Principal investigator: Prof. dr. F.W. (Folkert) Asselbergs
Started: June 1st 2023

About the AI4HF-project

The AI4HF-project is funded by the European Health & Digital Executive Agency and aims to co-design, develop, evaluate, and exploit an integrative and trustworthy artificial intelligence (AI) solution for personalised HF risk assessment, trained from large, complementary multi-source cardiovascular data, including (1) cardiac imaging, (2) cardiac biomarkers, (3) electrocardiography (ECG) and (4) information from clinical reports.


The project will put great emphasis on the concepts of trustworthy and inter-disciplinary AI, to ensure that the developed AI technology is trusted, approved, and deployed in the real world for the benefit of patients, cardiologists, physicians, care providers and society at large.


 Heart Failure (HF)

Despite continuous advances in diagnosis and treatment, cardiovascular diseases (CVDs) remain the main cause of mortality worldwide, accounting for about a third of annual deaths [1]. Complex conditions such as heart failure (HF), which is the subject of this proposal, continue to pose significant challenges in clinical cardiology. HF is a high-burden chronic condition which is the leading cause of hospitalisation for those over the age of 65. About half of hospital re-admissions are related to co-morbidities, polypharmacy and disabilities associated with HF [2]. Projections indicate that the prevalence of HF will increase by 46% to 2030 due to an ever-ageing population and lifestyle changes [3]. At the same time, our consortium coordinator from Amsterdam UMC have previously shown the prognosis of HF remains grim and is worse than many forms of cancer [4].

The challenge with HF is that it is associated with a significant variability in its aetiologies, manifestations and risks, as well as in its progression over time. Clinical risks of HF can vary from mildly reduced cardiac function and decreased quality of life to regular hospitalisation, increased comorbidities, serious adverse events (e.g. myocardial infarction) and mortality. However, current models for HF management, such as the recent guidelines [5] by our consortium partner ESC (European Society of Cardiology), remain largely category-based, such as by considering HF with preserved, mildly reserved or reduced ejection fraction. There is a need for a personalised medicine approach to tailor the care models (i.e. medication, dietary changes, physical exercise, pacemakers or cardiac resynchronisation therapy, among others) to each patient’s risk profile and hence optimise the clinical outcomes.

[2] Azad, N. and Lemay, G. 2014. Management of chronic heart failure in the older population. Journal of geriatric cardiology: JGC, 11(4), p.329.

[3] Benjamin, E.J. et al. 2017. Heart disease and stroke statistics—2017 update: a report from the American Heart Association. circulation, 135(10), pp.e146-e603.

[4] Koudstaal S. et al. 2016. Prognostic Burden of Heart Failure Recorded in Primary Care, Acute Hospital Admissions, or Both: A Population-Based Linked Electronic Health Record Cohort Study in 2.1 Million People. European J Heart Failure.

[5] McDonagh, T.A. et al. 2021. ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: European heart journal, 42(36), pp.3599-3726.

Consortium partners


  1. Netherlands Heart Institute, the Netherlands (Coordinator)
  2. University of Barcelona, Spain
  3. Centre for Research & Technology, Greece
  4. Barcelona Supercomputing Centre, Spain
  5. Software Research & Development Corporation, Turkey
  6. Vall d’Hebron Hospital Research Institute, Spain
  7. International Clinical Research Centre, Czechia
  8. Muhimbili University of Health and Allied Sciences, Tanzania
  9. Centre for Biomedical and Environmental Technology Research, Peru
  10. SHINE 2Europe, Portugal
  11. Regenold GmbH, Germany
  12. European Society of Cardiology, France
  13. European Heart Network, Belgium
  14. University Medical Centre Utrecht, the Netherlands
  15. Amsterdam University Medical Centre, the Netherlands

Associated partner

  1. University of Oxford, UK

Page Up