From task-specific AI to cardiovascular foundation models: a new era of multimodal interpretation.
Authors
Affiliations (12)
Affiliations (12)
- Department of Medicine, Division of Cardiovascular Medicine, Stanford University School of Medicine, Stanford, California, USA.
- Kaiser Permanente Division of Research, Pleasanton, California, USA.
- Stanford Cardiovascular Institute, Stanford University, Stanford, California, USA.
- Kaiser Permanente San Francisco Medical Center, San Francisco, California, USA.
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA.
- Stanford University Department of Computer Science, Stanford, California, USA.
- Stanford University School of Medicine, Stanford, California, USA.
- VA Palo Alto Health Care System, Palo Alto, California, USA.
- Stanford University Department of Electrical Engineering, Stanford, California, USA.
- Stanford University Department of Biomedical Data Science, Stanford, California, USA.
- Kaiser Permanente Division of Research, Pleasanton, California, USA [email protected].
- Department of Cardiology, Kaiser Permanente Santa Clara Medical Center, Santa Clara, California, USA.
Abstract
Artificial intelligence (AI) is reshaping cardiovascular medicine, evolving from task-specific supervised models towards multitask and foundation models capable of broader, more scalable interpretation. Early AI systems achieved high performance in electrocardiographic interpretation, echocardiographic measurement and disease diagnosis but their dependence on predefined outputs and labelled datasets limits flexibility and confines them to individual tasks. Foundation models address these limitations by learning reusable representations from large-scale data, often through self-supervised or contrastive pretraining, and adapting them to multiple downstream tasks. Emerging models in electrocardiography, echocardiography, chest radiography, cardiac MR and cardiac CT demonstrate capabilities including disease classification, quantitative measurement, segmentation, image-text retrieval, report generation and risk prediction. Generalist and multimodal biomedical foundation models further suggest a future in which cardiovascular AI integrates signals, imaging, clinical text, laboratory data and medical history to support patient-level diagnosis and decision-making. This review synthesises the transition from task-specific AI to cardiovascular foundation models and outlines opportunities for multimodal human-centred implementation.