Follow us on X
Follow us on Linkedin
Real-world-data enabled assessment
for health regulatory decision-making

REALM at the fifth European OHDSI Symposium

The fifth European OHDSI Symposium, "Scaling up reliable evidence across Europe", was held from June 1st - 3rd, 2024, at Steam Ship in Rotterdam, the Netherlands.

OHDSI’s mission is to improve health by empowering a community to collaboratively generate evidence that promotes better health decisions and better care. The symposium gathers different profiles - patients, health professionals, researchers and others.

REALM is an ambitious initiative aimed at evaluating AI models using a diverse range of data, including EHR, genomics, and radiology. To achieve this, we are developing a data catalogue that aggregates multiple data sources. Our commitment to the European Commission includes providing a transparent methodology for evaluating AI models by creating a reproducible way of generating test subsets from various data sources. By adopting the OMOP CDM with specific extensions, we ensure consistency and reliability across our datasets.

At the OHDSI Symposium, we highlighted our progress, focusing on two main areas: (1) designing the OMOP CDM environment and (2) demonstrating the capabilities of the REALM OMOP data catalog. Specifically, we showcased its application in evaluating our first AI model use case for COPD, developed by our partner TraqBeat. This presentation underscored our dedication to creating a robust infrastructure for AI model evaluation, emphasizing transparency and reproducibility.

Our partner, Frederic Jung from VITO, attended the event and presented our standardization efforts in adopting the OMOP Common Data Model (CDM). REALM participated with two posters. The first titled Harmonizing Public Research Access Datasets for AI Advancements in Asthma/ COPD Diagnosis is a joint effort from VITO, Maastricht University and Traqbeat technologies.

The second is titled Advancing Certification and Evaluation of Medical Device Software in the EU using OMOP which is a joint effort of VITO and Maastricht University.

For a glimpse of the atmosphere take a look at the gallery below.

Learn more about the event: