Clustering with other EU projects under the same funding call is a critical impact activity encouraged by the European Commission. The following projects have received funding to create AI-powered tools that will group patients based on their risk of disease or response to therapy, a technique that will assist care providers in determining the appropriate treatment response and significantly improve the quality of patient care. Since the EU AI Act classifies AI systems used in healthcare as high-risk, it is imperative that EU projects creating these tools are keeping on top of the latest AI regulation while simultaneously incorporating ethics into every step of their design. Networking with other projects allows for collaboration and knowledge exchange, which ultimately accelerates scientific progress and innovation. Our Health cluster objectives are as follows:
- To share knowledge and experiences in order to support end-users (clinicians and patients) and educate common stakeholders about AI tools and technologies in Healthcare.
- To leverage our dissemination activities by mentioning the projects in the cluster on our websites, inviting articles from the cluster projects in our newsletter.
- Ensuring the coherence and complementarity of our recommendations to the EC, LEAs and other stakeholders, as far as possible.
- Exploring synergies, research opportunities and joint exploitation activities.
The aim of Microb-AI-ome is to develop a new AI-based approach for early colorectal cancer detection by building on the link between the microbiome and incidence of colorectal cancer. It will use federated learning to train AI models locally to comply with privacy laws and combine all local models into a single global model.
SPIDeRR aims to streamline early diagnoses of rheumatic diseases. Its innovative approach will identify disease groups amongst patients with similar symptoms by integrating all the relevant data from every healthcare level. The project will apply machine learning techniques from the omics field to clinically collected patient data, resulting in new pipelines for translational science.
The STRATA-Fit experts are developing and validating computational models that will be used to identify and classify patients with difficult-to-treat rheumatoid arthritis (D2T RA) into clinically relevant phenotypes using real world clinical data.
STRATIF-AI is creating a scalable platform using continuous stratification, where all the data generated about a patient is cumulatively stored in Personal Data Vault, controlled by the patient, forming the foundation for a new interconnected and patient centric healthcare system.
The TARGET project aims to revolutionise the management of Atrial Fibrillation (AF) and AF-related strokes (AFRS) by developing virtual twin-based AI models for the personalised management of stroke related to AF. By combining mechanistic and data-driven virtual twins with causal AI, TARGET will bridge the gap between research and clinical practice.
AI4Lungs is developing and validating AI-based tools and computational models for improving patient stratification in the diagnosis and treatment of both infectious and non-infectious respiratory diseases.
The CoMPaSS-NMD project aims to improve the quality of life of patients suffering from Hereditary Neuromuscular Diseases (HNMDs) and their caregivers, by adopting a new multidimensional approach based on Artificial Intelligence (AI) for better and faster personalised diagnoses and treatments. It will do this by analysing a large amount of diverse data sources, collected from the clinical centres partners of the project, among which genetic and clinical information, creating one of the most advanced diagnostic computational tools.
COMFORT aims to assist medical professionals in delivering improved care for people affected by prostate or kidney cancer by producing the first multi-national evaluation of AI-models in a clinical setting, leading to improved urological cancer care using AI.