The Optum® longitudinal clinical repository from Humedica is derived from healthcare provider organizations in the US that include more than 700 hospitals and 7000 clinics treating more than 105 million patients receiving care. The data are certified as de-identified by an independent statistical expert following HIPAA statistical de-identification rules, and managed according to Optum® customer data use agreements. Clinical claims and other medical administrative data are obtained from both inpatient and ambulatory electronic health records (EHR), practice management systems, and numerous other internal systems, and are processed, normalized, and standardized across the continuum of care, from both acute inpatient stays and outpatient visits. Optum® data elements include demographics; medications prescribed and administered; immunizations; allergies; lab results (including microbiology); vital signs and other observable measurements; clinical and inpatient stay administrative data; and coded diagnoses and procedures. In addition, Optum® uses natural language processing (NLP) computing technology to extract critical facts from physician notes into usable datasets. The NLP data provide detailed information regarding signs and symptoms, family history, disease-related scores (eg, RAPID3 for rheumatoid arthritis or CHADS2 for stroke risk), genetic testing, medication changes, and physician rationale behind prescribing decisions that might never be recorded in the EHR.¹