Trustworthy Artificial Intelligence for Personalised Risk Assessment, or AI4HF, is a 4-year project that aims to co-design, develop and evaluate the first trustworthy artificial intelligence (AI) tool for personalising the care and management of patients with heart failure. AI4HF adopts a personalised medicine approach, and the tools and care pathways are co-created with all relevant stakeholders.
To ensure continuous involvement, Local Clinical/Patient Working Groups (WGs) were established at the project’s five clinical sites: Utrecht/Amsterdam (Netherlands), Barcelona (Spain), Brno (Czech Republic), Dar es Salaam (Tanzania), and Lima (Peru). Each group consists of 6-8 healthcare professionals specializing in heart failure care and 6-8 patients. Their primary role is to assess the cultural and organizational appropriateness of the materials and tools developed within the project.
Under the coordination of SHINE 2Europe and the participating clinical centers in the Netherlands, the five local sites conducted the second round of workshops in Autumn/Winter 2024. These workshops had two main objectives:
-
Gather feedback on the Information and Communication (I&C) packages developed in the project.
-
Investigate the relationships between patients, healthcare professionals, and artificial intelligence (AI) across different healthcare settings.
A total of 27 patients and 35 healthcare professionals participated in the sessions, with 3 to 7 patients and 6 to 9 healthcare professionals per site. Additionally, hospital administrators in Peru and Tanzania joined the discussions, reflecting institutional interest in AI-driven heart failure care.
Both patients and clinicians found the informational leaflets clear and relevant but suggested improvements to enhance accessibility. Recommendations included:
-
Shortening the text for easier readability.
-
Incorporating more graphical elements to make the content more engaging.
-
Exploring alternative formats, such as short videos, to improve comprehension.
The insights from these workshops are crucial in ensuring that AI-driven tools are not only scientifically robust but also practical and accessible for real-world use.
Regarding the role of AI in healthcare, both patients and clinicians expressed a range of perspectives. Some clinicians viewed AI as an extra (objective) colleague offering advice, while others saw it as an additional tool, with its output needing to be translated to patients by clinicians. In cases where AI is independently used by patients, participants emphasized the importance of ensuring patients have the right tools and information to assess the outcomes. There was also a consensus that AI should never replace clinicians in decision-making or human contact. The next focus group session will test specific assumptions and ethical concerns raised in the second focus group by discussing a concrete clinical encounter between a clinician and patient using AI.
The third round of Local WG workshops is scheduled for early Summer 2025. These sessions will focus on:
-
Gathering feedback on AI-powered risk prediction tools for heart failure, and
-
Exploring potential bias factors in heart failure care across different local contexts.
The AI4HF consortium extends its sincere appreciation to all participants for their dedication to improving heart failure care. Their valuable contributions continue to shape AI innovations that are responsive to real-world clinical needs.
