Time to use large-scale biobank databases in health policy and public health research

Large-scale biobank databases link data from thousands of participants and multiple sources such as electronic health records, surveys, imaging, and biomarkers. These data infrastructure research initiatives have the potential to inform health care and public health solutions that can address the needs of different populations, facilitate cross-sector collaboration, and improve the overall responsiveness of health care and public health systems. Despite this potential, large-scale biobanks are severely underutilized to answer health policy and public health research questions. Part of the reason is that information available in these data sources is usually collected for purposes such as improving health care within an integrated health care delivery system or advancing precision medicine. Still, the depth and breadth of these data collection efforts around the world together with advances in data science and artificial intelligence provide new opportunities to answer important health policy and public health questions using large-scale biobank data.