Using electronic health record metadata to predict housing instability amongst veterans
Housing instability is considered a significant life stressor and preemptive screening should be applied to identify those at risk for homelessness as early as possible so that they can be targeted for specialized care. We developed models to classify patient outcomes for an established VA Homelessn...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Preventive Medicine Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2211335523003960 |
| _version_ | 1797366600801714176 |
|---|---|
| author | Rafael Zamora-Resendiz David W. Oslin Dina Hooshyar Silvia Crivelli |
| author_facet | Rafael Zamora-Resendiz David W. Oslin Dina Hooshyar Silvia Crivelli |
| author_sort | Rafael Zamora-Resendiz |
| collection | DOAJ |
| description | Housing instability is considered a significant life stressor and preemptive screening should be applied to identify those at risk for homelessness as early as possible so that they can be targeted for specialized care. We developed models to classify patient outcomes for an established VA Homelessness Screening Clinical Reminder (HSCR), which identifies housing instability, in the two months prior to its administration. Logistic Regression and Random Forest models were fit to classify responses using the last 18 months of document activity. We measure concentration of risk across stratifications of predicted probability and observe an enriched likelihood of finding confirmed false negative responses from veterans with diagnosed housing instability. Positive responses were 34 times more likely to be detected within the top 1 % of patients predicted at risk than from those randomly selected. There is a 1 in 4 chance of detecting false negatives within the top 1 % of predicted risk. Machine learning methods can classify between episodes of housing instability using a data-driven approach that does not rely on variables curated from domain experts. This method has the potential to improve clinicians’ ability to identify veterans who are experiencing housing instability but are not captured by HSCR. |
| first_indexed | 2024-03-08T17:07:08Z |
| format | Article |
| id | doaj.art-a3bae77bbbb144bea67788c95cb5f197 |
| institution | Directory Open Access Journal |
| issn | 2211-3355 |
| language | English |
| last_indexed | 2024-03-08T17:07:08Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Preventive Medicine Reports |
| spelling | doaj.art-a3bae77bbbb144bea67788c95cb5f1972024-01-04T04:39:23ZengElsevierPreventive Medicine Reports2211-33552024-01-0137102505Using electronic health record metadata to predict housing instability amongst veteransRafael Zamora-Resendiz0David W. Oslin1Dina Hooshyar2Silvia Crivelli3Applied Mathematics & Computational Research Division, Lawrence Berkeley National Laboratory, US Department of Energy, Berkeley, CA, United States; Corresponding author.CPL. Michael J. Crescenz VA Medical Center (Philadelphia), Perelman School of Medicine, University of Pennsylvania Philadelphia, PA, United StatesNational Center on Homelessness among Veterans (the Center) Associate Professor, Department of Psychiatry, University of Texas Southwestern Medical Center, TX, United StatesApplied Mathematics & Computational Research Division, Lawrence Berkeley National Laboratory, US Department of Energy, Berkeley, CA, United StatesHousing instability is considered a significant life stressor and preemptive screening should be applied to identify those at risk for homelessness as early as possible so that they can be targeted for specialized care. We developed models to classify patient outcomes for an established VA Homelessness Screening Clinical Reminder (HSCR), which identifies housing instability, in the two months prior to its administration. Logistic Regression and Random Forest models were fit to classify responses using the last 18 months of document activity. We measure concentration of risk across stratifications of predicted probability and observe an enriched likelihood of finding confirmed false negative responses from veterans with diagnosed housing instability. Positive responses were 34 times more likely to be detected within the top 1 % of patients predicted at risk than from those randomly selected. There is a 1 in 4 chance of detecting false negatives within the top 1 % of predicted risk. Machine learning methods can classify between episodes of housing instability using a data-driven approach that does not rely on variables curated from domain experts. This method has the potential to improve clinicians’ ability to identify veterans who are experiencing housing instability but are not captured by HSCR.http://www.sciencedirect.com/science/article/pii/S2211335523003960Homelessness screeningDocument metadataElectronic healthcare recordsVeteran healthMachine learning |
| spellingShingle | Rafael Zamora-Resendiz David W. Oslin Dina Hooshyar Silvia Crivelli Using electronic health record metadata to predict housing instability amongst veterans Preventive Medicine Reports Homelessness screening Document metadata Electronic healthcare records Veteran health Machine learning |
| title | Using electronic health record metadata to predict housing instability amongst veterans |
| title_full | Using electronic health record metadata to predict housing instability amongst veterans |
| title_fullStr | Using electronic health record metadata to predict housing instability amongst veterans |
| title_full_unstemmed | Using electronic health record metadata to predict housing instability amongst veterans |
| title_short | Using electronic health record metadata to predict housing instability amongst veterans |
| title_sort | using electronic health record metadata to predict housing instability amongst veterans |
| topic | Homelessness screening Document metadata Electronic healthcare records Veteran health Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2211335523003960 |
| work_keys_str_mv | AT rafaelzamoraresendiz usingelectronichealthrecordmetadatatopredicthousinginstabilityamongstveterans AT davidwoslin usingelectronichealthrecordmetadatatopredicthousinginstabilityamongstveterans AT dinahooshyar usingelectronichealthrecordmetadatatopredicthousinginstabilityamongstveterans AT silviacrivelli usingelectronichealthrecordmetadatatopredicthousinginstabilityamongstveterans |