Hostname: page-component-7b7567c8c-wxvwp Total loading time: 0 Render date: 2026-11-18T21:56:46.991Z Has data issue: false hasContentIssue false

The ENACT network is acting on housing instability and the unhoused using the open health natural language processing toolkit

Published online by Cambridge University Press:  16 May 2024

Daniel R. Harris*
Affiliation:
Center for Clinical and Translational Sciences, University of Kentucky, Lexington, KY, USAInstitute for Biomedical Informatics, University of Kentucky, Lexington, KY, USA
Sunyang Fu
Affiliation:
Center for Translational AI Excellence and Applications in Medicine, University of Texas Health Science Center at Houston, Houston, TX, USA
Andrew Wen
Affiliation:
Center for Translational AI Excellence and Applications in Medicine, University of Texas Health Science Center at Houston, Houston, TX, USA
Alexandria Corbeau
Affiliation:
Center for Clinical and Translational Sciences, University of Kentucky, Lexington, KY, USAInstitute for Biomedical Informatics, University of Kentucky, Lexington, KY, USA
Darren Henderson
Affiliation:
Center for Clinical and Translational Sciences, University of Kentucky, Lexington, KY, USAInstitute for Biomedical Informatics, University of Kentucky, Lexington, KY, USA
Jordan Hilsman
Affiliation:
Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA, USA
David Oniani
Affiliation:
Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA, USA
Yanshan Wang
Affiliation:
Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA, USAClinical and Translational Science Institute, University of Pittsburgh, Pittsburgh, PA, USADepartment of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA
*
Corresponding author: D. R. Harris; Email: daniel.harris@uky.edu
Rights & Permissions [Opens in a new window]

Abstract

Housing is an environmental social determinant of health that is linked to mortality and clinical outcomes. We developed a lexicon of housing-related concepts and rule-based natural language processing methods for identifying these housing-related concepts within clinical text. We piloted our methods on several test cohorts: a synthetic cohort generated by ChatGPT for initial infrastructure testing, a cohort with substance use disorders (SUD), and a cohort diagnosed with problems related to housing and economic circumstances (HEC). Our methods successfully identified housing concepts in our ChatGPT notes (recall = 1.0, precision = 1.0), our SUD population (recall = 0.9798, precision = 0.9898), and our HEC population (recall = N/A, precision = 0.9160).

Information

Type
Brief Report
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.
Copyright
© The Author(s), 2024. Published by Cambridge University Press on behalf of Association for Clinical and Translational Science
Figure 0

Table 1.Housing-related concepts and phrases

Figure 1

Table 2.Performance using ENACT NLP rules

Figure 2

Table 3.Examples of errors

Figure 3

Table 4.Distribution of concepts per data set