Does access modality matter? Evaluation of validity in reusing clinical care data

Abstract

Self-service database portals may improve access to institutional data resources for clinical research or quality improvement, but questions remain about the validity of this approach. We tested the accuracy of data extracted from a clinical data repository using a self-service portal by comparing three approaches to measuring medication use among patients with coronary disease: (1) automated extraction using a portal, (2) extraction by an experienced data architect, and (3) manual chart abstraction. Outcomes included medications and diagnoses (e.g., myocardial infarction, heart failure). Charts were manually reviewed for 200 patients. Using matched criteria, self-service query identified 7327 of 7358 patients identified by the data analyst. For patients in both cohorts, agreement rates ranged from 0.99 for demographic data to 0.94 for laboratory data. Based on chart review, the self-service portal and the analyst had similar sensitivities and specificities for comorbid diagnoses and statin use.