TECHNOLOGICAL UNIVERSITY DUBLIN

RES-Q+ will build on the success of RES-Q (REgistry of Stroke Care Quality) - currently, used by many EU countries and 74 worldwide - to improve stroke care quality by collecting and analyzing hospital discharge reports. RES-Q+ will revolutionize these improvements by capturing the whole patient pathway. The solution will combine NLP with a clinically-validated semantic model to automate ingestion of hospital discharge reports in different languages and assist with audit and feedback. This will include creating a standard model for such reports and using AI to impute missing data. Further augmentations include the creation of two novel AI voice assistants, one to help patients provide feedback on their health and the other to help physicians provide high quality care. We will integrate all these tools into RES-Q+. This will be the basis for a European Open Stroke Data Platform, an open research platform for data aggregation, semantic harmonization and interoperability across European countries to promote the use and re-use of health data. We will facilitate efforts to define a standard European Stroke Hospital Discharge Report Exchange Format as a tool for better secondary use of data and healthcare in general. Consortium legal partners will develop a comprehensive legal and ethical toolbox as guidance towards legal compliance. This will boost wider adoption of such novel AI-based solutions by integrating all current and proposed Union legislation. Our clinical partners will provide medical records and steer the development to maximize clinical utility and validate final solutions. RES-Q+ will be deployed globally to solidify our position as European and global leader in quality improvement. Eventually we will guarantee citizens a similar level of quality control during hospitalizations as when flying in a commercial plane.

EC contribution:

EUR 522k

Start:

2022-11-01

End:

2026-10-31

Status:

SIGNED

Scheme:

HORIZON-RIA

Call:

HORIZON-HLTH-2021-TOOL-06

View on CORDIS (DOI 10.3030/101057603)

Based on previously developed models and an existing prototype of a clinical decision support system (patent pending), we set out in this project to further develop, test, and validate this clinical decision support for the treatment stratification of acute stroke patients to improve patient outcome. Machine learning (ML)-enabled Artificial intelligence (AI) methods are increasingly adopted in the medical field. Implementing ML-based CDSSs have the potential to be go beyond the current clinical state-of-the-art as AI excels at finding complex and non-linear relationships across a multitude of prognostic variables. AI also has the promise to combine different modalities, such as imaging and clinical values, leading to powerful stratification tools accounting for a multitude of patient sub-populations. Our consortium combines excellence in technical and medical machine learning development with the clinical expertise of three leading stroke hospital partners. Additionally, our consortium benefits from the special expertise in the development of trustworthy AI, software design, and the translation of AI models to the clinical setting with focus on the regulatory process. By leveraging the available medical data and exploiting technological opportunities in the field of AI, and developing and validating trustworthy AI solutions to be implemented in the clinical workflow we are seeking to surpass the clinical state-of-the-art by making a significant and sustainable impact on the treatment of acute stroke that will improve patient survival, outcome and quality of life. The results of our work will serve as a pathway for future projects and we will make our experiences public in the form of standard operating procedures (SOPs) in the areas of development, testing, validation, and regulatory processes.

EC contribution:

EUR 425k

Start:

2022-05-01

End:

2026-04-30

Status:

SIGNED

Scheme:

HORIZON-RIA

Call:

HORIZON-HLTH-2021-DISEASE-04

View on CORDIS (DOI 10.3030/101057263)

"Artificial Intelligence (AI) offers a new way to approach the seemingly intractable challenges of Global Development, mobilising unprecedented amounts of data and generating insights from previously unused sources (e.g. big data, mobile phone records). Unlike traditional development projects, AI systems can scale rapidly while requiring very little on-the-ground implementation. However, the ethical implications of incorporating AI into Global Development are not well-defined. Therefore, this project seeks to collect empirical data about the ethical questions that arise when AI is part of a development project. It will involve a case study of the AI Cookstoves Project, an on-going collaboration between the ADAPT Centre in Ireland and Makerere University in Uganda. The AI Cookstoves Project takes a familiar problem - the use of woodburning cookstoves - and approaches it with a combination of engineering, community input, and AI-generated design suggestions. In doing so, it raises ethical questions about development and AI, including whether the goal of energy efficiency for the stoves is outweighed by the energy costs of running a generative AI model, and how the inclusion of AI models affects the knowledge hierarchy among stakeholders with different kinds of knowledge. At the same time, the researcher will seek to understand how AI and Global Development experts conceive of the potential for AI in development through in-depth interviews of experts and participant observation at public presentations and working group discussions about AI, ethics, and global development, in Ireland and Uganda. This work brings a distinctly global lens to the question of AI ethics. In this way, it aims to speak to the Sustainable Development Goals for inclusive economic growth (#8) and reduced inequality (#10). It also seeks to provide policymakers with a new approach to AI ethics that is grounded in actual examples of AI in practice."

EC contribution:

EUR 253k

Start:

2025-09-01

End:

2027-08-31

Status:

SIGNED

Scheme:

HORIZON-TMA-MSCA-PF-EF

Call:

HORIZON-MSCA-2024-PF-01

View on CORDIS (DOI 10.3030/101211991)