Development of a surveillance system to identify incidence of evictions among patients in Veterans Affairs medical centers across the United States

Abstract: Evictions are a major social and public health concern in the United States. The development of Natural Language Processing (NLP) technologies allows for analysis of medical record notes to identify eviction cases in healthcare systems. The current study uses medical records data from the largest integrated healthcare system in the United States to develop a surveillance system to estimate incidence rates of NLP-identified evictions (NIEs) and associated patient characteristics. Data on over 8.5 million unique patients in the Veterans Affairs (VA) healthcare system from March 2018-March 2020 were analyzed and NLP was used to identify incidences of eviction. The 2-year incidence rate for NIEs was 2.38% (95% CI = 2.37-2.39%), with an annualized rate of 1.37% (95% CI = 1.36-1.38%). Logistic regression analyses found greater risk for NIEs among patients who were 45-64 years old, were male, non-Hispanic Black, were unmarried, had a high school education or less, had annual household income equal to or below $45,000, lived in an urban area, lived in a high area deprivation index, lived in the West region of the country, and had a history of military sexual trauma. Patients with a history of homelessness (aOR = 6.45; 95% CI = 6.36-6.54), and diagnoses of drug use disorder (aOR = 2.53; 95% CI = 2.49-2.57) or schizophrenia (aOR = 1.88; 95% CI = 1.83-1.93) were also at greater risk for NIEs. These findings suggest evictions are a rare, but important event among veterans, and may inform homeless prevention efforts by identifying veterans from certain backgrounds at greater risk. This study helps demonstrate the utility of using NLP for a surveillance system to identify evictions and track changes over time.

Read the full article
Report a problem with this article

Related articles

  • More for Researchers

    Relationship satisfaction change among UK service personnel: Associations with socio-demographics, military factors, and mental health

    Abstract: The unique demands of military life can adversely impact romantic relationships; however, research has mainly focused on these adverse outcomes at one-time point, overlooking changes over time or potential positive outcomes. Using a subsample of 3,845 male and female military personnel and veterans from a large UK dataset, this study examined positive and negative changes in relationship satisfaction between two-time points (2007–2009; 2014–2016). Most participants reported no change in their relationship satisfaction, suggesting stability − 8% reported a positive change and 10% a negative change. Positive change was associated with being in a long-term relationship, alcohol misuse remission, and persistent alcohol misuse. Negative change was associated with the onset of mental health problems (probable PTSD, CMD, or alcohol misuse) and having children under 18. Some factors, like increasing age, childhood family relationship adversity, and mental health problems, were associated with both positive and negative changes in relationship satisfaction. This study highlights the complexity of factors associated with relationship satisfaction among military personnel and veterans, with some experiencing positive changes, as well as negative changes over time.