The COVID-19 pandemic has highlighted the critical importance of robust health data ecosystems and efficient data-sharing architectures. The demand for timely, accurate, and comprehensive health data storage and exchange became paramount as the world faced an unprecedented public health crisis. The pandemic exposed several weaknesses in existing health information systems, including fragmented data silos, a lack of interoperability, and inadequate data sharing mechanisms. These challenges have highlighted the urgent need for interconnected health data systems that facilitate seamless data sharing across different platforms, regions, and sectors. In response to these challenges, the European Council has recognized the urgency of enhancing health data ecosystems across Europe, leading to the emergence of the European Health Data Space (EHDS) initiative. Central to this initiative is the European Electronic Health Record Exchange Format, designed to achieve interoperability of electronic health record data across Europe. Despite these advancements, the readiness of current guidelines and implementations, such as the European Patient Summary, to support secondary use in clinical research, particularly in cardiology, remains underexplored.
Methods:
The study aims to evaluate the European Patient Summary guidelines and their implementations, specifically the HL7 FHIR International Patient Summary Implementation Guide, to determine their suitability for secondary use in clinical research. The focus is on identifying gaps two ongoing EU-funded R&D projects were selected :DataTools4Heart and AI4HF. These projects were selected because they collectively address a broad range of clinical research questions in cardiology, covering use cases across all stages of care delivery: primary, secondary, and tertiary care.
As both projects utilize real-world EHR data to develop AI models specifically for HF patients, a common data model (CDM) was established to improve data interoperability while addressing data heterogeneity across European regions and cardiology units. The proposed CDM has been implemented by utilizing the HL7 FHIR standard in terms of data model and data access Application Programming Interfaces (APIs). Following the HL7 FHIR profiling approach, analyzing the requirements of each use case, a set of HL7 FHIR profiles, code systems, and value sets was developed and published (18). The effort was initiated in the DT4H project and continued in the scope of the AI4HF project. In this context, the CDM was examined and extended to address the needs of AI4HF, and it was later renamed the Common Data Model for Heart Failure Research.
