Improving Accuracy of Electronic Notes Using a Faster, Simpler Approach (Washington)

Project Final Report (PDF, 817 KB) Disclaimer

This project does not have any related annual summary.

Project Details - Ended

Project Categories

Summary:

Physician progress notes contain information essential to patient care, including findings from physical exams, summary of laboratory tests, and care plans. This documentation is an important record for clinical care; communication with patients and care team members; and support of measurements of care quality, research, quality improvement, and billing. With the accelerated use of electronic medical records (EMRs), as incentivized by the American Recovery and Reinvestment Act, clinical notes are increasingly created using EMR documentation tools. The transition from paper to electronic documentation has many advantages, including permitting multiple providers to simultaneously access notes as well as providing improved legibility and the ability to more easily search notes.

Many problems with the creation and content of electronic notes have also been identified. The main concern voiced by physicians is that writing notes in EMRs takes more time than using paper or dictation. As notes are increasingly in electronic form, there is growing perception that the accuracy, quality, and readability of notes has declined. Most concerning is the perception that electronic notes cannot be trusted to accurately reflect what was observed during a patient encounter, which threatens the primary use of notes—to aid in caring for patients—and also use for scientific research.

This project will develop, use, and evaluate a new voice-generated, enhanced electronic note system (VGEENS) for creating electronic physician notes in the EMR. The goal of VGEENS is to improve accuracy and timely availability of inpatient progress notes. VGEENS uses voice recordings to create an accurate and professional appearing note by leveraging advances in voice recognition and natural language processing (NLP), rather than relying on a mouse, keyboard, and display screen. While voice recognition software has been in use in medical settings for quite some time, by itself it does not bring relevant patient EMR information into the note nor use NLP to create problem lists or other discrete data based on text, and it is not well-suited to clinical workflow. VGEENS will permit documentation to more closely fit workflow and to incorporate information from within the patient’s EMR in a tailored manner.

The specific aims of the project are as follows:

  • Refine and implement VGEENS and integrate it with voice recognition, NLP, and links to the EMR to improve note accuracy and timeliness 
  • Evaluate VGEENS using a randomized trial to assess electronic note accuracy, quality, timeliness, and user satisfaction 

VGEENS will be evaluated with a randomized trial. Intervention physicians will use VGEENS, while the control physicians will continue to use their standard method. This novel approach has the potential to improve note accuracy while reducing delays in making progress notes in EMRs available to other clinicians. It leverages rapidly improving voice recognition and NLP technologies to permit physicians to use a natural, fast method—human voice—to convey their observation and thoughts into the EMR record.

Improving Accuracy of Electronic Notes Using a Faster, Simpler Approach - Final Report

Citation:
Payne T. Improving Accuracy of Electronic Notes Using a Faster, Simpler Approach - Final Report. (Prepared by the University of Washington under Grant No. R21 HS023631). Rockville, MD: Agency for Healthcare Research and Quality, 2016. (PDF, 817 KB)

The findings and conclusions in this document are those of the author(s), who are responsible for its content, and do not necessarily represent the views of AHRQ. No statement in this report should be construed as an official position of AHRQ or of the U.S. Department of Health and Human Services.
Principal Investigator: 
Document Type: 
Population: 
This project does not have any related resource.
This project does not have any related survey.
This project does not have any related story.
This project does not have any related emerging lesson.