Artificial intelligence in cardiology for non-experts: decoding key terms and understanding machine learning methodologies. A Scientific Statement of the ESC Working Group on e-Cardiology, the European Heart Rhythm Association (EHRA), the Association for Acute CardioVascular Care (ACVC), the Heart Failure Association (HFA), the European Association of Cardiovascular Imaging (EACVI), the European Association of Preventive Cardiology (EAPC), and the European Association of Percutaneous Cardiovascular Interventions (EAPCI) of the ESC, the ESC Regulatory Affairs Committee, and the ESC Digital Cardiology and Artificial Intelligence Committee
Year: 2026
Type: review
Abstract: Evidence-based medicine represents the systematic approach through which physicians today use the best available scientific evidence from clinical research to guide their clinical decision-making process. However, the emergence of artificial intelligence (AI), with its diverse models and potential applications in medicine, is leading to a new form of research driven by 'big data' and heterogeneous datasets, extending beyond conventional statistical analysis and thereby making AI literacy an increasingly essential competence for clinicians. Artificial intelligence applications in cardiology have shown potential to support disease diagnosis, risk prediction, workflow efficiency, and therapeutic decision-making. However, despite these opportunities, AI may also represent a technological barrier for many physicians, due to its mathematical foundations and the speed at which models evolve. A solid understanding of AI concepts is therefore necessary for cardiologists to critically interpret results and engage with this new research landscape. This scientific statement explores AI in cardiology from an educational perspective, outlining the key knowledge required to build adequate AI literacy. The goal is to enable cardiologists not only to avoid reliance on external experts for methodological decisions, but also to collaborate with greater insight and informed judgment.
Authors: Raffaele De Lucia, Matthijs Cluitmans, Julia Ramírez, Márton Kolossváry, Andreu M Climent, José Millet, Matteo Parollo, Marco Tubaro, Maurizio Volterrani, Paul Dendale, Fabrizio D’Ascenzo, Piotr Szymański, Magnus Thorsten Jensen, Polychronis Dilaveris, Gabriel Bernardino, David Duncker, Michiel Rienstra, Rafael Vidal-Perez, Emanuela T Locati, Roderick Treskes, Mark Schuuring, Cristiana Vitale, Nay Aung, Paul Leeson, Stefan Busnatu, Lukasz Koltowski, Ruben Casado-Arroyo
Institutions: Azienda Ospedaliera Universitaria Pisana, Maastricht University, Queen Mary University of London, Universidad de Zaragoza, William Harvey Research Institute, Gottsegen National Cardiovascular Center, Universitat Politècnica de València, San Raffaele University of Rome, IRCCS San Raffaele Roma, Hasselt University, Azienda Ospedaliera Citta' della Salute e della Scienza di Torino, University of Turin, University of Copenhagen, Amager Hospital, Hvidovre Hospital, National and Kapodistrian University of Athens, Universitat Pompeu Fabra, Medizinische Hochschule Hannover, University Medical Center Groningen, University of Groningen, Instituto de Salud Carlos III, Centro de Investigación en Red en Enfermedades Cardiovasculares, Centro de Investigación Biomédica en Red, Complexo Hospitalario Universitario A Coruña, IRCCS Policlinico San Donato, Medisch Spectrum Twente, University of Twente, University of Oxford, Medical University of Warsaw, Université Libre de Bruxelles, Erasmus Hospital
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,725
OpenAlex ID: W7225414074