EU project combining European cardiology data in different formats and languages to create easy-to-use cardiology toolbox moves into second phase

The DataTools4Heart project, which is now entering its second phase, aims to accelerate and simplify the work of clinical physicians, enable secure data sharing, support research and innovation in medical technologies, and most importantly, improve the quality of life for patients with cardiovascular diseases. Very soon, participants will begin the practical implementation of the developed software, integration of tools into a unified interface, and involvement of clinical experts who will help optimize user-friendliness and ensure seamless functionality of the tool.

Cardiovascular disease is the leading cause of death globally. Until now, cardiology data that could advance research and healthcare has remained unused in hospitals across Europe. This is due to data privacy requirements and variations in data formats and languages. To tackle these challenges, DT4H will extract, translate, and reuse data in a federated manner, i.e. without the information being shared with anyone or transferred out of the hospital.

To address these challenges, the DataTools4Heart (DT4H) project was launched, with participation from physicians at St. Anne’s University Hospital and scientists from the International Clinical Research Center (ICRC) in Brno. The aim of the project is to develop and implement a comprehensive cardiology tool designed for physicians, researchers, and data specialists. Within DT4H, software tools are being developed to extract cardiology data, convert it into a standardized format, and analyze it using a so-called federated approach.

“Collected data remains within the hospitals, including the execution of necessary analyses, which are performed based on a unified query system across all participating clinical centers. This minimizes the risk of data leakage while ensuring highly efficient use of the data,” explains Pavel Leinveber, Head of the Biomedical Engineering team at the International Clinical Research Center (ICRC), a joint workplace of St. Anne’s University Hospital and the Faculty of Medicine at Masaryk University.

The first version of the software, planned for release by the end of 2025, will enable effective management of a federated network for machine learning. “This opens the door to collaboration between institutions without compromising patient privacy. DT4H builds better artificial intelligence models from diverse datasets while strictly adhering to ethical standards. It’s a crucial step toward secure cooperation across clinical and research institutions. The developers are working closely with clinical physicians, who provide them with regular feedback. As a result, the final product will meet the practical needs of healthcare facilities,” says Roman Panovský, cardiologist and head of the Noninvasive Cardiac Imaging research team at the ICRC.

The overarching aim for DT4H is a commitment to advancing federated learning solutions for healthcare. Thus, the consortium is preparing for important developments through the following key actions for 2025:

  • Deployment of Stable Software Versions: By deploying the first stable versions of its software, the project will efficiently manage the federated learning network. This technical milestone represents a significant step forward in enabling secure, privacy-preserving collaboration across clinical and research institutions. The first stable version of the platform is expected to be released by the end of 2025.
  • Integration of Applications into a Unified Interface: To enhance usability and streamline workflows, the project has initiated two dedicated working groups focused on integrating diverse applications into a single, cohesive user interface. This effort ensures that users can access all functionalities seamlessly within one platform. Clinicians and researchers will gain access to powerful functionalities, including the ability to extract meaningful statistics from diverse demographic groups, convert unstructured data into structured formats, and perform AI-driven analyses—all without requiring programming expertise. Additionally, they can retrieve explainable insights that can seamlessly integrate into clinical practice, enhancing decision-making and patient care.
  • Clinician Engagement for Tool Optimization: Usability by physicians, researchers and data scientists is key to the success of DT4H. Recognising the importance of end-user needs, the project has launched a validation and request working group that collaborates closely with clinicians. These sessions aim to gather insights into analytical requirements and usability preferences, ensuring the resulting tools are both practical and user-friendly for clinical environments.

The first clinical analysis using the DT4H platform is anticipated to commence by mid-2025. Eight hospitals covering seven languages (Spanish, Dutch, Swedish, English, Czech, Italian and Romanian) will continue testing the system using actual clinical questions from their outpatient and emergency departments. Multilingual, AI-powered virtual assistants will help clinician researchers to navigate through the platform and data.

These eight hospitals are:

  • Universitair Medisch Centrum Utrecht, Netherlands.
  • Fondazione Policlínico Universitario Agostino Gemelli IRCCS, Italy.
  • Fundacio Hospital Universitari Vall d’Hebron – Institut De Recerca VHIR, Barcelona, Spain.
  • Spitalul Clinic De Urgenta Bucuresti, Romania.
  • Fakultní nemocnice u sv. Anny v Brně, Czech Republic
  • Academisch Medisch Centrum Bij De Universiteit Van Amsterdam AMC, Netherlands.
  • University College London, UK.
  • Region Stockholm, Sweden.

The results of these analyses, along with demonstrations of the software, will be unveiled at public forums and conferences later in the year, including the ESC Congress in Madrid (29 August- 1 September). There will be a dedicated session to the project, where the first results with real-world data are expected to be presented to delegates.  These events will provide an opportunity to showcase the project’s potential to revolutionise healthcare data analysis through federated learning.