Hearts, Volume 6, Issue 3 (September 2025) – 6 articles

Background/Objectives: Invasive coronary angiography (ICA) is the gold standard for the diagnosis of coronary artery disease (CAD), with various non-invasive imaging modalities also available. Machine learning (ML) methods are increasingly applied to overcome the limitations of diagnostic imaging by improving accuracy and observer independent performance. Methods: This meta-analysis (PRISMA method) summarizes the evidence for ML-based analyses of coronary imaging data from ICA, coronary computed tomography angiography (CT), and nuclear stress perfusion imaging (SPECT) to predict clinical outcomes and performance for precise diagnosis. We searched for studies from Jan 2012–March 2023. Study-reported c index values and 95% confidence intervals were used. Subgroup analyses separated models by outcome. Combined effect sizes using a random-effects model, test for heterogeneity, and Egger’s test to assess publication bias were considered. Results: In total, 46 studies were included (total subjects = 192,561; events = 31,353), of which 27 had sufficient data. Imaging modalities used were CT (n = 34), ICA (n = 7) and SPECT (n = 5). The most frequent study outcome was detection of stenosis (n = 11). Classic deep neural networks (n = 12) and convolutional neural networks (n = 7) were the most used ML models. Studies aiming to diagnose CAD performed best (0.85; 95% CI: 82, 89); models aiming to predict clinical outcomes performed slightly lower (0.81; 95% CI: 78, 84). The combined c-index was 0.84 (95% CI: 0.81–0.86). Test of heterogeneity showed a high variation among studies (I² = 97.2%). Egger’s test did not indicate publication bias (p = 0.485). Conclusions: The application of ML methods to diagnose CAD and predict clinical outcomes appears promising, although there is lack of standardization across studies. Full article

Background/Objectives: While elevated Lp(a) levels are associated with incident heart failure development, the role of Lp(a) in established heart failure with reduced ejection fraction (HFrEF) versus heart failure with preserved ejection fraction (HFpEF) remains unexplored. Methods: We conducted a retrospective analysis of 387 heart failure patients from our institutional database (January 2018–June 2024). Patients were categorized as HFrEF (n = 201) or HFpEF (n = 186) using ICD-10 codes. Categorical variables were compared between heart failure types using the Chi-square test or Fisher’s Exact test, and continuous variables were compared using the two-sample t-test or Wilcoxon rank-sum test, as appropriate. Logistic regression was utilized to assess heart failure type as a function of Lp(a) levels, adjusting for covariates. Spearman correlation assessed relationships between Lp(a) and pro-BNP levels. Results: Despite significant demographic and clinical differences between HFrEF and HFpEF patients, Lp(a) concentrations showed no significant variation between groups. Median Lp(a) levels were 60.9 nmol/dL (IQR: 21.9–136.7) in HFrEF versus 45.0 nmol/dL (IQR: 20.1–109.9) in HFpEF (p = 0.19). After adjusting for demographic and clinical covariates, Lp(a) showed no association with heart failure subtype (OR: 1.001, 95% CI: 0.99–1.004; p = 0.59). Conclusions: Lp(a) levels do not differ significantly between HFrEF and HFpEF phenotypes, suggesting possible shared pathophysiological mechanisms rather than phenotype-specific biomarker properties. These preliminary findings may support unified screening and treatment strategies for elevated Lp(a) across heart failure, pending confirmation in larger studies. Full article

Background: Large Language Models (LLMs) such as ChatGPT, Claude, and Gemini are being increasingly adopted in medicine; however, their reliability in cardiology remains underexplored. Purpose of the study: To compare the performance of three general-purpose LLMs in response to cardiology-related clinical queries. Study design: Seventy clinical prompts stratified by diagnostic phase (pre or post) and user profile (patient or physician) were submitted to ChatGPT, Claude, and Gemini. Three expert cardiologists, who were blinded to the model’s identity, rated each response on scientific accuracy, completeness, clarity, and coherence using a 5-point Likert scale. Statistical analysis included Kruskal–Wallis tests, Dunn’s post hoc comparisons, Kendall’s W, weighted kappa, and sensitivity analyses. Results: ChatGPT outperformed both Claude and Gemini across all criteria (mean scores: 3.7–4.2 vs. 3.4–4.0 and 2.9–3.7, respectively; p < 0.001). The inter-rater agreement was substantial (Kendall’s W: 0.61–0.71). Pre-diagnostic and patient-framed prompts received higher scores than post-diagnostic and physician-framed ones. Results remained robust across sensitivity analyses. Conclusions: Among the evaluated LLMs, ChatGPT demonstrated superior performance in generating clinically relevant cardiology responses. However, none of the models achieved maximal ratings, and the performance varied by context. These findings highlight the need for domain-specific fine-tuning and human oversight to ensure a safe clinical deployment. Full article

Hypertensive left ventricular hypertrophy (LVH) is an ominous cardiovascular sequel to chronic hypertension, marked by structural and functional alterations in the heart. Identified as a significant risk factor for adverse cardiovascular outcomes, LVH is typically detected through echocardiography and is characterized by pathological thickening of the left ventricular wall. This hypertrophy results from chronic pressure overload (increased afterload), leading to concentric remodelling, or from increased diastolic filling (preload), contributing to eccentric changes. Apoptosis, a regulated process of cell death, plays a critical role in the pathogenesis of LVH by contributing to cardiomyocyte loss and subsequent cardiac dysfunction. Given the substantial clinical implications of LVH for cardiovascular health, this review critically examines the role of cardiomyocyte apoptosis in its disease progression, evaluates the impact of pharmacological interventions, and highlights the necessity of a comprehensive, multifaceted treatment approach for the prevention and management of hypertensive LVH. Finally, we address the health disparities associated with LVH, with particular attention to the disproportionate burden faced by African Americans and other Black communities, as this remains a key priority in advancing equity in cardiovascular care. Full article

Cardiac iron overload is a rare but important adverse consequence of systemic iron overload, marked by the abnormal accumulation of iron in the myocardium. It is most typically caused by hereditary hemochromatosis (mutations in the HFE gene) or secondary iron overload conditions, such as transfusion-dependent anemias. Excess iron in the myocardium causes oxidative stress, cardiomyocyte damage, and progressive fibrosis, ultimately leading to cardiomyopathy. Clinical manifestations are diverse and may include heart failure, arrhythmias, and restrictive or dilated cardiomyopathy. Given the worsened prognosis with cardiac involvement, timely diagnosis and management are essential to improve clinical outcomes. This review provides a contemporary overview of the cardiovascular complications associated with iron overload, including clinical manifestations, diagnostic approaches, and treatment options. Full article

Background/Objectives: Cangrelor, an intravenous P2Y12 inhibitor, is increasingly used during percutaneous coronary intervention (PCI) for rapid and reversible platelet inhibition in patients unable to take oral antiplatelet agents, particularly in emergencies such as ST-elevation myocardial infarction (STEMI), cardiac arrest, or cardiogenic shock. This single-centre study evaluates cangrelor and outcomes in a non-surgical centre. Methods: Between June 2017 and December 2021, all the patients for whom cangrelor was used at a district general hospital (DGH) in the UK were included in this study. Data collection included baseline characteristics, admission, procedural details, and patient outcomes. The primary outcome was a composite of all-cause mortality, bleeding, and cardiovascular events, including myocardial infarction, stent thrombosis, and stroke, within 48 h. Secondary outcomes included predictors of the composite outcome at 48 h. Results: During the study period, cangrelor was administered peri-procedurally to 93 patients. Males comprised 85% of the patients; the mean age was 65.5 ± 10.6 years. A total of 1 patient (1.1%) had a cardiovascular event within 48 h of cangrelor administration, whereas all-cause mortality occurred in 17 patients (18%) within 48 h. No major bleeding events were noted at 48 h following cangrelor administration. Regression analysis did not find predictors of composite outcomes at 48 h. Conclusions: Cangrelor offers a potential alternative to oral P2Y12 inhibitors in specific high-risk scenarios. Further research is needed to validate its role in broader populations. Full article