Use of natural language processing method to identify regional anesthesia from clinical notes.

INTRODUCTION: Accurate data capture is integral for research and quality improvement efforts. Unfortunately, limited guidance for defining and documenting regional anesthesia has resulted in wide variation in documentation practices, even within individual hospitals, which can lead to missing and inaccurate data. This cross-sectional study sought to evaluate the performance of a natural language processing (NLP)-based algorithm developed to identify regional anesthesia within unstructured clinical notes. METHODS: We obtained postoperative clinical notes for all patients undergoing elective non-cardiac surgery with general anesthesia at one of six Veterans Health Administration hospitals in California between January 1, 2017, and December 31, 2022. After developing and executing our algorithm, we compared our results to a frequently used referent, the Corporate Data Warehouse structured data, to assess the completeness and accuracy of the currently available data. Measures of agreement included sensitivity, positive predictive value, false negative rate, and accuracy. RESULTS: We identified 27,713 procedures, of which 9310 (33.6%) received regional anesthesia. 96.6% of all referent regional anesthesia cases were identified in the clinic notes with a very low false negative rate and good accuracy (false negative rate=0.8%, accuracy=82.5%). Surprisingly, the clinic notes documented more than two times the number of regional anesthesia cases that were documented in the referent (algorithm n=9154 vs referent n=4606). DISCUSSION: While our algorithm identified nearly all regional anesthesia cases from the referent, it also identified more than two times as many regional anesthesia cases as the referent, raising concerns about the accuracy and completeness of regional anesthesia documentation in administrative and clinical databases. We found that NLP was a promising alternative for identifying clinical information when existing databases lack complete documentation.

Mapping the Discharge Process After Surgery.

Importance: Care transition models are structured approaches used to ensure the smooth transfer of patients between health care settings or levels of care, but none currently are tailored to the surgical patient. Tailoring care transition models to the unique needs of surgical patients may lead to significant improvements in surgical outcomes and reduced care fragmentation. The first step to developing surgical care transition models is to understand the surgical discharge process. Objective: To map the surgical discharge process in a sample of US hospitals and identify key components and potential challenges specific to a patient's discharge after surgery. Design, Setting, and Participants: This qualitative study followed a cognitive task analysis framework conducted between January 1, 2022, and April 1, 2023, in Veterans Health Administration (VHA) hospitals. Observations (n = 16) of discharge from inpatient care after a surgical procedure were conducted in 2 separate VHA surgical units. Interviews (n = 13) were conducted among VHA health care professionals nationwide. Exposure: Postoperative hospital discharge. Main Outcomes and Measures: Data were coded according to the principles of thematic analysis, and a swim lane process map was developed to represent the study findings. Results: At the hospitals in this study, the discharge process observed for a surgical patient involved multidisciplinary coordination across the surgery team, nursing team, case managers, dieticians, social services, occupational and physical therapy, and pharmacy. Important components for a surgical discharge that were not incorporated in the current care transition models included wound care education and supplies; pain control; approvals for nonhome postdischarge locations; and follow-up plans for wounds, ostomies, tubes, and drains at discharge. Potential challenges to the surgical discharge process included social situations (eg, home environment and caregiver availability), team communication issues, and postdischarge care coordination. Conclusions and Relevance: These findings suggest that current and ongoing studies of discharge care transitions for a patient after surgery should consider pain control; wounds, ostomies, tubes, and drains; and the impact of challenging social situations and interdisciplinary team coordination on discharge success.

VA's implementation of universal screening and evaluation for the suicide risk identification program in November 2020 -Implications for Veterans with prior mental health needs.

IMPORTANCE: United States Veterans are at higher risk for suicide than non-Veterans. Veterans in rural areas are at higher risk than their urban counterparts. The coronavirus pandemic intensified risk factors for suicide, especially in rural areas. OBJECTIVE: To examine associations between Veterans Health Administration's (VA's) universal suicide risk screening, implemented November 2020, and likelihood of Veterans being screened, and receiving follow-up evaluations, as well as post-screening suicidal behavior among patients who used VA mental health services in 2019. METHODS: VA's Suicide Risk Identification Strategy (Risk ID), implemented October 2018, is a national, standardized process for suicide risk screening and evaluation. In November 2020, VA expanded Risk ID, requiring annual universal suicide screening. As such, we are evaluating outcomes of interest before and after the start of the policy among Veterans who had ≥1 VA mental health care visit in 2019 (n = 1,654,180; rural n = 485,592, urban n = 1,168,588). Regression-adjusted outcomes were compared 6 months pre-universal screening and 6, 12 and 13 months post-universal screening implementation. MEASURES: Item-9 on the Patient Health Questionnaire (I-9, VA's historic suicide screener), Columbia- Suicide Severity Risk Scale (C-SSRS) Screener, VA's Comprehensive Suicide Risk Evaluation (CSRE), and Suicide Behavior and Overdose Report (SBOR). RESULTS: 12 months post-universal screening implementation, 1.3 million Veterans (80% of the study cohort) were screened or evaluated for suicide risk, with 91% the sub-cohort who had at least one mental health visit in the 12 months post-universal screening implementation period were screened or evaluated. At least 20% of the study cohort was screened outside of mental health care settings. Among Veterans with positive screens, 80% received follow-up CSREs. Covariate-adjusted models indicated that an additional 89,160 Veterans were screened per month via the C-SSRS and an additional 30,106 Veterans/month screened via either C-SSRS or I-9 post-universal screening implementation. Compared to their urban counterparts, 7,720 additional rural Veterans/month were screened via the C-SSRS and 9,226 additional rural Veterans/month were screened via either the C-SSRS or I-9. CONCLUSION: VA's universal screening requirement via VA's Risk ID program increased screening for suicide risk among Veterans with mental health care needs. A universal approach to screening may be particularly advantageous for rural Veterans, who are typically at higher risk for suicide but have fewer interactions with the health care system, particularly within specialty care settings, due to higher barriers to accessing care. Insights from this program offer valuable insights for health systems nationwide.

Therapeutic and Economic Benefits of Service Dogs Versus Emotional Support Dogs for Veterans With PTSD.

OBJECTIVE: This work aimed to assess the therapeutic and economic benefits of service dogs versus emotional support dogs for veterans with posttraumatic stress disorder (PTSD). METHODS: Veterans with PTSD (N=227) participating in a multicenter trial were randomly assigned to receive a service or emotional support dog; 181 veterans received a dog and were followed up for 18 months. Primary outcomes included overall functioning (assessed with World Health Organization Disability Assessment Scale II [WHODAS 2.0]) and quality of life (Veterans RAND 12-Item Health Survey [VR-12]). Secondary outcomes included PTSD symptoms (PTSD Checklist for DSM-5), suicidal ideation, depression, sleep quality, health care costs and utilization, medication adherence, employment, and productivity. RESULTS: Participants paired with a dog had a mean±SD age of 50.6±13.6 years (range 22-79), and most were male (80%), White (66%), and non-Hispanic (91%). Adjusted linear mixed repeated-measures models indicated no difference between the two groups on WHODAS 2.0 or VR-12 scores. Participants with service dogs had a 3.7-point greater reduction in PTSD symptoms versus participants with emotional support dogs (p=0.036). No reduced health care utilization or cost was associated with receiving a service dog. Veterans with service dogs had an increase of 10 percentage points in antidepressant adherence compared with those with emotional support dogs (p<0.01). CONCLUSIONS: Both groups appeared to benefit from having a service or emotional support dog. No significant differences in improved functioning or quality of life were observed between the groups. Those in the service dog group had a greater reduction in PTSD symptoms and better antidepressant adherence, improvements that should be explored further.

Applying cognitive task analysis to health services research.

OBJECTIVE: Designing practical decision support tools and other health care technology in health services research relies on a clear understanding of the cognitive processes that underlie the use of these tools. Unfortunately, methods to explore cognitive processes are rarely used in health services research. Thus, the objective of this manuscript is to introduce cognitive task analysis (CTA), a family of methods to study cognitive processes involved in completing a task, to a health services research audience. This methods article describes CTA procedures, proposes a framework for their use in health services research studies, and provides an example of its application in a pilot study. DATA SOURCES AND STUDY SETTING: Observations and interviews of health care providers involved in discharge planning at six hospitals in the Veterans Health Administration. STUDY DESIGN: Qualitative study of discharge planning using CTA. DATA COLLECTION/EXTRACTION METHODS: Data were collected from structured observations and semi-structured interviews using the Critical Decision Method and analyzed using thematic analysis. PRINCIPAL FINDINGS: We developed an adaptation of CTA that could be used in a clinical environment to describe clinical decision-making and other cognitive processes. The adapted CTA framework guides the user through four steps: (1) Planning, (2) Environmental Analysis, (3) Knowledge Elicitation, and (4) Analyses and Results. This adapted CTA framework provides an iterative and systematic approach to identifying and describing the knowledge, expertise, thought processes, procedures, actors, goals, and mental strategies that underlie completing a clinical task. CONCLUSIONS: A better understanding of the cognitive processes that underly clinical tasks is key to developing health care technology and decision-support tools that will have a meaningful impact on processes of care and patient outcomes. Our adapted framework offers a more rigorous and detailed method for identifying task-related cognitive processes in implementation studies and quality improvement. Our adaptation of this underutilized qualitative research method may be helpful to other researchers and inform future research in health services research.

End-of-Life Cost Trajectories in Cancer Patients Treated by Medicare versus the Veterans Health Administration.

BACKGROUND/OBJECTIVES: To evaluate differences in end-of-life cost trajectories for cancer patients treated through Medicare versus by the Veterans Health Administration (VA). DESIGN: A retrospective analysis of VA and Medicare administrative data from FY 2010 to 2014. We employed three-level generalized estimating equations to evaluate monthly cost trajectories experienced by patients in their last year of life, with patients nested within hospital referral region. SETTING: Care received at VA facilities or by Medicare-reimbursed providers nationwide. PARTICIPANTS: A total of 36,401 patients dying from cancer and dually enrolled in VA and Medicare. MEASUREMENTS: We evaluated trajectories for total, inpatient, outpatient, and drug costs, using the last 12 months of life. Cost trajectories were prioritized as costs are not directly comparable across Medicare and VA. Patients were assigned to be VA-reliant, Medicare-reliant or Mixed-reliant based on their healthcare utilization in the last year of life. RESULTS: All three groups experienced significantly different cost trajectories for total costs in the last year of life. Inpatient cost trajectories were significantly different between Medicare-reliant and VA-reliant patients, but did not differ between VA-reliant and Mixed-reliant patients. Outpatient and drug cost trajectories exhibited the inverse pattern: they were significantly different between VA-reliant and Mixed-reliant patients, but not between VA-reliant and Medicare-reliant patients. However, visual examination of cost trajectories revealed similar cost patterns in the last year of life among all three groups; there was a sharp rise in costs as patients approach death, largely due to inpatient care. CONCLUSION: Despite substantially different financial incentives and organization, VA- and Medicare-treated patients exhibit similar patterns of increasing end-of-life costs, largely driven by inpatient costs. Both systems require improvement to ensure quality of end-of-life care is aligned with recommended practice.

Comorbidity Assessment Is Uneven Across Veterans Health Administration and Medicare for the Same Patient: Implications for Risk Adjustment.

OBJECTIVE: Compare comorbidity identification in Medicare and Veterans Health Administration (VA) data for the purposes of risk adjustment. DATA SOURCES: Analysis of Medicare and VA datasets for dually-enrolled Veterans receiving care in both settings, fiscal years 2010-2014. STUDY DESIGN: A retrospective analysis of administrative data for a national sample of cancer decedents. DATA EXTRACTION METHODS: Comorbidities were evaluated using Elixhauser and Charlson coding algorithms. PRINCIPAL FINDINGS: Clinical comorbidities were more likely to be recorded in Medicare than in VA datasets. Of 42 comorbidities, 36 (86%) were recorded at a different frequency. For example, congestive heart failure was recorded for 22.0% of patients in Medicare data and for 11.3% of patients in VA data (P<0.001). CONCLUSION: There are large differences in comorbidity assessment across VA and Medicare administrative data for the same patient, posing challenges for risk adjustment.

Potentially avoidable hospitalizations after chemotherapy: Differences across medicare and the Veterans Health Administration.

BACKGROUND: The Centers for Medicare and Medicaid Services (CMS) has released quality measures regarding potentially avoidable hospitalizations visits in the 30 days after receipt of outpatient chemotherapy. This study evaluated the proportions of patients treated by Medicare-reimbursed clinicians and Veterans Health Administration (VA) clinicians who experienced avoidable acute care in order to evaluate differences in health system performance. METHODS: This retrospective evaluation of Medicare and VA administrative data used a cohort of cancer decedents (fiscal years 2010-2014). Cohort members were veterans aged 66 years or older at death who were dually enrolled in Medicare and the VA. Chemotherapy was identified through International Classification of Diseases, Ninth Revision and Current Procedural Terminology (ICD-9) codes. CMS defines avoidable hospitalizations as those related to anemia, dehydration, diarrhea, emesis, fever, nausea, neutropenia, pain, pneumonia, or sepsis in the 30 days after chemotherapy. Following CMS guidance, this study compared the proportions of patients with potentially avoidable hospitalizations, using hierarchical generalized estimating equations. RESULTS: There were 27,443 patients who received outpatient chemotherapy. Patients receiving Medicare chemotherapy were significantly more likely to have potentially avoidable hospitalizations than patients receiving VA chemotherapy (adjusted odds ratio, 1.58; 95% confidence interval, 1.41-1.78; P < .001). In predicted estimates, 7.1% of Medicare-treated veterans had potentially avoidable hospitalizations in the 30 days after chemotherapy, compared with 4.6% of VA-treated veterans. CONCLUSIONS: Results indicate veterans with cancer receiving chemotherapy in the VA have higher quality care with respect to avoidable hospitalizations than veterans receiving chemotherapy through Medicare. As more veterans seek care in the private sector under the Maintaining Internal Systems and Strengthening Integrated Outside Networks (MISSION) Act, concerted efforts may be warranted to ensure that veterans do not experience a decline in care quality.

Health System and Beneficiary Costs Associated With Intensive End-of-Life Medical Services.

Importance: Despite recommendations to reduce intensive medical treatment at the end of life, many patients with cancer continue to receive such services. Objective: To quantify expected beneficiary and health system costs incurred in association with receipt of intensive medical services in the last month of life. Design, Setting, and Participants: This retrospective cohort study used data collected nationally from Medicare and the Veterans Health Administration for care provided in fiscal years 2010 to 2014. Participants were 48 937 adults aged 66 years or older who died of solid tumor and were continuously enrolled in fee-for-service Medicare and the Veterans Health Administration in the 12 months prior to death. The data were analyzed from February to August 2019. Exposures: American Society of Clinical Oncology metrics regarding medically intensive services provided in the last month of life, including hospital stay, intensive care unit stay, chemotherapy, 2 or more emergency department visits, or hospice for 3 or fewer days. Main Outcomes and Measures: Costs in the last month of life associated with receipt of intensive medical services were evaluated for both beneficiaries and the health system. Costs were estimated from generalized linear models, adjusting for patient demographics and comorbidities and conditioning on geographic region. Results: Of 48 937 veterans who received care through the Veterans Health Administration and Medicare, most were white (90.8%) and male (98.9%). More than half (58.9%) received at least 1 medically intensive service in the last month of life. Patients who received no medically intensive service generated a mean (SD) health system cost of $7660 ($1793), whereas patients who received 1 or more medically intensive services generated a mean (SD) health system cost of $23 612 ($5528); thus, the additional financial consequence to the health care system for medically intensive services was $15 952 (95% CI, $15 676-$16 206; P < .001). The biggest contributor to these differences was $21 093 (95% CI, $20 364-$21 689) for intensive care unit stay, while the smallest contributor was $3460 (95% CI, $2927-$3880) for chemotherapy. Mean (SD) expected beneficiary costs for the last month of life were $133 ($50) for patients with no medically intensive service and $1257 ($408) for patients with at least 1 medically intensive service (P < .001). Conclusions and Relevance: Given the low income of many elderly patients in the United States, the financial consequences of medically intensive services may be substantial. Costs of medically intensive services at the end of life, including patient financial consequences, should be considered by both physicians and families.