JMIR Publications

ABSTRACT

Background:

The widespread adoption of electronic health records (EHRs) has facilitated the secondary use of EHR data for clinical research. However, screening eligible patients from EHR is a challenging task. The concepts in eligibility criteria are not completely matched with EHR, especially for “derived concepts”. The lack of high-level expression of SQL makes it difficult and time-consuming to express them. The openEHR Expression language (openEHR EL) as a domain-specific language based on clinical information models shows promise to represent complex eligibility criteria.

Objective:

The study aims to develop a patient screening tool based on EHR for clinical research using openEHR to solve concepts mismatch and improve query performance.

Methods:

A patient screening tool based on EHRs using openEHR is proposed. It utilizes the advantages of information models and expression language in openEHR to provide high-level expressions and improve query performance. Firstly, openEHR archetypes and templates were chosen to define concepts called “simple concepts” from EHR directly. After, openEHR EL was utilized to generate “derived concepts” by combining simple concepts and constraints. Third, a hierarchical index corresponding to archetypes in Elasticsearch was generated to improve query performance for subqueries and join queries related to “derived concepts”. Finally, on top of these works, we realized a patient screening tool for clinical research.

Results:

500 sentences randomly selected from 4691 eligibility criteria in total 389 clinical trials about stroke from the Chinese Clinical Trial Registry (ChiCTR) were evaluated. An openEHR-based clinical data repository (CDR) in a Grade A tertiary hospital in China was considered as an experimental environment. Based on them, 589 medical concepts were found in these sentences. Among all of them, 513(87.1%) concepts can be represented, and the others cannot be represented because of a lack of information models and coarse-grained requirements. Also, our case study on 6 queries demonstrates our tool shows better query performance among 4 cases (66.67%).

Conclusions:

We develop a patient screening tool using openEHR. It not only helps solve concepts mismatch but also improves the query performance to reduce the burden on researchers. Also, we demonstrate the promising solution for secondary use of EHR data using openEHR which can be referenced by other researchers.