Health Data Set Bias Examination in the European Health Data Space

Diversity in health datasets is a necessary, quantifiable property of inclusivity across key domains (e.g., demographic, socioeconomic, health, and environmental) that directly shapes how well research generalizes and how fair its impacts are. In its absence, interventions risk encoding bias and exacerbating health disparities. In this work, we outline how dataset diversity can be measured and how these measures can be surfaced in the EHDS via metadata. We argue that simple annotations are insufficient: structured interaction with the data owner is required to assess the utility of health datasets for specific research purposes.