Discovery and Visualization of New Information from Clinical Reports in the Electronic Health Record (Minnesota)

Project Details - Ended

Project Categories

Summary:

Although support for evidence-based medicine is high, tools to help clinicians navigate and synthesize the growing amount of electronic clinical data are limited. Electronic health records (EHRs) improve patient care by reducing redundancies that occur during prescribing and ordering processes. Yet, EHRs generate redundancies with other types of information, especially with unstructured text in clinical notes, which can lead to clinician information overload. Unstructured text in clinical notes is an important part of EHRs because it allows clinicians to communicate complex and nuanced information. Reviewing clinical notes, which is a necessary part of making diagnostic and therapeutic decisions, however, is hindered by many factors including redundant information, large numbers of documents, suboptimal text user interface (UI) design, and limited time to interact with patients.

The aim of this grant is to develop tools in the EHR for clinical notes to improve clinicians’ capacity to provide safe and effective care, especially for clinicians who follow complex patients whose care requires synthesis of many clinical elements across a lengthy medical history. The research team will apply probabilistic language modeling methods and improve automated methods to detect new information in patient notes. Visualization of the new information will then be improved by developing a note visualization tool. The new system will be evaluated in a randomized 6-9 month trial conducted among a group of hospitalists. The trial will evaluate documentation time, provider satisfaction, and EHR usage patterns. Additionally, using qualitative UI evaluation frameworks, the project team will develop principles for improving clinical note UIs. This will improve the understanding of key barriers and opportunities to improve the use of clinical notes in EHRs. 

The specific aims of the study are to:

  • Refine computational methods to identify new information in clinical notes.
  • Assess the effect of visualizing new information in clinical notes in an inpatient hospitalist setting.
  • Discover elements of a rationally designed EHR graphical UI to facilitate clinical document usage in practice.

Accomplishment of these aims will lay a foundation to improve clinicians’ efficiency, improve decisionmaking, decrease cognitive overload, and increase satisfaction with documentation mechanisms in EHR.

This project does not have any related annual summary.
This project does not have any related resource.
This project does not have any related survey.
This project does not have any related project spotlight.
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.