ","pages":"Article 133445"},"PeriodicalIF":3.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144208494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reply to “nail biting in adults with congenital heart disease: Genetic predisposition or educational influence?”","authors":"Masahiko Umei","doi":"10.1016/j.ijcard.2025.133450","DOIUrl":"10.1016/j.ijcard.2025.133450","url":null,"abstract":"","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"436 ","pages":"Article 133450"},"PeriodicalIF":3.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hongyan Xie , Xin Zhao , Nan Zhang , Jiayi Liu , Guang Yang , Yunshan Cao , Jialin Xu , Lei Xu , Zhonghua Sun , Zhaoying Wen , Senchun Chai , Dongting Liu
{"title":"Machine learning–based hemodynamics quantitative assessment of pulmonary circulation using computed tomographic pulmonary angiography","authors":"Hongyan Xie , Xin Zhao , Nan Zhang , Jiayi Liu , Guang Yang , Yunshan Cao , Jialin Xu , Lei Xu , Zhonghua Sun , Zhaoying Wen , Senchun Chai , Dongting Liu","doi":"10.1016/j.ijcard.2025.133457","DOIUrl":"10.1016/j.ijcard.2025.133457","url":null,"abstract":"<div><h3>Background</h3><div>Pulmonary hypertension (pH) is a malignant pulmonary circulation disease. Right heart catheterization (RHC) is the gold standard procedure for quantitative evaluation of pulmonary hemodynamics. Accurate and noninvasive quantitative evaluation of pulmonary hemodynamics is challenging due to the limitations of currently available assessment methods.</div></div><div><h3>Methods</h3><div>Patients who underwent computed tomographic pulmonary angiography (CTPA) and RHC examinations within 2 weeks were included. The dataset was randomly divided into a training set and a test set at an 8:2 ratio. A radiomic feature model and another two-dimensional (2D) feature model aimed to quantitatively evaluate of pulmonary hemodynamics were constructed. The performance of models was determined by calculating the mean squared error, the intraclass correlation coefficient (ICC) and the area under the precision-recall curve (AUC-PR) and performing Bland–Altman analyses.</div></div><div><h3>Results</h3><div>345 patients: 271 patients with PH (mean age 50 ± 17 years, 93 men) and 74 without PH (mean age 55 ± 16 years, 26 men) were identified. The predictive results of pulmonary hemodynamics of radiomic feature model integrating 5 2D features and other 30 radiomic features were consistent with the results from RHC, and outperformed another 2D feature model. The radiomic feature model exhibited moderate to good reproducibility to predict pulmonary hemodynamic parameters (ICC reached 0.87). In addition, pH can be accurately identified based on a classification model (AUC-PR =0.99).</div></div><div><h3>Conclusion</h3><div>This study provides a noninvasive method for comprehensively and quantitatively evaluating pulmonary hemodynamics using CTPA images, which has the potential to serve as an alternative to RHC, pending further validation.</div></div>","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"437 ","pages":"Article 133457"},"PeriodicalIF":3.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144198999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Non-vitamin K antagonist oral anticoagulants (NOACs) and risk of spontaneous intracranial hemorrhage in patients with ischemic stroke: An analysis using Taiwan's National Health Insurance Research Database","authors":"Kay-Chun Chang , Yu-Wen Cheng , Yu-Hone Hsu , Yang-Yi Chen , Wei-Chuan Liao","doi":"10.1016/j.ijcard.2025.133449","DOIUrl":"10.1016/j.ijcard.2025.133449","url":null,"abstract":"<div><h3>Background</h3><div>The impact of non-vitamin K antagonist oral anticoagulants (NOACs) on the treatment of ischemic stroke remains unclear. This study aimed to compare the risk of spontaneous intracranial hemorrhage (sICH) in ischemic stroke patients using different NOACs versus warfarin.</div></div><div><h3>Methods</h3><div>We conducted a retrospective cohort study using Taiwan's National Health Insurance Research Database from 2011 to 2019. Adults with ischemic stroke and no prior sICH or gastrointestinal (GI) bleeding before anticoagulant initiation were included. Patients were grouped by anticoagulant type. Outcomes included sICH, GI bleeding, in-hospital mortality, and all-cause mortality. Adjusted hazard ratios (aHRs) and odds ratios (aORs) were estimated using Cox and logistic regression models, respectively.</div></div><div><h3>Results</h3><div>Among 3783 patients, those using dabigatran or edoxaban alone, or in combination with other NOACs, had a reduced risk of in-hospital mortality (aOR = 0.52, 0.52, and 0.57, respectively). Patients using rivaroxaban or apixaban alone had a lower risk of gastrointestinal bleeding (aHR = 0.68 and 0.64, respectively). Patients using rivaroxaban, dabigatran, or edoxaban alone, or in combination, had a lower risk of all-cause mortality (aHR = 0.78, 0.54, 0.49, and 0.51, respectively). In contrast, patients using apixaban alone or in combination with other NOACs had a higher risk of sICH (aHR = 1.38 and 2.12, respectively). Short-term NOAC use (≤30 days) was associated with increased sICH risk, whereas long-term use (>90 days) of rivaroxaban, dabigatran, or apixaban was associated with a reduced risk.</div></div><div><h3>Conclusion</h3><div>Appropriate selection and long-term use (over 90 days) of NOACs for ischemic stroke patients may improve outcomes.</div></div>","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"436 ","pages":"Article 133449"},"PeriodicalIF":3.2,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144191756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Krishna Jaipal, Shorrem Naeem, Syed Aaraiz Ul Hassan
{"title":"“Letter to the editor: “Prognostic value of angiography-derived microcirculatory resistance in patients undergoing rotational Atherectomy”","authors":"Krishna Jaipal, Shorrem Naeem, Syed Aaraiz Ul Hassan","doi":"10.1016/j.ijcard.2025.133435","DOIUrl":"10.1016/j.ijcard.2025.133435","url":null,"abstract":"","PeriodicalId":13710,"journal":{"name":"International journal of cardiology","volume":"436 ","pages":"Article 133435"},"PeriodicalIF":3.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144186912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}