Abstract
INTRODUCTION: Oncology is a data-rich environment reflecting the increasing incidence of cancer in the US aging population, transformation of cancer into a chronic disease due to advances in treatment, and the emergence of new data categories such as genomics. Concomitantly, healthcare systems are challenged to meet regulatory and voluntary reporting of cancer data to support government, quality certification, research and strategic partnership needs. MATERIALS AND METHODS: The National Academies of Science, Engineering, and Medicine organized a workshop entitled "Enabling 21st-century applications for cancer surveillance through enhanced registries and beyond" with representation from NCI Comprehensive Cancer Centers, oncology and medical informatics professional societies, industry, CDC, NCI, and patient advocacy groups. RESULTS: The proliferation of cancer registries has resulted in heterogeneity in data vocabularies and data transport standards. Federal policy is complementing private initiatives to modernize cancer data architecture that would support a Learning Health System. However, business models are needed to provide sustained investments in data infrastructure. CONCLUSION: A computational approach to cancer registries would set the stage for interoperability and data sharing within a learning health ecosystem. Healthcare systems need to invest in their data infrastructure to improve data quality and adaptation of new data sources such as genomics and wearables. The ecosystem must evolve business models to sustain these investments.