Creating a Learning Health System in a Cancer Center: Generalizability of an Electronic Health Record Phenotype for Advanced Solid Cancer.

Abstract

To test the generalizability of an electronic health record (EHR) phenotype for patients with advanced solid cancer, which was previously developed in a single cancer center. We compared an algorithm to identify patients with advanced solid cancer from a random sample of patients with active cancer in the Veterans Health Administration (VA) and an academic cancer center with a human-coded reference standard between January 1, 2016, and December 31, 2019. Compared with the human-coded reference standard, the algorithm had high specificity (93%; 95% CI, 87 to 99 and 97%; 95% CI, 93 to 100) and reasonable sensitivity (85%; 95% CI, 76 to 94 and 87%; 95% CI, 77 to 97) in the VA and academic cancer center populations, respectively. Patients with advanced cancer (compared with those with active nonadvanced cancer) had higher mortality at the VA and academic cancer center (29.2% and 17.0% 6-month mortality <i>v</i> 6.8% and 3.5%), respectively. This EHR phenotype can be used to measure and improve the quality of palliative care for patients with advanced cancer within and across health care settings.