The “Trustworthy Artificial Intelligence for Personalised Risk Assessment in Chronic Heart Failure (AI4HF)” project is an innovative initiative that harnesses the power of Artificial Intelligence (AI) to provide personalized risk assessment and care plans for individuals living with Chronic Heart Failure. It utilizes advanced AI algorithms, global collaboration, and a patient-centered approach to improve healthcare outcomes. This four-year project is led by prof. dr. F.W. (Folkert) Asselbergs, coordinated by the Netherlands Heart Institute, and being conducted by a consortium of 16 international (associated) partners. AI4HF is funded by the European Commission.

Cardiovascular diseases remain the main cause of mortality worldwide; in particular, heart failure (HF) poses complex challenges in clinical practice, as it is associated with a significant variability in aetiologies, manifestations, and risks, as well as in its progression and trajectories over time. Clinical risks of HF can vary from reduced cardiac function and regular hospitalisations, all the way to cardiac events and mortality. There is a need for a personalised medicine approach to tailor the healthcare models (i.e., lifestyle changes, medications, interventions) to each HF patient’s risk profile and hence optimise the clinical outcomes. Artificial intelligence (AI) solutions trained from multi-source cardiovascular data have the potential to dissect the precise characteristics of each patient and predict their likely trajectories at an early stage. However, existing AI methods remain a far distance from clinical transfer and adoption due to a common and key limitation: their trustworthiness and acceptance by cardiologists and patients alike have not been achieved.

AI4HF will develop the first trustworthy AI solutions for personalised risk assessment and management of HF patients. The project will build on a unique set of big data repositories, trustworthy AI methods, computational tools, and clinical results from major EU-funded projects in cardiology. To test robustness, fairness, transparency, usability, and transferability, the validation will occur in eight clinical centres in both high- and low-to-middle-income countries in the EU and internationally. AI4HF will develop a comprehensive and standardised methodological framework for trustworthy and ethical AI development and evaluation based on the FUTURE-AI guidelines developed by the consortium members. AI4HF will be implemented through continuous multi-stakeholder engagement, taking into account clinical needs and patient preferences, as well as socio-ethical and regulatory perspectives.

The AI4HF technology will enable to dissect the precise characteristics of each HF patient, then predict the patient’s likely outcomes at an early stage to enable timely and personalised care. The project will emphasize 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.


The ambitious aim of the AI4HF project is, together with patients and health care professionals, to co-design, develop, evaluate and exploit an integrative and trustworthy AI-model for tailoring management of heart failure patietents.

The largest-ever dataset of heart failure patients will be harnessed to develop the AI model. The inclusion of hundreds of thousands of patients with heart failure in Europe, South America and Africa will result in novel analyses across populations, clinical settings and ethnic groups.

The AI4HF consortium will leverage a unique blend of resources and tools. Real-world health data will be obtained from BigData@Heart and integrated using the FAIR4Health platform following best practice recommendations for building trustworthy AI tools established by FUTURE-AI.


All project partners collaborate and work in a multidisciplinary matter on different Work Packages (WPs) to achieve its ambitious aim. The main pillars of AI4HF are:

  1. Multi-stakeholder engagement and social innovation
  2. Multi-centre data management and federation
  3. Trustworthy AI methods for risk prediction in HF
  4. Trustworthy AI tools and interfaces for end-users
  5. Traceability tools for post-deployment AI monitoring
  6. Multi-centre, multi-faced clinical evaluation study
  7. Impact evaluation and technology exploitation
  8. Project management, dissemination and communication
  9. Ethics

The obtained research results within the AI4HF project will be shared here.

At the end of the project the following deliverables will become available:

  • Patient and clinical requirements
  • Multi-stakeholder requirements
  • Trustworthy-by-Design Specification Document
  • Data Management Plan
  • Report on federated learning activities
  • Robust and generalisable AI methods
  • Bias detection and mitigation methods
  • Uncertainty estimation and data acquisition pathways
  • User interfaces including AI-patient interface
  • Clinical decision support system
  • User manuals and training materials
  • AI product passport
  • System for continuous evaluation and learning
  • Integrated AI monitoring platform
  • Midterm recruitment report
  • Clinical evaluation report
  • Report on the status of posting results
  • Study initiation package
  • Report on economic, healthcare and socio-ethical implications
  • Final information & communication package
  • Regulatory, exploitation and sustainability plans
  • Project handbook including management strategy
  • Dissemination and communication materials (incl. website)
  • Dissemination and communication strategy and plan
  • Ethics requirements