Intervention-related complications negatively affect healthcare quality and costs. Complication registration and reporting play an important role in the improvement of healthcare outcomes but are time-consuming and hampered by under-reporting. We developed an artificial intelligence (AI)-aided tool that extracts specific complications, including bleeding, tamponade, CVA and phrenic paralysis, from electronic healthcare records of patients undergoing pulmonary vein isolation (PVI), percutaneous transluminal coronary angioplasty (PTCA) and transcatheter aortic valve implantation (TAVI). Both structured and unstructured data were used, along with additional signals identified through machine learning. The model was optimized to achieve high sensitivity. Electronic records of 6,564 patients undergoing PVI, PTCA, and TAVI, performed at our hospital from 2017–2022, were used. The final model detected the various complications with a sensitivity between 94.4 and 100
Atrial cardiomyopathy (AtCM) is increasingly recognised as an underlying atrial substrate contributing to atrial fibrillation (AF), heart failure (HF), and cardio-embolic stroke. However, diagnostic criteria, disease thresholds, and targeted treatment strategies remain poorly defined. To describe the rationale, structure, and translational strategy of the EmbRACE (Electro-Molecular Basis and the theRapeutic management of Atrial Cardiomyopathy, fibrillation and associated outcomEs) network, a national consortium established to address key knowledge gaps in AtCM. EmbRACE integrates mechanistic research, computational modelling, clinical trials, and implementation science within seven interconnected work packages. Human atrial tissue biobanking and deep phenotyping (WP1) enable molecular profiling of candidate pathways (WP2), which are validated in experimental models (WP3). Computational modelling and artificial intelligence (WP4) integrate multimodal clinical and biological data to derive composite AtCM phenotypes and severity frameworks. Substrate-targeting clinical trials evaluate AF ablation (RACE X; WP5), weight reduction using GLP‑1 agonists (DUTCH-WAIST; WP6), and optimised rate control using calcium channel antagonists (SMART-VERAPAF; WP6). Implementation science (WP7) focuses on guideline integration, decision-support tools, and governance of AI-based risk models. EmbRACE establishes a translational pipeline from mechanistic discovery to clinical application. By integrating tissue-level insights with multimodal risk modelling and interventional trials, the consortium aims to define clinically meaningful AtCM thresholds, to validate indirect markers, and to determine whether targeted treatment modifies disease progression and clinical outcomes. EmbRACE provides a multidisciplinary framework to transform AtCM from a theoretical construct into a clinically actionable entity, enabling earlier detection, improved risk stratification, and AtCM-directed therapy in cardiovascular prevention.
This article contextualises the 2025 European Society of Cardiology (ESC) guidelines for managing cardiovascular disease (CVD) and pregnancy in the Netherlands. The guideline addendum provides additional recommendations for situations where the ESC guidelines may not fully align with Dutch clinical practice. By endorsing the ESC guidelines through this addendum, the Netherlands Society of Cardiology (Nederlandse Vereniging Voor Cardiologie) supports its members in adhering to evidence-based management strategies for CVD and pregnancy.
