Representation of Unstructured Data Across Common Data Models

Basic Details
Date Posted
Wednesday, July 14, 2021
Status
In progress
Description

A critical step in building the Sentinel network is to establish the organizational framework for expanding access to electronic health record (EHR) data. This includes structured data, particularly domains not found in administrative claims, such as laboratory results and inpatient medication administrations, as well as information derived from unstructured data such as free-text clinical notes. Unstructured data are of particular interest as they often include information that is not captured in any other source.

The goal of this project is to guide the Sentinel network on how best to incorporate information derived from unstructured data into a Common Data Model (CDM) framework. This project has three objectives: 

  • Identify priority elements that should be derived from unstructured data 
  • Assess the overall availability of the priority elements among potential data partners
  • Provide recommendations as to how those priority elements should be represented in the Sentinel Common Data Model (SCDM) 
Workgroup Leader(s)

Keith Marsolo, PhD; Lesley Curtis, PhD; Duke Clinical Research Institute, Durham, NC

Workgroup Member(s)

Sarah Palmer, MPH; Duke Clinical Research Institute, Durham, NC

Ruth Reeves, PhD; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN

Li Zhou, PhD, MD; Harvard Medical School and Brigham and Women’s Hospital, Boston, MA

Jeffrey Brown, PhD; Kathleen Shattuck, MPH; Department of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA

Sarah Dutcher, PhD, MS; Efe Eworuke, PhD; Aida Kuzucan, PharmD, PhD; Office of Surveillance and Epidemiology, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, MD