Hellenic Journal of Cardiology最新文献

{"title":"Clinical phenotypes and outcomes of patients with left ventricular thrombus: an unsupervised cluster analysis","authors":"Aloysius S.T. Leow ,&nbsp;Fang Qin Goh ,&nbsp;Benjamin Y.Q. Tan ,&nbsp;Jamie S.Y. Ho ,&nbsp;William K.F. Kong ,&nbsp;Roger S.Y. Foo ,&nbsp;Mark Y.Y. Chan ,&nbsp;Leonard L.L. Yeo ,&nbsp;Ping Chai ,&nbsp;A. Geru ,&nbsp;Tiong-Cheng Yeo ,&nbsp;Siew Pang Chan ,&nbsp;Xin Zhou ,&nbsp;Gregory Y.H. Lip ,&nbsp;Ching-Hui Sia","doi":"10.1016/j.hjc.2024.08.010","DOIUrl":"10.1016/j.hjc.2024.08.010","url":null,"abstract":"<div><h3>Background</h3><div>Left ventricular thrombus (LVT) can develop in a diverse group of patients with various underlying causes, resulting in divergent natural histories and trajectories with treatment. Our aim was to use cluster analysis to identify unique clinical profiles among patients with LVT and then compare their clinical characteristics, treatment strategies, and outcomes.</div></div><div><h3>Methods</h3><div>We conducted a retrospective study involving 472 patients with LVT whose data were extracted from a tertiary center's echocardiography database, from March 2011 to January 2021. We used the TwoStep cluster analysis method, examining 19 variables.</div></div><div><h3>Results</h3><div>Our analysis of the 472 patients with LVT revealed two distinct patient clusters. Cluster 1, comprising 247 individuals (52.3%), was characterized by younger patients with a lower incidence of traditional cardiovascular risk factors and relatively fewer comorbidities compared with Cluster 2. Most patients had LVT attributed to an underlying ischemic condition, with a larger proportion being due to post-acute myocardial infarction in Cluster 1 (68.8%), and due to ischemic cardiomyopathy in Cluster 2 (57.8%). Notably, patients in Cluster 2 exhibited a reduced likelihood of LVT resolution (hazard ratio [HR] 0.58, 95% confidence interval [CI] 0.44–0.77, <em>p</em> &lt; 0.001) and a higher risk of all-cause mortality (HR 2.27, 95% CI 1.43–3.60, <em>p</em> = 0.001). These associations persisted even after adjusting for variables such as anticoagulation treatment, the presence of left ventricular aneurysms, and specific LVT characteristics such as mobility, protrusion, and size.</div></div><div><h3>Conclusion</h3><div>Through TwoStep cluster analysis, we identified two distinct clinical phenotypes among patients with LVT, each distinguished by unique baseline clinical attributes and varying prognoses.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 65-74"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142114942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital twins: reimagining the future of cardiovascular risk prediction and personalised care","authors":"Katarzyna Dziopa ,&nbsp;Karim Lekadir ,&nbsp;Pim van der Harst ,&nbsp;Folkert W. Asselbergs","doi":"10.1016/j.hjc.2024.06.001","DOIUrl":"10.1016/j.hjc.2024.06.001","url":null,"abstract":"<div><div>The rapid evolution of highly adaptable and reusable artificial intelligence models facilitates the implementation of digital twinning and has the potential to redefine cardiovascular risk prevention. Digital twinning combines vast amounts of data from diverse sources to construct virtual models of an individual. Emerging artificial intelligence models, called generalist AI, enable the processing of different types of data, including data from electronic health records, laboratory results, medical texts, imaging, genomics, or graphs. Among their unprecedented capabilities are an easy adaptation of a model to previously unseen medical tasks and the ability to reason and explain output using precise medical language derived from scientific literature, medical guidelines, or knowledge graphs. The proposed combination of a digital twinning approach with generalist AI is a path to accelerate the implementation of precision medicine and enhance early recognition and prevention of cardiovascular disease. This proposed strategy may extend to other domains to advance predictive, preventive, and precision medicine and also boost health research discoveries.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 4-8"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141297319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From algorithms to clinical outcomes: how artificial intelligence shapes metaclinical medicine","authors":"Panos E. Vardas ,&nbsp;Charalambos Vlachopoulos","doi":"10.1016/j.hjc.2025.01.009","DOIUrl":"10.1016/j.hjc.2025.01.009","url":null,"abstract":"","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 1-3"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent diagnosis of Kawasaki disease from real-world data using interpretable machine learning models","authors":"Yifan Duan ,&nbsp;Ruiqi Wang ,&nbsp;Zhilin Huang ,&nbsp;Haoran Chen ,&nbsp;Mingkun Tang ,&nbsp;Jiayin Zhou ,&nbsp;Zhengyong Hu ,&nbsp;Wanfei Hu ,&nbsp;Zhenli Chen ,&nbsp;Qing Qian ,&nbsp;Haolin Wang","doi":"10.1016/j.hjc.2024.08.003","DOIUrl":"10.1016/j.hjc.2024.08.003","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to leverage real-world electronic medical record data to develop interpretable machine learning models for diagnosis of Kawasaki disease while also exploring and prioritizing the significant risk factors.</div></div><div><h3>Methods</h3><div>A comprehensive study was conducted on 4087 pediatric patients at the Children’s Hospital of Chongqing, China. The study collected demographic data, physical examination results, and laboratory findings. Statistical analyses were performed using IBM SPSS Statistics, Version 26.0. The optimal feature subset was used to develop intelligent diagnostic prediction models based on the Light Gradient Boosting Machine, Explainable Boosting Machine (EBM), Gradient Boosting Classifier (GBC), Fast Interpretable Greedy-Tree Sums, Decision Tree, AdaBoost Classifier, and Logistic Regression. Model performance was evaluated in three dimensions: discriminative ability via receiver operating characteristic curves, calibration accuracy using calibration curves, and interpretability through SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations).</div></div><div><h3>Results</h3><div>In this study, Kawasaki disease was diagnosed in 2971 participants. Analysis was conducted on 31 indicators, including red blood cell distribution width and erythrocyte sedimentation rate. The EBM model demonstrated superior performance relative to other models, with an area under the curve of 0.97, second only to the GBC model. Furthermore, the EBM model exhibited the highest calibration accuracy and maintained its interpretability without relying on external analytical tools such as SHAP and LIME, thus reducing interpretation biases. Platelet distribution width, total protein, and erythrocyte sedimentation rate were identified by the model as significant predictors for the diagnosis of Kawasaki disease.</div></div><div><h3>Conclusion</h3><div>This study used diverse machine learning models for early diagnosis of Kawasaki disease. The findings demonstrated that interpretable models such as EBM outperformed traditional machine learning models in terms of both interpretability and performance. Ensuring consistency between predictive models and clinical evidence is crucial for the successful integration of artificial intelligence into real-world clinical practice.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 38-48"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141918164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A complexity evaluation system for mitral valve repair based on preoperative echocardiographic and machine learning","authors":"Kun Zhu ,&nbsp;Hang Xu ,&nbsp;Shanshan Zheng ,&nbsp;Shui Liu ,&nbsp;Zhaoji Zhong ,&nbsp;Haining Sun ,&nbsp;Fujian Duan ,&nbsp;Sheng Liu","doi":"10.1016/j.hjc.2024.04.003","DOIUrl":"10.1016/j.hjc.2024.04.003","url":null,"abstract":"<div><h3>Background</h3><div>To develop a novel complexity evaluation system for mitral valve repair based on preoperative echocardiographic data and multiple machine learning algorithms.</div></div><div><h3>Methods</h3><div>From March 2021 to March 2023, 231 consecutive patients underwent mitral valve repair. Clinical and echocardiographic data were included in the analysis. The end points included immediate mitral valve repair failure (mitral replacement secondary to mitral repair failure) and recurrence regurgitation (moderate or greater mitral regurgitation [MR] before discharge). Various machine learning algorithms were used to establish the complexity evaluation system.</div></div><div><h3>Results</h3><div>A total of 231 patients were included in this study; the median ejection fraction was 66% (63–70%), and 159 (68.8%) patients were men. Mitral repair was successful in 90.9% (210 of 231) of patients. The linear support vector classification model has the best prediction results in training and test cohorts and the variables of age, A2 lesions, leaflet height, MR grades, and so on were risk factors for failure of mitral valve repair.</div></div><div><h3>Conclusion</h3><div>The linear support vector classification prediction model may allow the evaluation of the complexity of mitral valve repair. Age, A2 lesions, leaflet height, MR grades, and so on may be associated with mitral repair failure.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 25-37"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140830606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unraveling phenotypic heterogeneity in stanford type B aortic dissection patients through machine learning clustering analysis of cardiovascular CT imaging","authors":"Kun Liu ,&nbsp;Deyin Zhao ,&nbsp;Lvfan Feng ,&nbsp;Zhaoxuan Zhang ,&nbsp;Peng Qiu ,&nbsp;Xiaoyu Wu ,&nbsp;Ruihua Wang ,&nbsp;Azad Hussain ,&nbsp;Jamol Uzokov ,&nbsp;Yanshuo Han","doi":"10.1016/j.hjc.2024.08.006","DOIUrl":"10.1016/j.hjc.2024.08.006","url":null,"abstract":"<div><h3>Objective</h3><div>Aortic dissection remains a life-threatening condition necessitating accurate diagnosis and timely intervention. This study aimed to investigate phenotypic heterogeneity in patients with Stanford type B aortic dissection (TBAD) through machine learning clustering analysis of cardiovascular computed tomography (CT) imaging.</div></div><div><h3>Methods</h3><div>Electronic medical records were collected to extract demographic and clinical features of patients with TBAD. Exclusion criteria ensured homogeneity and clinical relevance of the TBAD cohort. Controls were selected on the basis of age, comorbidity status, and imaging availability. Aortic morphological parameters were extracted from CT angiography and subjected to K-means clustering analysis to identify distinct phenotypes.</div></div><div><h3>Results</h3><div>Clustering analysis revealed three phenotypes of patients with TBAD with significant correlations with population characteristics and dissection rates. This pioneering study used CT-based three-dimensional reconstruction to classify high-risk individuals, demonstrating the potential of machine learning in enhancing diagnostic accuracy and personalized treatment strategies. Recent advancements in machine learning have garnered attention in cardiovascular imaging, particularly in aortic dissection research. These studies leverage various imaging modalities to extract valuable features and information from cardiovascular images, paving the way for more personalized interventions.</div></div><div><h3>Conclusion</h3><div>This study provides insights into the phenotypic heterogeneity of patients with TBAD using machine learning clustering analysis of cardiovascular CT imaging. The identified phenotypes exhibit correlations with population characteristics and dissection rates, highlighting the potential of machine learning in risk stratification and personalized management of aortic dissection. Further research in this field holds promise for improving diagnostic accuracy and treatment outcomes in patients with aortic dissection.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 49-64"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141918167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection and classification of electrocardiography using hybrid deep learning models","authors":"Immaculate Joy Selvam ,&nbsp;Moorthi Madhavan ,&nbsp;Senthil Kumar Kumarasamy","doi":"10.1016/j.hjc.2024.08.011","DOIUrl":"10.1016/j.hjc.2024.08.011","url":null,"abstract":"<div><h3>Objective</h3><div>Electrocardiography (ECGs) has been a vital tool for cardiovascular disease (CVD) diagnosis, which visually depicts the heart's electrical activity. To enhance automatic classification between normal and diseased ECG, it is essential to extract consistent and qualitative features.</div></div><div><h3>Methods</h3><div>Precision of ECG classification through a hybrid Deep Learning (DL) approach leverages both Convolutional Neural Network (CNN) architecture and Variational Autoencoder (VAE) techniques. By combining these methods, we aim to achieve more accurate and robust ECG interpretation. The method is trained and tested over the PTB-XL dataset, which contains 21,799 with 12-lead ECGs from 18,869 patients, each spanning 10 s. The classification evaluation of five super-classes and 23 sub-classes of CVD, with the proposed CNN-VAE model is compared.</div></div><div><h3>Results</h3><div>The classification of various CVDs resulted in the highest accuracy of 98.51%, specificity of 98.12%, sensitivity of 97.9%, and F1-score of 97.95%. We have also achieved the minimum false positive and false negative rates of 2.07% and 1.87%, respectively, during validation. The results are validated upon the annotations given by individual cardiologists, who assigned potentially multiple ECG statements to each record.</div></div><div><h3>Conclusion</h3><div>When compared to other deep learning methods, our suggested CNN-VAE model performs significantly better in the testing phase. This study proposes a new architecture of combining CNN-VAE for CVD classification from ECG data, this can help clinicians to identify the disease earlier and carry out further treatment. The CNN-VAE model can better characterize input signals due to its hybrid architecture.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 75-84"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142114943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning for cardiac imaging: focus on myocardial diseases, a narrative review","authors":"Theodoros Tsampras ,&nbsp;Theodora Karamanidou ,&nbsp;Giorgos Papanastasiou ,&nbsp;Thanos G. Stavropoulos","doi":"10.1016/j.hjc.2024.12.002","DOIUrl":"10.1016/j.hjc.2024.12.002","url":null,"abstract":"<div><div>The integration of computational technologies into cardiology has significantly advanced the diagnosis and management of cardiovascular diseases. Computational cardiology, particularly, through cardiovascular imaging and informatics, enables a precise diagnosis of myocardial diseases utilizing techniques such as echocardiography, cardiac magnetic resonance imaging, and computed tomography. Early-stage disease classification, especially in asymptomatic patients, benefits from these advancements, potentially altering disease progression and improving patient outcomes. Automatic segmentation of myocardial tissue using deep learning (DL) algorithms improves efficiency and consistency in analyzing large patient populations. Radiomic analysis can reveal subtle disease characteristics from medical images and can enhance disease detection, enable patient stratification, and facilitate monitoring of disease progression and treatment response. Radiomic biomarkers have already demonstrated high diagnostic accuracy in distinguishing myocardial pathologies and promise treatment individualization in cardiology, earlier disease detection, and disease monitoring. In this context, this narrative review explores the current state of the art in DL applications in medical imaging (CT, CMR, echocardiography, and SPECT), focusing on automatic segmentation, radiomic feature phenotyping, and prediction of myocardial diseases, while also discussing challenges in integration of DL models in clinical practice.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 18-24"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142814865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Designing medical artificial intelligence systems for global use: focus on interoperability, scalability, and accessibility","authors":"Evangelos K. Oikonomou ,&nbsp;Rohan Khera","doi":"10.1016/j.hjc.2024.07.003","DOIUrl":"10.1016/j.hjc.2024.07.003","url":null,"abstract":"<div><div>Advances in artificial intelligence (AI) and machine learning systems promise faster, more efficient, and more personalized care. While many of these models are built on the premise of improving access to the timely screening, diagnosis, and treatment of cardiovascular disease, their validity and accessibility across diverse and international cohorts remain unknown. In this mini-review article, we summarize key obstacles in the effort to design AI systems that will be scalable, accessible, and accurate across distinct geographical and temporal settings. We discuss representativeness, interoperability, quality assurance, and the importance of vendor-agnostic data types that will be available to end-users across the globe. These topics illustrate how the timely integration of these principles into AI development is crucial to maximizing the global benefits of AI in cardiology.</div></div>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":"81 ","pages":"Pages 9-17"},"PeriodicalIF":2.7,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141725129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Role of Life's Essential 8 score in mediating socioeconomic status in the incidence of atrial fibrillation and heart failure: a population-based cohort study.","authors":"Nana Wang, Xiaocan Jia, Zhixing Fan, Chaojun Yang, Yuping Wang, Jingwen Fan, Chenyu Zhao, Yongli Yang, Xuezhong Shi","doi":"10.1016/j.hjc.2024.12.006","DOIUrl":"10.1016/j.hjc.2024.12.006","url":null,"abstract":"<p><strong>Objective: </strong>To assess whether the Life's Essential 8 (LE8) score mediates the association of socioeconomic status (SES) with atrial fibrillation (AF) and heart failure (HF).</p><p><strong>Methods: </strong>A total of 236,754 participants from the UK Biobank were included. SES was determined based on household income, education attainment, and employment status using latent class analysis. Cox regression was utilized to explore the association of SES with AF and HF after adjusting for age, sex, ethnicity, and alcohol status. Counterfactual mediation analysis was employed to calculate the mediation proportion of the LE8 score. Stratified analysis was conducted based on age and sex.</p><p><strong>Results: </strong>With a median of 13.61 years of follow-up, 14,635 cases of AF and 6878 cases of HF were documented. The HR (95% CI) of the total effect of SES on AF was 1.43 (1.36, 1.48). The indirect effect mediated by the LE8 score was 1.14 (1.13, 1.15), with the mediation proportion being 40.84 (36.97, 47.01)%. The total effect of SES on HF was 2.44 (2.26, 2.59). The indirect effect was 1.28 (1.25, 1.29), with the mediation proportion being 36.77 (34.59, 39.06)%. The mediation proportion was greater for AF in age < 60 years compared to age ≥ 60 years, and it was also higher in males than females for both AF and HF.</p><p><strong>Conclusion: </strong>Approximately one-third of the socioeconomic inequalities in AF and HF could be explained by the LE8 score. These findings highlighted the importance of integrating cardiovascular health promotion into public health policies aimed at mitigating socioeconomic health inequalities.</p>","PeriodicalId":55062,"journal":{"name":"Hellenic Journal of Cardiology","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142916435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}