Proceedings Released from the National Cancer Policy Forum's “Applying Big Data to Address the Social Determinants of Health in Oncology” Workshop; CBIIT Director Among Experts Who Presented
The National Academies of Sciences, Engineering, and Medicine's National Cancer Policy Forum hosted a workshop on October 28-29, 2019, "Applying Big Data to Address the Social Determinants of Health in Oncology," to address health disparities related to cancer research and treatment outcomes. The proceedings, which were recently published, illustrate the workshop goals of identifying social determinants of health (SDOH) and finding new ways to effectively leverage big data to improve health equity and reduce existing disparities.
CBIIT Director Dr. Tony Kerlavage, one of the expert presenters, noted that there is an unprecedented amount of data being produced in basic and clinical research and care delivery, and those data are increasingly generated from new sources. Such data have the ability to level the playing field when it comes to SDOH. By accurately collecting and analyzing large and diverse data sets, we can better address the inequity that exists today in oncology.
One of the biggest hurdles has been our inability to standardize large data sets to facilitate analysis. Dr. Kerlavage noted that we need to find ways to link cancer registry data with electronic health records, administrative claims data, the National Death Index, residential history, and environmental exposure data. These data would be invaluable for research on SDOH, but these linkages are difficult to achieve due to the lack of standardization.
"Using different analysis tools and IT infrastructures, which are not interoperable, [leads] to data collections being siloed from each other," he remarked. Some of these issues are being addressed through the use of Cloud-based commons, which amass large amounts of data and bring analysis tools to the data, rather than the reverse. Repositories of data analysis tools also are being created. Still, sharing statistical, artificial intelligence, and machine learning models will be critical for facilitating research. He added that researchers vary in their willingness to share such models, and, to date, there is no agreed-upon approach to encourage such sharing.
To promote better transparency and to advance science, Dr. Kerlavage suggested that researchers who share their data and tools should receive credit for doing so (e.g., through grant funding and promotion and tenure decisions).
To learn more about the discussions from Dr. Tony Kerlavage and others at the workshop, visit the National Academies Press website.