Association between patient-reported social and behavioral risks and health care costs in high-risk Veterans Health Administration patients
Abstract: Social risks complicate patients' ability to manage their conditions and access healthcare, but their association with health expenditures is not well established. To identify patient-reported social risk, behavioral, and health factors associated with health expenditures in Veterans Affairs (VA) patients at high risk for hospitalization or death. Prospective cohort study among high-risk Veterans obtaining VA care. Patient-reported social risk, function, and other measures derived from a 2018 survey sent to 10,000 VA patients were linked to clinical and demographic characteristics extracted from VA data. Response-weighted generalized linear and marginalized two-part models were used to examine VA expenditures (total, outpatient, medication, inpatient) 1 year after survey completion in adjusted models. Among 4680 survey respondents, the average age was 70.9 years, 6.3% were female, 16.7% were African American, 20% had body mass index ≥35, 42.4% had difficulty with two or more basic or instrumental activities of daily living, 19.3% reported transportation barriers, 12.5% reported medication insecurity and 21.8% reported food insecurity. Medication insecurity was associated with lower outpatient expenditures (−$1859.51 per patient per year, 95% confidence interval [CI]: −3200.77 to −518.25) and lower total expenditures (−$4304.99 per patient per year, 95% CI: −7564.87 to −1045.10). Transportation barriers were negatively associated with medication expenditures (−$558.42, 95% CI: −1087.93 to −31.91). Patients with one functional impairment had higher outpatient expenditures ($2997.59 per patient year, 95% CI: 1185.81–4809.36) than patients without functional impairments. No social risks were associated with inpatient expenditures. In this study of VA patients at high risk for hospitalization and mortality, few social and functional measures were independently associated with the costs of VA care. Individuals with functional limitations and those with barriers to accessing medications and transportation may benefit from targeted interventions to ensure that they are receiving the services that they need.
Abstract: Novel and automated means of opioid use and relapse risk detection are needed. Unstructured electronic medical record data, including written progress notes, can be mined for clinically relevant information, including the presence of substance use and relapse-critical markers of risk and recovery from opioid use disorder (OUD). In this study, we used natural language processing (NLP) to automate the extraction of opioid relapses, and the timing of these occurrences, from veteran patients' electronic medical record. We then demonstrated the utility of our NLP tool via analysis of pre-/post-COVID-19 opioid relapse trends among veterans with OUD. For this demonstration, we analyzed data from 107,606 veterans OUD enrolled in Veterans Health Administration, comparing a pandemic-exposed cohort (n = 53,803; January 2019-March 2021) to a matched prepandemic cohort (n = 53,803; October 2017-December 2019). The recall of our NLP tool was 75% and our precision was 94%, demonstrating moderate sensitivity and excellent specificity. Using the NLP tool, we found that the odds of opioid relapse postpandemic onset were proportionally higher compared to prepandemic trends, despite patients having fewer mental health encounters from which to derive instances of relapse postpandemic onset. In this research application of the tool, and as hypothesized, we found that opioid relapse risk was elevated postpandemic. The application of NLP Methods: to identify and monitor relapse risk holds promise for future surveillance, risk prevention, and clinical outcome research.