Cardiology最新文献

{"title":"Real-World Evidence: Integrating Machine Learning with Real-World Big Data for Predictive Analytics in Healthcare.","authors":"Nicolas Vecchio","doi":"10.1159/000541861","DOIUrl":"https://doi.org/10.1159/000541861","url":null,"abstract":"","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142589415","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":"Signal-guided multitask learning for myocardial infarction classification using images of electrocardiogram.","authors":"Bo Eun Park, Byungeun Shon, Jungrae Cho, Min-Su Jung, Jong Sung Park, Myeong Seop Kim, Eunkyu Lee, Hyohun Choi, Hyuk Kyoon Park, Yoon Jung Park, Hong Nyun Kim, Namkyun Kim, Myung Hwan Bae, Jang Hoon Lee, Dong Heon Yang, Hun Sik Park, Yongkeun Cho, Sungmoon Jeong, Se Yong Jang","doi":"10.1159/000542399","DOIUrl":"https://doi.org/10.1159/000542399","url":null,"abstract":"<p><strong>Introduction: </strong>The diagnosis of myocardial infarction (MI) needs to be swift and accurate, but definitively diagnosing it based on the first test encountered in clinical practice, the electrocardiogram (ECG), is not an easy task. The purpose of the study is to develop a deep learning (DL) algorithm using multitask learning method to differentiate patients experiencing MI from those without coronary artery disease using image-based ECG data.</p><p><strong>Methods: </strong>A DL model was developed based on 11,227 ECG images. We developed a new ECG interpretation algorithm through signal-guided multitask learning, building on a previously published single-task algorithm. The utility of this model was evaluated by testing 51 physicians in interpreting ECGs with and without the assistance of the DL model.</p><p><strong>Results: </strong>The proposed model demonstrated superior performance, achieving 90.56% accuracy, 83.82% sensitivity, 93.02% specificity, 81.44% precision, and an F1 score of 82.61% in discriminating MI ECG. Overall, the median accuracy of ECG interpretation improved from 62% to 68% with the DL algorithm. Trainees and specialists in internal medicine experienced significant accuracy increases (60% to 66% for trainees, 72% to 80% for specialists). In the MI group, NSTEMI accuracy was notably lower than STEMI (33% vs. 80%, p < 0.001), but the DL algorithm improved interpretative capabilities in both NSTEMI and STEMI.</p><p><strong>Conclusions: </strong>Signal-guided multitask DL algorithm demonstrated superior performance compared with previous single-task algorithm. The DL algorithm supports the physicians' decision discriminating MI ECGs from non-MI ECGs. The improvement was consistent in subgroups of STEMI and NSTEMI.</p>","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142589417","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":"FIBRINOLYSIS WAS REPLACED BEFORE IT WAS UNDERSTOOD.","authors":"Victor Gurewich, David Segarnick","doi":"10.1159/000542197","DOIUrl":"https://doi.org/10.1159/000542197","url":null,"abstract":"<p><p>Introduction Fibrinolysis is often wrongly believed to be due to tissue plasminogen activator (tPA) alone. Instead, both endogenous plasminogen activators are required, but only a mini bolus of tPA is needed to initiate fibrinolysis. This is due to tPA's unique high fibrin affinity binding site located on the fibrin D-domain. Both activators are present in all normal plasma, consistent with both being involved in biological fibrinolysis, which is also the model for optimal therapeutic fibrinolysis. Methods This uses a sequential combination of a 5 mg mini bolus of tPA followed by an infusion of proUK (40 mg/hr) for 90 minutes. This treatment is both highly effective and free of side effects. Results By contrast, due to a misunderstanding of fibrinolysis, tPA is often administered alone. This requires doses of 90-100 mg of tPA over 60 minutes, which is neither very effective nor safe, due to a risk of bleeding complications from the lysis of hemostatic fibrin by tPA's fibrin affinity. Due to this problem, fibrinolysis was replaced by interventional procedures, like percutaneous coronary intervention (PCI), which is much slower, limited to clots larger than the catheter, but is generously reimbursed by third party payers.</p>","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142575033","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":"The Need for New Data on Left Ventricular Remodeling and the Crucial Role of Ejection Time for our daily clinical practice.","authors":"Erwan Donal, Adrien Al Wazzan","doi":"10.1159/000542317","DOIUrl":"https://doi.org/10.1159/000542317","url":null,"abstract":"","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142575036","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":"Optimal QT correction formula for older Chinese: Guangzhou Biobank Cohort Study.","authors":"Wen Bo Tian, Wei Sen Zhang, Chao Qiang Jiang, Xiang Yi Liu, Feng Zhu, Ya Li Jin, Tong Zhu, Tai Hing Lam, Kar Keung Cheng, Lin Xu","doi":"10.1159/000542238","DOIUrl":"https://doi.org/10.1159/000542238","url":null,"abstract":"<p><strong>Introduction: </strong>To identify the optimal QT correction formula for generating corrected QT (QTc) and cutoffs for prolonged QTc, and examine the associations with mortality and cardiovascular disease (CVD) in older Chinese.</p><p><strong>Methods: </strong>A prospective study included 24,611 Chinese aged 50+ years and without CVD at 2003-2008 from Guangzhou Biobank Cohort Study. QT interval was corrected by Bazett, Fridericia, Framingham and Hodges formulas. The slope and R2 of the QTc and heart rate regression were used to determine the optimal correction formula. The 95th percentile of QTc was used to defined prolonged QTc. Cox regression was used to examine associations of prolonged QTc with mortality and CVD. The net reclassification index was calculated to assess risk reclassification.</p><p><strong>Results: </strong>During an average follow-up of 15.3 years, 5,261 deaths and 5,539 CVD occurred. Optimal heart correction was observed for the Hodges formula, and Bazett formula performed the worst. Prolonged QTc corrected by Fridericia, Framingham and Hodges formulas had similar association strength with all-cause mortality, CVD mortality and incident CVD (especially coronary heart disease, myocardial infarction and ischemic stroke), with hazard ratios approximately being 1.25, 1.40 and 1.15, respectively. They also improved risk reclassification for all-cause mortality, CVD mortality and incident CVD by approximately 5%, 10% and 6%, respectively. However, prolonged QTc corrected by Bazett formula was not associated with incident CVD and did not improve risk reclassification.</p><p><strong>Conclusions: </strong>Hodges formula outperformed other formulas for heart rate correction. Fridericia, Framingham and Hodges formulas can be used for death and cardiovascular risk prediction.</p>","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142543869","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 Predictive Models for Mortality in Heart Failure Patients with Clostridioides Difficile Infection.","authors":"Stephan Peronard Mayntz","doi":"10.1159/000542319","DOIUrl":"https://doi.org/10.1159/000542319","url":null,"abstract":"","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142521074","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":"Deep Learning-Based Method for Rapid 3D Whole-Heart Modeling in Congenital Heart Disease: Correspondence.","authors":"Hinpetch Daungsupawong, Viroj Wiwanitkit","doi":"10.1159/000542318","DOIUrl":"https://doi.org/10.1159/000542318","url":null,"abstract":"","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142521073","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":"Associations between Chest Pain, Diagnosis, and Clinical Outcome in Patients Hospitalized with Acute Dyspnea: Data from the ACE 2 Study.","authors":"Rahul Bhatnagar, Kristian Berge, Arne Didrik Høiseth, Torbjørn Omland, Magnus Nakrem Lyngbakken, Helge Røsjø","doi":"10.1159/000541897","DOIUrl":"10.1159/000541897","url":null,"abstract":"<p><strong>Introduction: </strong>Patients hospitalized due to dyspnea sometimes also report concomitant chest pain. Whether co-existing chest pain in patients with acute dyspnea associates with specific diagnosis and clinical outcome is not known.</p><p><strong>Method: </strong>We included 313 patients admitted to Akershus University Hospital with acute dyspnea and asked the patients directly on hospital admission whether they had experienced chest pain during the last 24 h. We examined the associations between chest pain and (1) diagnosis of the index hospitalization and (2) clinical outcome during follow-up. The diagnosis for the index hospitalization was adjudicated as acute heart failure (HF) or non-HF etiology of acute dyspnea by two experts working independently. Non-HF patients were further sub-grouped into chronic obstructive pulmonary disease (COPD) or non-COPD etiology.</p><p><strong>Results: </strong>In total, 143 patients were admitted with acute HF (46% of the population), 83 patients with COPD (26% of the population), and 87 patients with non-HF, non-COPD-related dyspnea (28% of the population). Ninety-six patients (31%) with acute dyspnea reported chest pain during the last 24 h prior to hospital admission. The prevalence of chest pain was not statistically different for patients who were hospitalized with acute HF (n = 42, 44%), acute exacerbation of COPD (n = 22, 23%), or non-HF, non-COPD-related dyspnea (n = 32, 33%), p > 0.05 for all comparisons between groups. During median of 823 days follow-up, 114 patients died (36%). Patients with dyspnea and concomitant chest pain did not have different outcome compared to patients with dyspnea and no chest pain (log-rank test: p = 0.09). Chest pain prior to admission was neither associated with all-cause mortality in any of the adjudicated diagnosis groups.</p><p><strong>Conclusions: </strong>Chest pain was reported in 31% of patients hospitalized with acute dyspnea but the prevalence did not differ according to adjudicated diagnosis. Patients with dyspnea and chest pain did not have worse outcome compared to patients with dyspnea and no chest pain.</p>","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458565","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":"Long-Term Outcome of Patients with Atrial Fibrillation and High Risk of Stroke Treated with Oral Anticoagulation or Left Atrial Appendage Occlusion: A Cardinality Matched Analysis.","authors":"Thomas Gilhofer, Victoria Bokemeyer, Victor Schweiger, Mario Gehler, Jonathan Michel, Mi Chen, Alessandro Candreva, Linn Ryberg, Christian Templin, Barbara Stähli, Julia Stehli, Alexander Gotschy, Philipp Jakob, Frank Ruschitzka, Stefanie Aeschbacher, Philipp Krisai, Leo H Bonati, Moa Lina Haller, Nicolas Rodondi, Juerg Beer, Peter Ammann, Giorgio Moschovitis, Elia Rigamonti, Stefan Osswald, David Conen, Fabian Nietlispach, Ronald Karl Binder, Tobias Reichlin, Michael Kühne, Albert Markus Kasel","doi":"10.1159/000541907","DOIUrl":"10.1159/000541907","url":null,"abstract":"<p><strong>Introduction: </strong>Atrial fibrillation (AF) poses a significant risk of stroke. Left atrial appendage occlusion (LAAO) is an alternative for patients with contraindications to oral anticoagulation (OAC) or with high risk of bleeding. This study aims to compare the outcomes of LAAO versus conventional stroke prevention in high-risk AF-patients.</p><p><strong>Methods: </strong>This secondary analysis incorporates data from the prospective Swiss-AF and Beat-AF cohorts, and the Zurich LAAO Registry. Cardinality matching was performed to create two comparable cohorts: conventional treatment (92% OAC) and LAAO. The primary endpoint was a composite of stroke, cardiovascular (CV) death, and clinically relevant bleeding. Kaplan-Meier method with competing risk analysis was used.</p><p><strong>Results: </strong>Each group included 468 patients (age 76.4 [70.5, 82.0] years, 33% female). The LAAO group exhibited higher baseline bleeding risk (HAS BLED 2.0 [1.0-3.0] versus 3.0 [3.0-4.0]; p < 0.001). Median follow-up time: 6.0 (4.7-7.0) years in conventional treatment group and 4.0 (1.5-6.1) in LAAO group. No significant difference in the primary composite endpoint (HR 0.87, 95% CI: 0.72-1.06, p = 0.18), stroke risk (HR 1.14, 95% CI: 0.66-1.97, p = 0.64), or CV mortality (HR 1.08, 95% CI: 0.82-1.42, p = 0.60) was observed between groups. LAAO correlated with a significantly lower risk of clinically relevant bleeding (HR 0.61, 95% CI: 0.47-0.80, p < 0.001).</p><p><strong>Conclusion: </strong>In this cardinality matched analysis with long-term follow-up, LAAO showed similar stroke and CV death rates but lower clinically relevant bleeding risk compared to conventional therapy in high-risk AF-patients.</p>","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458566","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 Deep Learning-Based Method for Rapid 3D Whole-Heart Modeling in Congenital Heart Disease.","authors":"Haiping Huang, Yisheng Wu","doi":"10.1159/000541980","DOIUrl":"https://doi.org/10.1159/000541980","url":null,"abstract":"<p><strong>Introduction: </strong>This study aims to develop a deep learning-based method for generating three-dimensional heart mesh models for patients with congenital heart disease by integrating medical imaging and clinical diagnostic information.</p><p><strong>Methods: </strong>A deep learning model was trained using CT and cardiac MRI (CMR) images, along with clinical data from 110 patients. The web-based platform automatically outputs STL files for 3D printing and Unity 3D OBJ files for virtual reality (VR) applications upon uploading the medical images and diagnostic information. The models were tested on three congenital heart disease cases, with corresponding 3D printed and VR heart models generated.</p><p><strong>Results: </strong>The 3D printed and VR heart models received high praise from professional doctors for their anatomical accuracy and clarity. Evaluations indicated that the proposed method effectively and rapidly reconstructs complex congenital heart disease structures, proving useful for preoperative planning and diagnostic support.</p><p><strong>Conclusion: </strong>The 3D modeling approach has the potential to enhance the precision of surgical planning and diagnosis for congenital heart disease. Future studies should explore larger datasets and training models for different types of congenital heart disease to validate the model's broad applicability.</p>","PeriodicalId":9391,"journal":{"name":"Cardiology","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458564","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}