Project Summary

One of PCORI’s goals is to improve the methods that researchers use for patient-centered outcomes research. PCORI funds methods projects like this one to better understand and advance the use of research methods that improve the strength and quality of comparative effectiveness research.

This research project is in progress. PCORI will post the research findings on this page within 90 days after the results are final.

What is the research about?

Electronic health records, or EHRs, include a lot of information about a patient’s health such as test results, diagnoses, and treatments. EHRs also have notes that doctors and patients can use to track patients’ goals and decisions. These notes can be useful for research, but they can be hard for researchers to use, partly because there are many ways to describe the same thing. For example, high blood pressure may be called hypertension in the notes. The notes may also include abbreviations or spelling mistakes.

Internet search engines track millions of searches and use the choices people make to make better search suggestions. In this project, the research team wants to use similar methods to make EHR notes easier to search and use for research.

Who can this research help?

Researchers can use results from this project when planning how to collect and study patient information in EHRs.

What is the research team doing?

The research team is creating a new search engine for EHRs to help users find what they are looking for and to suggest related search terms. The search engine looks at words that often appear together in EHR notes and the types of searches people conduct if they don’t find what they want on the first try.

To test the search engine, the research team is looking for EHR notes on topics such as obesity, rehabilitation after stroke, and appendicitis. Patients, clinicians, and other researchers are working with the team to plan and conduct the study.

Research methods at a glance

Design Elements Description
Goal Develop an EHR text search engine
Approach
  • Develop a text search engine that uses word embedding and knowledge bases to suggest and categorize potential related phrases
  • Test search engine using PCOR use cases

Project Information

Yungui Huang
Huan Sun, PhD
Nationwide Children's Hospital/The Ohio State University
$1,060,000
Unlocking Clinical Text in EMR by Query Refinement Using Both Knowledge Bases and Word Embedding

Key Dates

November 2017
March 2022
2017

Study Registration Information

Tags

Award Type
State State The state where the project originates, or where the primary institution or organization is located. View Glossary
Last updated: March 14, 2022