European Society of Cardiology joins effort to improve access to heart data
While the vast majority of patient data are now in digital formats, accessing them for research or population health initiatives can be quite difficult. A new initiative the European Society of Cardiology (ESC) is involved in hopes to remove certain barriers in Europe and make it easier to access those data.
The ESC said European hospitals generate large volumes of cardiology data during routine care, but much of it is not reusable for research. Not unlike U.S. health systems, data often remains inaccessible due to differences in data formats, challenging storage formats and interface issues. Europe also has additional barriers in that data is often in different languages, and privacy requirements differ from one country to the next.
To solve these issues, ESC is among 16 partner healthcare organizations involved with the creation of DataTools4Heart (DT4H). It is a Horizon Europe Research and Innovation Action targeting these barriers by developing a federated, privacy-preserving cardiology data toolbox. Rather than moving patient data between institutions, DT4H keeps data at the hospital and moves the analysis to the data. ESC said the DataTools4Heart platform is now entering its clinical testing phase.
“Having the federated learning backend running against real hospital data is the step that turns an architecture into a usable platform," Karim Lekadir, ICREA research professor at the University of Barcelona, director of the BCN-AIM lab and coordinator of DataTools4Heart, said in a statement. "What we learn from these first tests, particularly on data quality and missingness, will determine how the toolbox performs at the remaining sites."
The current testing phase will measure the platform’s performance and look for irregularities and gaps that are often found in real-world hospital records. The data ingestion IT has been developed to identify inconsistencies and coding errors early.
DataTools4Heart was created in response to ESC's call for a major shift toward integrative data-driven approaches to develop personalized cardiovascular medicine. The project includes multi-site federated health data from clinical centers in Spain, the Netherlands, United Kingdom, Italy, Sweden, Romania and Czech Republic. The data will serve as a representative sample of the European healthcare landscape and help create the European Health Data Space.
It introduces a multilingual natural language processing (NLP) suite to standardize the structuring of cardiology reports across Europe. This includes AI cardiology-specific entity recognition and machine translation.
The new platform integrates standardized data ingestion and harmonization tools based on a common data model. The technology will extract information from unstructured clinical text using federated machine learning that trains models across sites without centralizing patient data. It will use the anatomized information to generate synthetic data generation to aid in research, which then project calls CardioSynth.
In addition, virtual assistants will help clinicians and researchers navigate the data to make its utilization easier.
Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: [email protected]