Material financial hardship and insurance-related experiences among Utah's rural and urban cancer survivors.

PURPOSE: Describe material financial hardship (e.g., using savings, credit card debt), insurance, and access to care experienced by Utah cancer survivors; investigate urban-rural differences in financial hardship. METHODS: Cancer survivors were surveyed from 2018 to 2021 about their experiences with financial hardship, access to healthcare, and job lock (insurance preventing employment changes). Weighed percentage responses, univariable and multivariable logistic regression models for these outcomes compared differences in survivors living in rural and urban areas based on Rural-Urban Commuting Area Codes. RESULTS: The N = 1793 participants were predominantly Non-Hispanic White, female, and 65 or older at time of survey. More urban than rural survivors had a college degree (39.8% vs. 31.0%, p = 0.04). Overall, 35% of survivors experienced ≥ 1 financial hardship. In adjusted analyses, no differences were observed between urban and rural survivors for: material financial hardship, the overall amount of hardship reported, insurance status at survey, access to healthcare, or job lock. Hispanic rural survivors were less likely to report financial hardship than Hispanic urban survivors (odds ratio (OR) = 0.24, 95%CI = 0.08-0.73)). Rural survivors who received chemo/immune therapy as their only treatment were more likely to report at least one instance of financial hardship than urban survivors (OR = 2.72, 95%CI = 1.08-6.86). CONCLUSIONS: The relationship between rurality and financial hardship among survivors may be most burdensome for patients whose treatments require travel or specialty medication access. IMPLICATIONS FOR CANCER SURVIVORS: The impact of living rurally on financial difficulties after cancer diagnoses is complex. Features of rurality that may alter financial difficulty after a cancer diagnosis may vary geographically and instead of considering rurality as a stand-alone factor, these features should be investigated independently.

Accuracy of patient race and ethnicity data in a central cancer registry.

PURPOSE: Race and Hispanic ethnicity data can be challenging for central cancer registries to collect. We evaluated the accuracy of the race and Hispanic ethnicity variables collected by the Utah Cancer Registry compared to self-report. METHODS: Participants were 3,162 cancer survivors who completed questionnaires administered in 2015-2022 by the Utah Cancer Registry. Each survey included separate questions collecting race and Hispanic ethnicity, respectively. Registry-collected race and Hispanic ethnicity were compared to self-reported values for the same individuals. We calculated sensitivity and specificity for each race category and Hispanic ethnicity separately. RESULTS: Survey participants included 323 (10.2%) survivors identifying as Hispanic, a lower proportion Hispanic than the 12.1% in the registry Hispanic variable (sensitivity 88.2%, specificity 96.5%). For race, 43 participants (1.4%) self-identified as American Indian or Alaska Native (AIAN), 32 (1.0%) as Asian, 23 (0.7%) as Black or African American, 16 (0.5%) Pacific Islander (PI), and 2994 (94.7%) as White. The registry race variable classified a smaller proportion of survivors as members of each of these race groups except White. Sensitivity for classification of race as AIAN was 9.3%, Asian 40.6%, Black 60.9%, PI 25.0%, and specificity for each of these groups was > 99%. Sensitivity and specificity for White were 98.8% and 47.4%. CONCLUSION: Cancer registry race and Hispanic ethnicity data often did not match the individual's self-identification. Of particular concern is the high proportion of AIAN individuals whose race is misclassified. Continued attention should be directed to the accurate capture of race and ethnicity data by hospitals.

Cancer survivorship experiences in Utah: an evaluation assessing indicators of survivors' quality of life, health behaviors, and access to health services.

PURPOSE: The 2016-2020 Utah Comprehensive Cancer Prevention and Control Plan prioritized strategies to address cancer survivorship experiences. In this paper we present estimates for nine indicators evaluating these priorities, trends over time, and assess disparities in survivorship experiences across demographic subgroups. METHODS: We surveyed a representative sample of Utah cancer survivors diagnosed between 2012 and 2019 with any reportable cancer diagnosis. We calculated weighted percentages and 95% confidence intervals (CI) for each indicator. We assessed change over time using a test for trend across survey years in a logistic regression model and used Rao-Scott F-adjusted chi-square tests to test the association between demographic characteristics and each survivorship indicator. RESULTS: Most of the 1,793 respondents (93.5%) reported their pain was under control, 85.7% rated their overall health as good, very good, or excellent, but 46.5% experienced physical, mental, or emotional limitations. Only 1.7% of survivors aged 75 or older were current smokers, compared to 5.8% of 65-74-year-olds and 7.9% of survivors aged 55-74 (p < 0.006). No regular physical activity was reported by 20.6% and varied by survivor age and education level. The proportion who received a survivorship care plan increased from 34.6% in 2018 to 43.0% in 2021 (p = 0.025). However, survivors under age 55 were significantly less likely to receive a care plan than older survivors. CONCLUSION: This representative survey of cancer survivors fills a gap in understanding of the cancer survivorship experience in Utah. Results can be used to evaluate and plan additional interventions to improve survivorship quality of life.

Cancer survivors' financial hardship and their caregivers' employment: results from a statewide survey.

PURPOSE: Many caregivers take paid and/or unpaid time off work, change from full-time to part-time, or leave the workforce. We hypothesized that cancer survivor-reported material hardship (e.g., loans, bankruptcy), behavioral hardship (e.g., skipping care/medication due to cost), and job lock (i.e., staying at a job for fear of losing insurance) would be associated with caregiver employment changes. METHODS: Adult cancer survivors (N = 627) were surveyed through the Utah Cancer Registry in 2018-2019, and reported whether their caregiver had changed employment because of their cancer (yes, no). Material hardship was measured by 9 items which we categorized by the number of instances reported (0, 1-2, and ≥ 3). Two items represented both behavioral hardship (not seeing doctor/did not take medication because of cost) and survivor/spouse job lock. Odds ratios (OR) were estimated using survey-weighted logistic regression to examine the association of caregiver employment changes with material and behavioral hardship and job lock, adjusting for cancer and sociodemographic factors. RESULTS: There were 183 (29.2%) survivors reporting their caregiver had an employment change. Survivors with ≥ 3 material hardships (OR = 3.13, 95%CI 1.68-5.83), who skipped doctor appointments (OR = 2.88, 95%CI 1.42-5.83), and reported job lock (OR = 2.05, 95%CI 1.24-3.39) and spousal job lock (OR = 2.19, 95%CI 1.17-4.11) had higher odds of caregiver employment changes than those without these hardships. CONCLUSIONS: Caregiver employment changes that occur because of a cancer diagnosis are indicative of financial hardship. IMPLICATIONS FOR CANCER SURVIVORS: Engaging community and hospital support for maintenance of stable caregiver employment and insurance coverage during cancer may lessen survivors' financial hardship.

Adherence to Guideline-Recommended cancer screening among Utah cancer survivors.

BACKGROUND: Adherence to cancer screening is important for cancer survivors because they are at high risk of subsequent cancer diagnoses or recurrence. We assessed adherence to breast, cervical, and colorectal cancer-(CRC)-screening guidelines and evaluated demographic disparities among a population-based sample of survivors. METHODS: A representative sample of Utah survivors diagnosed from 2012-2018 with any reportable invasive cancer was selected from central cancer registry records for a survey about survivorship needs. We estimated the proportion of eligible survivors adhering to U.S. Preventive Services Task Force screening guidelines and calculated risk ratios and 95% confidence intervals. Analyses were age-adjusted and weighted to account for sample design and nonresponse. RESULTS: And 1421 survivors completed the survey (57.2% response rate). Screening adherence was 74.4% for breast, 69.4% for cervical, and 79.7% for CRC. Rural residents were more likely to adhere to breast cancer screening than urban residents (86.1% vs. 72.7%; adjusted RR = 1.19, CI = 1.05, 1.36). Higher educational attainment was associated with increased adherence to cervical and colorectal cancer screening. Younger age was associated with greater adherence to cervical cancer screening (p = 0.006) but lower adherence to CRC screening (p = 0.003). CRC screening adherence was lower among the uninsured and those without a primary care provider (45.6%) compared to those with a regular provider (83.0%; adjusted RR = 0.57, CI = 0.42, 0.79). CONCLUSIONS: Surveys based on samples from central cancer registries can provide population estimates to inform cancer control. Findings demonstrate work is needed to ensure all Utah cancer survivors obtain recommended cancer screenings. Efforts should focus particularly on increasing uptake of breast and cervical cancer screening and reducing demographic disparities in CRC screening. PRECIS: Despite high risk for subsequent cancer diagnosis, Utah cancer survivors are not all obtaining recommended breast, cervical, and colorectal cancer screenings. This presents a significant healthcare gap.

The feasibility of web surveys for obtaining patient-reported outcomes from cancer survivors: a randomized experiment comparing survey modes and brochure enclosures.

BACKGROUND: Central cancer registries are often used to survey population-based samples of cancer survivors. These surveys are typically administered via paper or telephone. In most populations, web surveys obtain much lower response rates than paper surveys. This study assessed the feasibility of web surveys for collecting patient-reported outcomes via a central cancer registry. METHODS: Potential participants were sampled from Utah Cancer Registry records. Sample members were randomly assigned to receive a web or paper survey, and then randomized to either receive or not receive an informative brochure describing the cancer registry. We calculated adjusted risk ratios with 95% confidence intervals to compare response likelihood and the demographic profile of respondents across study arms. RESULTS: The web survey response rate (43.2%) was lower than the paper survey (50.4%), but this difference was not statistically significant (adjusted risk ratio = 0.88, 95% confidence interval = 0.72, 1.07). The brochure also did not significantly influence the proportion responding (adjusted risk ratio = 1.03, 95% confidence interval = 0.85, 1.25). There were few differences in the demographic profiles of respondents across the survey modes. Older age increased likelihood of response to a paper questionnaire but not a web questionnaire. CONCLUSIONS: Web surveys of cancer survivors are feasible without significantly influencing response rates, but providing a paper response option may be advisable particularly when surveying older individuals. Further examination of the varying effects of brochure enclosures across different survey modes is warranted.

Combining Natural Language Processing of Electronic Medical Notes With Administrative Data to Determine Racial/Ethnic Differences in the Disclosure and Documentation of Military Sexual Trauma in Veterans.

BACKGROUND: Despite national screening efforts, military sexual trauma (MST) is underreported. Little is known of racial/ethnic differences in MST reporting in the Veterans Health Administration (VHA). OBJECTIVE: This study aimed to compare patterns of MST disclosure in VHA by race/ethnicity. RESEARCH DESIGN: Retrospective cohort study of MST disclosures in a national, random sample of Veterans who served in Afghanistan and Iraq and completed MST screens from October 2009 to 2014. We used natural language processing (NLP) to extract MST concepts from electronic medical notes in the year following Veterans' first MST screen. MEASURE(S): Any evidence of MST (positive MST screen or NLP concepts) and late MST disclosure (NLP concepts following a negative MST screen). Multivariable logistic regressions, stratified by sex, tested racial/ethnic differences in any MST evidence, and late disclosure. RESULTS: Of 6618 male and 6716 female Veterans with MST screen results, 1473 had a positive screen (68 male, 1%; 1405 female, 21%). Of those with a negative screen, 257 evidenced late MST disclosure by NLP (44 male, 39%; 213 female, 13%). Late MST disclosure was usually documented during mental health visits. There were no significant racial/ethnic differences in MST disclosure among men. Among women, blacks were less likely than whites to have any MST evidence (adjusted odds ratio=0.75). In the subsample with any MST evidence, black and Hispanic women were more likely than whites to disclose MST late (adjusted odds ratio=1.89 and 1.59, respectively). CONCLUSIONS: Combining NLP results with MST screen data facilitated the identification of under-reported sexual trauma experiences among men and racial/ethnic minority women.

Predictors of Response Outcomes for Research Recruitment Through a Central Cancer Registry: Evidence From 17 Recruitment Efforts for Population-Based Studies.

When recruiting research participants through central cancer registries, high response fractions help ensure population-based representation. We conducted multivariable mixed-effects logistic regression to identify case and study characteristics associated with making contact with and obtaining cooperation of Utah cancer cases using data from 17 unique recruitment efforts undertaken by the Utah Cancer Registry (2007-2016) on behalf of the following studies: A Population-Based Childhood Cancer Survivors Cohort Study in Utah, Comparative Effectiveness Analysis of Surgery and Radiation for Prostate Cancer (CEASAR Study), Costs and Benefits of Follow-up Care for Adolescent and Young Adult Cancers, Study of Exome Sequencing for Head and Neck Cancer Susceptibility Genes, Genetic Epidemiology of Chronic Lymphocytic Leukemia, Impact of Remote Familial Colorectal Cancer Risk Assessment and Counseling (Family CARE Project), Massively Parallel Sequencing for Familial Colon Cancer Genes, Medullary Thyroid Carcinoma (MTC) Surveillance Study, Osteosarcoma Surveillance Study, Prostate Cancer Outcomes Study, Risk Education and Assessment for Cancer Heredity Project (REACH Project), Study of Shared Genomic Segment Analysis and Tumor Subtyping in High-Risk Breast-Cancer Gene Pedigrees, Study of Shared Genomic Segment Analysis for Localizing Multiple Myeloma Genes. Characteristics associated with lower odds of contact included Hispanic ethnicity (odds ratio (OR) = 0.34, 95% confidence interval (CI): 0.27, 0.41), nonwhite race (OR = 0.46, 95% CI: 0.35, 0.60), and younger age at contact. Years since diagnosis was inversely associated with making contact. Nonwhite race and age ≥60 years had lower odds of cooperation. Study features with lower odds of cooperation included longitudinal design (OR = 0.50, 95% CI: 0.41, 0.61) and study brochures (OR = 0.70, 95% CI: 0.54, 0.90). Increased odds of cooperation were associated with including a questionnaire (OR = 3.19, 95% CI: 1.54, 6.59), postage stamps (OR = 1.60, 95% CI: 1.21, 2.12), and incentives (OR = 1.62, 95% CI: 1.02, 2.57). Among cases not responding after the first contact, odds of eventual response were lower when >10 days elapsed before subsequent contact (OR = 0.71, 95% CI: 0.59, 0.85). Obtaining high response is challenging, but study features identified in this analysis support better results when recruiting through central cancer registries.

Regional Variations in Documentation of Sexual Trauma Concepts in Electronic Medical Records in the United States Veterans Health Administration.

Background: Experiences of sexual trauma are associated with adverse patient and health system outcomes, but are not systematically documented in electronic health records (EHR). Objective: To describe variations in how sexual trauma is documented in the Veterans Health Adminstration's EHR. Methods: Sexual trauma concepts were extracted from from 362,559 clinical notes using a natural language processing pipeline. Results: We observed variations in the presence of sexual trauma in notes across five United States regions: Pacific, Continental, Midwest, North Atlantic, Southeast. We also observed variations in the types of notes used to document sexual trauma (e.g., mental health, primary care) and sources of sexual trauma (e.g., adult, childhood, military) mentioned in the EHR. Our findings illustrate potential differences in cultural norms related to patient disclosure of sensitive information, and provider documentation. Standardized protocol for eliciting and documenting sexual trauma histories are needed to ensure Veteran access to high quality, trauma-informed care.

Automated Extraction and Classification of Cancer Stage Mentions fromUnstructured Text Fields in a Central Cancer Registry.

Cancer stage is one of the most important prognostic parameters in most cancer subtypes. The American Joint Com-mittee on Cancer (AJCC) specifies criteria for staging each cancer type based on tumor characteristics (T), lymph node involvement (N), and tumor metastasis (M) known as TNM staging system. Information related to cancer stage is typically recorded in clinical narrative text notes and other informal means of communication in the Electronic Health Record (EHR). As a result, human chart-abstractors (known as certified tumor registrars) have to search through volu-minous amounts of text to extract accurate stage information and resolve discordance between different data sources. This study proposes novel applications of natural language processing and machine learning to automatically extract and classify TNM stage mentions from records at the Utah Cancer Registry. Our results indicate that TNM stages can be extracted and classified automatically with high accuracy (extraction sensitivity: 95.5%-98.4% and classification sensitivity: 83.5%-87%).

Gender differences in service utilization among Operations Enduring Freedom, Iraqi Freedom, and New Dawn Veterans Affairs patients with severe mental illness and substance use disorders.

Severe mental illness (SMI) and substance use disorders (SUD) are among the more chronic and costly mental health conditions treated in the Department of Veterans Affairs (VA). Service use patterns of returning veterans with SMI and SUD have received little attention. We examined gender differences in the utilization of VA services among a national sample of Operations Enduring Freedom, Iraqi Freedom, and New Dawn (OEF/OIF/OND) VA patients with SMI, SUD, and their comorbidity (SMI/SUD) in their first year of established VA care (N = 24,166). Outpatient services and acute-residential stays were modeled using negative binomial and logistic regression, respectively. Among all diagnostic categories, men used outpatient services less often than did women, including primary care (adjusted rate ratio [ARR] = .71, 95% confidence interval CI [.68, .74]), mental health (ARR = .85, 95% CI [.80, .91]), and addiction (ARR = .91, 95% CI [.83, .99]) services. For emergency department (ED) and psychiatric inpatient services, gender interacted significantly with diagnosis. The combination of SMI/SUD compared to either SMI or SUD conferred greater risk of ED utilization among men than women (adjusted odds ratio [AOR] = 2.09, 95% CI [1.24, 3.51], and 1.95, 95% CI [1.17, 3.26], respectively). SMI versus SUD conferred greater risk of psychiatric inpatient utilization among men than women (AOR = 1.83, 95% CI [1.43, 2.34]). Our findings point to gender differences in outpatient and acute service utilization among OEF/OIF/OND VA patients with some of the more chronic and costly mental health conditions. Further investigation of health care utilization patterns is needed to understand factors driving these gender differences to ensure that veterans have appropriate access to the services they need. (PsycINFO Database Record

Increased Health Care Utilization and Costs Among Veterans With a Positive Screen for Military Sexual Trauma.

BACKGROUND: The effects of sexual trauma on long-term health care utilization and costs are not well understood due to infrequent documentation of sexual trauma history in health care systems. The Veteran's Health Administration provides a unique opportunity to address this constraint as sexual trauma is actively screened for as part of routine care. METHODS: We used a retrospective cohort design to analyze Veteran's Health Administration mental health and medical service utilization and costs as a function of a positive screen for exposure to military sexual trauma (MST) among Veterans of recent conflicts in Iraq and Afghanistan. We computed adjusted 5-year estimates of overall utilization and costs, and utilization and costs determined not to be related to MST. RESULTS: The cohort included 426,223 men and 59,611 women. A positive MST screen was associated with 50% higher health care utilization and costs relative to a negative screen. Overall, a positive relative to negative MST screen was associated with a 5-year incremental difference of 34.6 encounters and $10,734 among women, and 33.5 encounters and $11,484 among men. After accounting for MST-related treatment, positive MST screen was associated with 11.9 encounters and $4803 among women, and 19.5 encounters and $8001 among men. CONCLUSIONS: Results demonstrate significant and consistent differences in health care utilization and costs between Veterans with a positive relative to negative MST screen. Even after accounting for MST-related care, a positive screen was associated with significantly higher utilization and costs. MST-related needs may be more readily recognized in women relative to men.

Patient-aligned Care Team Engagement to Connect Veterans Experiencing Homelessness With Appropriate Health Care.

BACKGROUND: Veterans experiencing homelessness frequently use emergency and urgent care (ED). OBJECTIVE: To examine the effect of a Patient-aligned Care Team (PACT) model tailored to the unique needs of Veterans experiencing homelessness (H-PACT) on frequency and type of ED visits in Veterans Health Administration (VHA) medical facilities. RESEARCH DESIGN: During a 12-month period, ED visits for 3981 homeless Veterans enrolled in (1) H-PACT at 20 VHA medical centers (enrolled) were compared with those of (2) 24,363 homeless Veterans not enrolled in H-PACT at the same sites (nonenrolled), and (3) 23,542 homeless Veterans at 12 non-H-PACT sites (usual care) using a difference-in-differences approach. MEASURE(S): The primary outcome was ED and other health care utilization and the secondary outcome was emergent (not preventable/avoidable) ED visits. RESULTS: H-PACT enrollees were predominantly white males with a higher baseline Charlson comorbidity index. In comparing H-PACT enrollees with usual care, there was a significant decrease in ED usage among the highest ED utilizers (difference-in-differences, -4.43; P<0.001). The decrease in ED visits were significant though less intense for H-PACT enrollees versus nonenrolled (-0.29, P<0.001). H-PACT enrollees demonstrated a significant increase in the proportion of ED care visits that were not preventable/avoidable in the 6 months after enrollment, but had stable rates of primary care, mental health, social work, and substance abuse visits over the 12 months. CONCLUSIONS: Primary care treatment engagement can reduce ED visits and increase appropriate use of ED services in VHA for Veterans experiencing homelessness, especially in the highest ED utilizers.

Military sexual trauma is associated with post-deployment eating disorders among Afghanistan and Iraq veterans.

OBJECTIVE: Evaluate the association of military sexual trauma (MST) screen status with eating disorder diagnoses among veterans within 1- and 5-years after initiating Veterans Health Administration (VHA) care, and whether the association varied by sex. METHOD: Retrospective cohort study of US Afghanistan/Iraq veterans who used VHA services between FY 2004 and 2014 (N = 595,525). This study used VHA administrative data to assess the presence of eating disorder diagnoses in medical records within 1- and 5-years of initiating VHA care, and whether a positive screen for MST was associated with eating disorders. RESULTS: Three percent (n = 18,488) screened positive for MST. At 1- and 5-year follow up, 0.1% (n= 513, 74% female), and 0.2% (n = 504, 71% female) were diagnosed with an eating disorder, respectively. In regression models adjusted for demographic variables, military service, and psychiatric comorbidities, the presence of an eating disorder diagnosis was nearly two times higher among those with a positive screen for MST in the 1-year (adjusted odds ratio [AOR] = 1.94, 95% confidence interval [CI] = 1.57-2.40) and 5-year (AOR = 1.86, 95%CI = 1.49-2.32) cohorts. The increased likelihood conferred by MST for an eating disorder diagnosis was differentially stronger among male veterans than female veterans in the 1-year cohort only (AOR = 2.13, 95%CI = 1.01-4.50). DISCUSSION: Veterans with a positive screen for MST, especially male veterans, had a nearly two-fold increased likelihood of having an eating disorder diagnosis. Screening for eating disorders may be important in both male and female veterans who report MST.

Homelessness following disability-related discharges from active duty military service in Afghanistan and Iraq.

BACKGROUND: Many dynamics in the relationship among military service-related disabilities, health care benefits, mental health disorders, and post-deployment homelessness among US Veterans are not well understood. OBJECTIVES: Determine whether Veterans with a disability-related discharge from military service are at higher risk for homelessness, whether Veterans Health Administration (VHA) service-connected disability benefits mitigates that risk, and whether risks associated with discharge type, service-connected disability, or the interaction between them vary as a function of mental health disorders. METHODS: Retrospective cohort study of 364,997 Veterans with a disability-related or routine discharge and initial VHA encounter between 2005 and 2013. Logistic regression and survival analyses were used to estimate homelessness risk as a function of discharge status, mental health disorders, and receipt of VHA disability benefits. RESULTS: Disability-discharged Veterans had higher rates of homelessness compared to routine discharges (15.1 verses 9.1 per 1000 person-years at risk). At the time of the first VHA encounter, mental health disorders were associated with differentially greater risk for homelessness among Veterans with a disability discharge relative to those with a routine discharge. During the first year of VHA service usage, higher levels of disability benefits were protective against homelessness among routinely-discharged Veterans, but not among disability-discharged Veterans. By 5-years, disability discharge was a risk factor for homelessness (AOR = 1.30). CONCLUSIONS: In the long-term, disability discharge is an independent risk factor for homelessness. While VHA disability benefits help mitigate homelessness risk among routinely-discharged Veterans during the early reintegration period, they may not offer sufficient protection for disability-discharged Veterans.

Non-routine Discharge From Military Service: Mental Illness, Substance Use Disorders, and Suicidality.

INTRODUCTION: Mental illness and substance use disorders among newly returned military service members pose challenges to successful reintegration into civilian life and, in extreme cases, may lead to outcomes such as incarceration, homelessness, and suicide. One potential early indicator for these difficulties is non-routine discharge from military service. METHODS: Using data from the Veterans Health Administration (VHA) for 443,360 active duty service Veterans who deployed to Afghanistan and Iraq and subsequently utilized VHA services between Fiscal Years 2004 and 2013, this study examined risk for receiving a VHA-documented diagnosis of mental illness, substance use disorders, and suicidality as a function of discharge type, controlling for demographic and military service covariates. Analyses were conducted in 2016. RESULTS: In total, 126,314 Veterans (28.5%) had a non-routine military service discharge. Compared with routinely discharged Veterans, odds for nearly all diagnostic outcomes were significantly greater among Veterans discharged for disqualification or misconduct, including personality disorders (AOR=9.21 and 3.29, respectively); bipolar/psychotic disorders (AOR=3.98 and 3.40); alcohol/substance use disorders (AOR=1.55 and 4.42); and suicidal ideation and behaviors (AOR=2.81 and 2.77). Disability-discharged Veterans had significantly higher odds for diagnoses of anxiety disorders (AOR=1.97) and bipolar/psychotic disorders (AOR=3.93). CONCLUSIONS: Non-routine service discharge strongly predicts VHA-diagnosed mental illness, substance use disorders, and suicidality, with particularly elevated risk among Veterans discharged for disqualification or misconduct. Results emphasize the importance of discharge type as an early marker of adverse post-discharge outcomes, and suggest a need for targeted prevention and intervention efforts to improve reintegration outcomes among this vulnerable subpopulation.

Detecting the presence of an indwelling urinary catheter and urinary symptoms in hospitalized patients using natural language processing.

OBJECTIVE: To develop a natural language processing pipeline to extract positively asserted concepts related to the presence of an indwelling urinary catheter in hospitalized patients from the free text of the electronic medical note. The goal is to assist infection preventionists and other healthcare professionals in determining whether a patient has an indwelling urinary catheter when a catheter-associated urinary tract infection is suspected. Currently, data on indwelling urinary catheters is not consistently captured in the electronic medical record in structured format and thus cannot be reliably extracted for clinical and research purposes. MATERIALS AND METHODS: We developed a lexicon of terms related to indwelling urinary catheters and urinary symptoms based on domain knowledge, prior experience in the field, and review of medical notes. A reference standard of 1595 randomly selected documents from inpatient admissions was annotated by human reviewers to identify all positively and negatively asserted concepts related to indwelling urinary catheters. We trained a natural language processing pipeline based on the V3NLP framework using 1050 documents and tested on 545 documents to determine agreement with the human reference standard. Metrics reported are positive predictive value and recall. RESULTS: The lexicon contained 590 terms related to the presence of an indwelling urinary catheter in various categories including insertion, care, change, and removal of urinary catheters and 67 terms for urinary symptoms. Nursing notes were the most frequent inpatient note titles in the reference standard document corpus; these also yielded the highest number of positively asserted concepts with respect to urinary catheters. Comparing the performance of the natural language processing pipeline against the human reference standard, the overall recall was 75% and positive predictive value was 99% on the training set; on the testing set, the recall was 72% and positive predictive value was 98%. The performance on extracting urinary symptoms (including fever) was high with recall and precision greater than 90%. CONCLUSIONS: We have shown that it is possible to identify the presence of an indwelling urinary catheter and urinary symptoms from the free text of electronic medical notes from inpatients using natural language processing. These are two key steps in developing automated protocols to assist humans in large-scale review of patient charts for catheter-associated urinary tract infection. The challenges associated with extracting indwelling urinary catheter-related concepts also inform the design of electronic medical record templates to reliably and consistently capture data on indwelling urinary catheters.

Extracting Sexual Trauma Mentions from Electronic Medical Notes Using Natural Language Processing.

Patient history of sexual trauma is of clinical relevance to healthcare providers as survivors face adverse health-related outcomes. This paper describes a method for identifying mentions of sexual trauma within the free text of electronic medical notes. A natural language processing pipeline for information extraction was developed and scaled to handle a large corpus of electronic medical notes used for this study from US Veterans Health Administration medical facilities. The tool was used to identify sexual trauma mentions and create snippets around every asserted mention based on a domain-specific lexicon developed for this purpose. All snippets were evaluated by trained human reviewers. An overall positive predictive value (PPV) of 0.90 for identifying sexual trauma mentions from the free text and a PPV of 0.71 at the patient level are reported. The metrics are superior for records from female patients.

A pilot study of a heuristic algorithm for novel template identification from VA electronic medical record text.

RATIONALE: Templates in text notes pose challenges for automated information extraction algorithms. We propose a method that identifies novel templates in plain text medical notes. The identification can then be used to either include or exclude templates when processing notes for information extraction. METHODS: The two-module method is based on the framework of information foraging and addresses the hypothesis that documents containing templates and the templates within those documents can be identified by common features. The first module takes documents from the corpus and groups those with common templates. This is accomplished through a binned word count hierarchical clustering algorithm. The second module extracts the templates. It uses the groupings and performs a longest common subsequence (LCS) algorithm to obtain the constituent parts of the templates. The method was developed and tested on a random document corpus of 750 notes derived from a large database of US Department of Veterans Affairs (VA) electronic medical notes. RESULTS: The grouping module, using hierarchical clustering, identified 23 groups with 3 documents or more, consisting of 120 documents from the 750 documents in our test corpus. Of these, 18 groups had at least one common template that was present in all documents in the group for a positive predictive value of 78%. The LCS extraction module performed with 100% positive predictive value, 94% sensitivity, and 83% negative predictive value. The human review determined that in 4 groups the template covered the entire document, with the remaining 14 groups containing a common section template. Among documents with templates, the number of templates per document ranged from 1 to 14. The mean and median number of templates per group was 5.9 and 5, respectively. DISCUSSION: The grouping method was successful in finding like documents containing templates. Of the groups of documents containing templates, the LCS module was successful in deciphering text belonging to the template and text that was extraneous. Major obstacles to improved performance included documents composed of multiple templates, templates that included other templates embedded within them, and variants of templates. We demonstrate proof of concept of the grouping and extraction method of identifying templates in electronic medical records in this pilot study and propose methods to improve performance and scaling up.