Real-world-data Enabled Assessment for heaLth regulatory decision-Making

Informazioni relative al progetto

REALM

ID dell’accordo di sovvenzione: 101095435

DOI

10.3030/101095435

Data della firma CE 24 Novembre 2022

Data di avvio 1 Gennaio 2023

Data di completamento 31 Dicembre 2026

Finanziato da

• Health

Costo totale

€ 6 659 650,00

Contributo UE

€ 6 659 650,00

Coordinato da

UNIVERSITEIT MAASTRICHT
Netherlands

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Websites, patent fillings, videos etc. (1)

Public project website

The website will inform the public about the project’s aims, updates and results. The website will be continuously updated throughout the project’s lifetime. Links to social media will be implemented as well.

Documents, reports (7)

Multimodal Synthetic Data Generator

The deliverable will provide a comprehensive generation framework that combines data generators of various medical data types, design evaluation metrics and benchmarks to assess the performance of the framework. `The deliverable consists of: 1) open-source code of the generators, evaluation methods, and benchmarks and 2) a scientific report for the multimodal synthetic data generation design and evaluation.

Manuscript on MDR, IVDR and AI Act

Result of the legal and regulatory analysis of newly adopted EU regulations on MDR, IVDR and soon-to-be-adopted AI Act. The manuscript's methodology will cover scoping review of existing scholarly literature and dogmatic analysis of their provision with particular focus on the mutual relations between indicated legislative measures.

Standard Data Quality Framework (SDQF)

This deliverable will provide the security and privacy requirements for the medical systems and software development in terms of confidentiality, integrity, availability, authenticity and non-repudiation principles, taking into account EU and national legal frameworks. As a result functional requirements will define all the functional properties that must be implemented and finally supported within the REALM solution, including all behavioural aspects of the system components, tools and applications.

Federated cloud-based data repository

A cloud-based infrastructure will be created for collecting and standardizing data from various sources (electronic health records, lab reports, images) such that it can be saved in a structured database. The infrastructure will be augmented with additional modules for extracting relevant clinical features, discovering associations between features, and applying AI-based models to the data in order to address a specific clinical question

Authorized access agreements with European Medical Data Pools and DT

In this deliverable we aim to bridge REALM’s data infrastructure with ongoing (and completed) European projects with standardized medical data component, Digital Twins Platforms, In-Silico trial technologies and restricted access biobanks.

Data Management Plan V2

Version 2 of Data Management Plan

Data Management Plan

The DMP describes the data management life cycle for the data to be collected, processed and/or generated. As part of making research data findable, accessible, interoperable and re-usable (FAIR), the DMP will include information on:- the handling of research data during & after the end of the project- what data will be collected, processed and/or generated- which methodology & standards will be applied- whether data will be shared/made open access and how data will be curated & preserved (including after the end of the project).

Pubblicazioni

Peer reviewed articles (4)

Generating unseen diseases patient data using ontology enhanced generative adversarial networks

Autori: Chang Sun 0001; Michel Dumontier
Pubblicato in: npj Digital Medicine, 2025, ISSN 2398-6352
Editore: Springer Nature (Nature Portfolio)
DOI: 10.1038/S41746-024-01421-0

Generative AI for synthetic data across multiple medical modalities: A systematic review of recent developments and challenges

Autori: Mahmoud K. Ibrahim; Yasmina Al Khalil; Sina Amirrajab; Chang Sun 0001; Marcel Breeuwer; Josien P. W. Pluim; Bart Elen; Gökhan Ertaylan; Michel Dumontier
Pubblicato in: Computers in Biology and Medicine, 2025, ISSN 1879-0534
Editore: Elsevier
DOI: 10.48550/ARXIV.2407.00116

Introducing DEFORMISE: A deep learning framework for dementia diagnosis in the elderly using optimized MRI slice selection

Autori: Nikolaos Ntampakis, Konstantinos Diamantaras, Ioanna Chouvarda, Vasileios Argyriou, Panagiotis Sarigiannidis
Pubblicato in: Biomedical Signal Processing and Control, Numero 113, 2025, ISSN 1746-8094
Editore: Elsevier BV
DOI: 10.1016/J.BSPC.2025.109151

BMC Medical Ethics

Autori: Ratti, E; Morrison, M; Jakab, I
Pubblicato in: BMC Medical Ethics, 2025, ISSN 1472-6939
Editore: BioMed Central
DOI: 10.1186/S12910-025-01198-1

Other (4)

RAG-Enhanced LLM Pipeline for Semantic Mapping of Context-based Features to OMOP Vocabulary

Autori: Kakkamani, S., JUNG, F., Verbiest, J., & PEETERS, L.
Pubblicato in: European OHDSI Symposium 2025
Editore: OHDSI Europe
DOI: 10.5281/ZENODO.18789039

Enhancing transparency in AI for healthcare with OMOP Model Card reporting

Autori: JUNG, F., Lohachab, A., Madureira Sanches Ribeiro, G., Rommes, S., Urovi, V., Sun, C., & Ertaylan, G.
Pubblicato in: European OHDSI Symposium 2025
Editore: OHDSI Europe
DOI: 10.5281/ZENODO.18788825

RIANA Dashboard: A Blockchain-Enabled Approach for Representing AI Model Intent in OMOP with Atlas-Like Functionality

Autori: JUNG, F., Madureira Sanches Ribeiro, G., Lohachab, A., Rommes, S., Urovi, V., Sun, C., Ertaylan, G., & Attipoe, A.
Pubblicato in: European OHDSI Symposium 2025
Editore: OHDSI Europe
DOI: 10.5281/ZENODO.18788892

REALM – innovative solutions for the creation and evaluation of AI medical device software

Autori: JUNG, F., Sun, C., Ibrahim, M., & Ertaylan, G.
Pubblicato in: European OHDSI Symposium 2024 , Rotterdam
Editore: OHDSI Europe
DOI: 10.5281/ZENODO.18788473

Book chapters (3)

Enhancing Performance for Highly Imbalanced Medical Data via Data Regularization in a Federated Learning Setting

Autori: Georgios Tsoumplekas; Ilias Siniosoglou; Vasileios Argyriou; Ioannis D. Moscholios; Panagiotis G. Sarigiannidis
Pubblicato in: Lecture Notes in Computer Science ISBN: 9783031672842, 2024
Editore: Springer Nature (Springer)
DOI: 10.48550/ARXIV.2405.20430

A Blockchain-Based Approach for Model Card Accountability and Regulatory Compliance

Autori: Ankur Lohachab, Visara Urovi
Pubblicato in: Lecture Notes in Business Information Processing, Advanced Information Systems Engineering Workshops, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-61003-5_4

Optimizing Melanoma Prognosis Through Synergistic Preprocessing and Deep Learning Architecture for Dermoscopic Thickness Prediction

Autori: Nikolaos Ntampakis, Konstantinos Diamantaras, Konstantinos Goulianas, Ioanna Chouvarda, Vasileios Argyriou, Panagiotis Sarigiannidis
Pubblicato in: Lecture Notes in Computer Science, Medical Image Understanding and Analysis, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-66958-3_24

Conference proceedings (3)

AI Deployment in Medical Devices-Ethical and Regulaltory Reflections, Beyond Data Protection and Bias – EU perspective

Autori: Tomasz Braun, Dominika Ewa Harasimiuk
Pubblicato in: 2023 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), 2023
Editore: IEEE
DOI: 10.1109/CIBCB56990.2023.10264892

Open research datasets harmonized to the OMOP CDM can be used to evaluate COPD AI models

Autori: JUNG, F., Sakkalis, V., Sun, C., Ibrahim, M., & Ertaylan, G.
Pubblicato in: European OHDSI Symposium 2024, Rotterdam
Editore: OHDSI Europe
DOI: 10.5281/ZENODO.18783801

Enhancing Performance for Highly Imbalanced Medical Data via Data Regularization in a Federated Learning Setting

Autori: Georgios Tsoumplekas, Ilias Siniosoglou, Vasileios Argyriou, Ioannis D. Moscholios, Panagiotis Sarigiannidis
Pubblicato in: Lecture Notes in Computer Science, Artificial Intelligence in Healthcare, 2024
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-67285-9_22