Assessing longitudinal housing status using Electronic Health Record data: a comparison of natural language processing, structured data, and patient-reported history

Alec B Chapman; Kristina Cordasco; Stephanie Chassman; Talia Panadero; Dylan Agans; Nicholas Jackson; Kimberly Clair; Richard Nelson; Ann Elizabeth Montgomery; Jack Tsai; Erin Finley; Sonya Gabrielian

doi:10.3389/frai.2023.1187501

Assessing longitudinal housing status using Electronic Health Record data: a comparison of natural language processing, structured data, and patient-reported history

Front Artif Intell. 2023 May 24:6:1187501. doi: 10.3389/frai.2023.1187501. eCollection 2023.

Authors

Alec B Chapman^{1

2}, Kristina Cordasco^{3

4}, Stephanie Chassman^{3

5}, Talia Panadero^{3

6}, Dylan Agans^{3

7}, Nicholas Jackson^{3

8}, Kimberly Clair³, Richard Nelson^{1

2}, Ann Elizabeth Montgomery^{9

10}, Jack Tsai¹¹, Erin Finley⁹, Sonya Gabrielian^{3

12}

Affiliations

¹ Informatics, Decision-Enhancement and Analytic Sciences (IDEAS) Center, Salt Lake City Veterans Affairs Healthcare System, Salt Lake City, UT, United States.
² Division of Epidemiology, University of Utah, School of Medicine, Salt Lake City, UT, United States.
³ Center for the Study of Healthcare Innovation, Implementation and Policy (CSHIIP), Greater Los Angeles Veterans Affairs Healthcare System, Los Angeles, CA, United States.
⁴ Department of Medicine, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.
⁵ Desert Pacific Mental Illness Research, Education, and Clinical Center (MIRECC), Veterans Affairs Greater Los Angeles, Los Angeles, CA, United States.
⁶ Department of Epidemiology, Fielding School of Public Health, University of California, Los Angeles, Los Angeles, CA, United States.
⁷ Department of Community Health Sciences, Fielding School of Public Health, University of California, Los Angeles, Los Angeles, CA, United States.
⁸ Department of Medicine Statistics Core, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.
⁹ United States Department of Veteran Affairs, Birmingham Veterans Affairs Health Care System, Birmingham, AL, United States.
¹⁰ School of Public Health, University of Alabama at Birmingham, Birmingham, AL, United States.
¹¹ National Homeless Programs Office, United States Department of Veterans Affairs, Washington, DC, United States.
¹² Department of Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.

Abstract

Introduction: Measuring long-term housing outcomes is important for evaluating the impacts of services for individuals with homeless experience. However, assessing long-term housing status using traditional methods is challenging. The Veterans Affairs (VA) Electronic Health Record (EHR) provides detailed data for a large population of patients with homeless experiences and contains several indicators of housing instability, including structured data elements (e.g., diagnosis codes) and free-text clinical narratives. However, the validity of each of these data elements for measuring housing stability over time is not well-studied.

Methods: We compared VA EHR indicators of housing instability, including information extracted from clinical notes using natural language processing (NLP), with patient-reported housing outcomes in a cohort of homeless-experienced Veterans.

Results: NLP achieved higher sensitivity and specificity than standard diagnosis codes for detecting episodes of unstable housing. Other structured data elements in the VA EHR showed promising performance, particularly when combined with NLP.

Discussion: Evaluation efforts and research studies assessing longitudinal housing outcomes should incorporate multiple data sources of documentation to achieve optimal performance.

Keywords: electronic health records; homelessness; natural language processing; social determinants of health; veterans affairs.

Grants and funding

This study was supported by QUERI-VISN (Quality Enhancement Research Initiative-Veterans Integrated Services Networks) Partnered Implementation Initiative (PII) 21-285 (Multiple Principal Investigators: Gabrielian, Cordasco, Finley).