Tools to accurately identify veterans who undergo molecular diagnostic testing

201 Background: Yearly, 52,000 veterans are diagnosed with cancer. Minorities represent 18.5% (9,651) of these patients. The rapid and explosive growth of molecular diagnostics (MDx) has created challenges for large healthcare systems such as the Veterans Health Administration (VA) to integrate genomic data into the EMR. Yet, this is an important component of high quality cancer care. In 2011, the VA cancer registry (VACCR) began reporting molecular data. This presentation will describe one project to improve integration of genomics into the EMR and the VACCR. Methods: Using ICD diagnosis codes, we identified veterans diagnosed in 2011 with brain, breast, colon, gastrointestinal stromal, lung, and melanoma cancers. Administrative data was obtained to identify MDx testing. These data were then compared to random chart audits. Significant discrepancies between these sources of data prompted collaboration with national and proprietary reference labs (ARUP, LabCorp, Quest, Genomic Health) to obtain the volume of testing by each VAMC. These data were used to conduct targeted chart reviews to identify the location, processes of care, free and structured text information. These data informed the development of natural language processing (NLP) tools to automatically identify patients that underwent testing. Results: Laboratories had the most accurate source of data. Data from ARUP, Quest, and LabCorp identified a significantly higher volume of testing than reported by administrative data. Applying NLP tools to patients diagnosed with breast cancer identified 44 of the 116 tests ordered for the 21-gene risk score tests. Conclusions: Decision support systems are needed to link tumor SNOMED code to diagnostic testing. Until systems are developed, collaborations with reference labs may be an effective method for identifying molecular data. NLP tools may also serve as an adjunct method for capturing MDx tests ordered from smaller labs.