Machine learning using combined coronary CT angiography and stress cardiac MRI data outperformed existing scores in predicting major adverse cardiovascular events in patients with newly diagnosed coronary artery disease.

Comparison between the SAPIEN S3 and the SAPIEN XT transcatheter heart valves: A single-center experience

Background: Hypertension remains the leading global risk factor for cardiovascular morbidity and mortality, with suboptimal control rates despite guideline-directed therapies. Digital health and artificial intelligence (AI) technologies offer novel approaches for improving diagnosis, monitoring, and individualized treatment of hypertension. Objectives: To critically review the current landscape of AI-enabled digital tools for hypertension management, including emerging applications, implementation challenges, and future directions. Methods: A narrative review of recent PubMed-indexed studies (2019–2024) was conducted, focusing on clinical applications of AI and digital health technologies in hypertension. Emphasis was placed on real-world deployment, algorithmic explainability, digital biomarkers, and ethical/regulatory frameworks. Priority was given to high-quality randomized trials, systematic reviews, and expert consensus statements. Results: AI-supported platforms—including remote blood pressure monitoring, machine learning titration algorithms, and digital twins—have demonstrated early promise in improving hypertension control. Explainable AI (XAI) is critical for clinician trust and integration into decision-making. Equity-focused design and regulatory oversight are essential to prevent exacerbation of health disparities. Emerging implementation strategies, such as federated learning and co-design frameworks, may enhance scalability and generalizability across diverse care settings. Conclusions: AI-guided titration and digital twin approaches appear most promising for reducing therapeutic inertia, whereas cuffless blood pressure monitoring remains the least mature. Future work should prioritize pragmatic trials with equity and cost-effectiveness endpoints, supported by safeguards against bias, accountability gaps, and privacy risks.

A cardiac MRI model incorporating the ischemic late gadolinium enhancement (LGE) parameters of extent, transmurality, location, and midwall LGE significantly outperformed traditional risk factors in predicting all-cause mortality in participants with ischemic cardiomyopathy.

Background: Epidemiological characteristics and prognostic profiles of patients with newly diagnosed coronary artery disease (CAD) are heterogeneous. Therefore, providing individualized cardiovascular (CV) risk stratification and tailored prevention is crucial.Objective: Phenotypic unsupervised clustering integrating clinical, coronary computed tomography angiography (CCTA), and cardiac magnetic resonance (CMR) data were used to unveil pathophysiological differences between subgroups of patients with newly diagnosed CAD.Materials and Methods: Between 2008 and 2020, consecutive patients with newly diagnosed obstructive CAD on CCTA and further referred for vasodilator stress CMR were followed for the occurrence of major adverse cardiovascular events (MACE), defined by cardiovascular death or non-fatal myocardial infarction. For this exploratory work, a cluster analysis was performed on clinical, CCTA, and CMR variables, and associations between phenogroups and outcomes were assessed.Results: Among 2,210 patients who underwent both CCTA and CMR, 2,015 (46% men, mean 70 ± 12 years) completed follow-up [median 6.8 (IQR 5.9–9.2) years], in which 277 experienced a MACE (13.7%). Three mutually exclusive and clinically distinct phenogroups (PG) were identified based upon unsupervised hierarchical clustering of principal components: (PG1) CAD in elderly patients with few traditional risk factors; (PG2) women with metabolic syndrome, calcified plaques on CCTA, and preserved left ventricular ejection fraction (LVEF); (PG3) younger men smokers with proximal non-calcified plaques on CCTA, myocardial scar, and reduced LVEF. Using survival analysis, the occurrence of MACE, cardiovascular mortality, and all-cause mortality (all p < 0.001) differed among the three PG, in which PG3 had the worse prognosis. In each PG, inducible ischemia was associated with MACE [PG1, Hazards Ratio (HR) = 3.09, 95% CI, 1.70–5.62; PG2, HR = 3.62, 95% CI, 2.31–5.7; PG3, HR = 3.55, 95% CI, 2.3–5.49; all p < 0.001]. The study presented some key limitations that may impact generalizability.Conclusions: Cluster analysis of clinical, CCTA, and CMR variables identified three phenogroups of patients with newly diagnosed CAD that were associated with distinct clinical and prognostic profiles. Inducible ischemia assessed by stress CMR remained associated with the occurrence of MACE within each phenogroup. Whether automated unsupervised phenogrouping of CAD patients may improve clinical decision-making should be further explored in prospective studies.

Digital twin technology, which enables the creation of patient-specific virtual models, is increasingly applied in interventional cardiology to support personalized procedural planning and risk assessment. This review examines current applications of digital twins in coronary and structural heart interventions, including percutaneous coronary intervention (PCI), transcatheter aortic valve replacement (TAVR), transcatheter mitral valve replacement (TMVR), and left atrial appendage closure (LAAC). In coronary interventions, digital simulations based on computed tomography or angiography can estimate physiological indices, guide stent placement, and predict post-procedural hemodynamics. For structural interventions, simulation platforms generate 3D reconstructions from imaging data to model device–anatomy interactions, support valve sizing, and assess risks such as paravalvular leak or left ventricular outflow tract obstruction. Several tools are already integrated into clinical workflows, with growing evidence supporting their utility in improving planning accuracy and procedural outcomes. Nonetheless, broader adoption is limited by challenges related to model validation, data integration, workflow complexity, and regulatory constraints. In particular, validation remains difficult for procedures performed less frequently, such as TMVR. Ongoing developments in artificial intelligence and computational methods may enhance model speed and accuracy, enabling wider and more efficient clinical use. Digital twin technologies represent a promising direction for advancing precision medicine in transcatheter coronary and structural heart interventions.