event-icon
Description

Abstract: Much effort has been devoted to leverage EHR data for matching patients into clinical trials. However, EHRs may not contain all important data elements for clinical research eligibility screening. To better design research-friendly EHRs, an important step is to identify data elements frequently used for eligibility screening but not yet available in EHRs. This study fills this knowledge gap. Using the Alzheimer’s disease domain as an example, we performed text mining on the eligibility criteria text in Clinicaltrials.gov to identify frequently used eligibility criteria concepts. We compared them to the EHR data elements of a cohort of Alzheimer’s Disease patients to assess the data gap by using the OMOP Common Data Model to standardize the representations for both criteria concepts and EHR data elements. We identified the most common SNOMED CT concepts used in Alzheimer’s Disease trials, and found 40% of common eligibility criteria concepts were not even defined in the concept space in the EHR dataset for a cohort of Alzheimer’s Disease patients, indicating a significant data gap may impede EHR-based eligibility screening. The results of this study can be useful for designing targeted research data collection forms to help fill the data gap in the EHR.

Learning Objective 1: Recognize disparity between eligibility criteria in Alzheimer's Disease clinical trials and available information in Electronic Health Records.

Authors:

Alex Butler (Presenter)
Columbia University College of Physicians & Surgeons

Wei Wei, Columbia University College of Physicians & Surgeons
Chi Yuan, Columbia University College of Physicians & Surgeons
Tian Kang, Columbia University College of Physicians & Surgeons
Yuqi Si, The University of Texas Health Science Center at Houston
Chunhua Weng, Columbia University College of Physicians & Surgeons

Presentation Materials:

Keywords