A Systematic Process for Assessing Fitness-for-Purpose of Health Outcomes for Computable Phenotyping with Electronic Health Records Data

Health insurance claims data currently form the backbone of the Sentinel Distributed Database (SDD), owing to their complete capture of outpatient pharmacy dispensing records, medical encounters, and hospitalizations during well-defined periods of health plan enrollment. However, due to limitations inherent to claims data, Sentinel’s Active Risk Identification and Analysis (ARIA) system is, at times, deemed insufficient to address a regulatory question of interest, e.g., due to the lack of granular clinical information available. 

In an effort to minimize this occurrence and enhance the SDD, the Sentinel Innovation Center (IC) has undertaken efforts to establish a query-ready, quality-checked distributed data network linking longitudinal electronic health records (EHRs) with claims data for 21 million patients from two large commercial data assets, HealthVerity and TriNetX. This project aims to build on these previous efforts by reviewing a selection of health outcomes of interest for which typical ARIA analyses were previously determined to be insufficient due to poor outcome identification, and conducting fitness-for-purpose (FFP) analyses to make recommendations regarding the likelihood of successful development of computable phenotype algorithms by incorporating rich EHR data and data-driven modeling methods (using data from the EHR-claims linked system).

This Sentinel Innovation Center (IC) project is led by Kaiser Permanente Washington Health Research Institute in collaboration with the Harvard Pilgrim Health Care Institute and Harvard Medical School.