Evolving From Discrete Molecular Data Integrations to Actionable Molecular Insights Within the Electronic Health Record

Abstract

Critical decisions in oncology treatment today rely on understanding the molecular composition of the malignancy. In this era of rapidly changing technology, such as generative artificial intelligence (AI), discrete incorporation of molecular data including the results of DNA nextgeneration sequencing (NGS), RNA NGS, and immunohistochemistry testing remains essential for characterizing molecular cancer subtypes and selecting the right targeted therapies at the right doses. 1,2 The electronic health record (EHR) is often considered to be a single location where clinicians review patient profiles, order molecular testing, and view results with associated treatment recommendations through clinical decision support (CDS) tools. 3,4 However, EHRs were initially designed as billing tools rather than patient management tools 5 and may provide data without any insight, context, integration, or value to improve management.