Skip to main content

Auto-Scribing Electronic Health Records (EHRs) with Natural Language Processing (NLP) and Autosummarization

Primary Investigators:
Taylor Johnson
 
Brief Description of Project:
Electronic Health Records (EHRs) are digital records consisting of clinical patient history. Healthcare providers (HCPs), such as physicians and nurses, create natural language notes for these EHRs during clinical encounters with patients, often times resulting in the HCP interacting with a computer for data entry instead of the patient. Through this project, we aim to revolutionize HCP data entry into EHR systems with a long-term vision of eliminating keyboard-and-mouse data entry. Our approach, implemented in a software prototype, uses machine learning methods for natural language processing (NLP) to provide speech-to-text and autosummarization of HCP and patient audio from interactions during patient clinical visits. This project will further develop and evaluate this approach to evaluate the benefits of such auto-scribing, such as improving patient outcomes, efficiency, and HCP satisfaction with EHRs.

Desired Qualifications:
Students at all levels (freshman through senior) are welcome and will be able to help refine our prototype system and approach. Programming experience in Matlab, Java, and Python would all be desirable. All code will be version controlled using Git/Mercurial, which experience with is desired, but not required.
 
Nature of Supervision:
The adviser will hold weekly group meetings with the undergraduates, current PhD students, and postdocs, as well as weekly individual meetings with undergraduate students. We will have several meetings in conjunction with collaborators in the VUMC. The current group members are available here: http://www.taylortjohnson.com/?m=people
 
A Brief Research Plan (period is for 10 weeks):
In the first 2-3 weeks, students will learn about electronic health records (EHRs), natural language processing (NLP), machine learning, and our existing prototype framework. In weeks 4-9, students will develop and test extensions to our framework and help to perform accuracy evaluations. In the final week, students will prepare and submit a written report describing their prototype enhancements, accuracy evaluation, and their experience with the research program. Students will present an oral presentation on their summer research in the final week.
 
Number of Open Slots: 2
 
Contact Information:
Name: Taylor T. Johnson
Title: Assistant Professor
Department: Electrical Engineering and Computer Science
Campus Address: ISIS 401D
Mailing Address: 1025 16th Avenue South Room 401D
Nashville, TN 37212
United States
Email: taylor.johnson@vanderbilt.edu
Phone: (615) 875-9057

Students at all levels (freshman through senior) are welcome and will be able to help refine our prototype system and approach. Programming experience in Matlab, Java, and Python would all be desirable. All code will be version controlled using Git/Mercurial, which experience with is desired, but not required.