Deploying a national clinical text processing infrastructure.

OBJECTIVES: Clinical text processing offers a promising avenue for improving multiple aspects of healthcare, though operational deployment remains a substantial challenge. This case report details the implementation of a national clinical text processing infrastructure within the Department of Veterans Affairs (VA). METHODS: Two foundational use cases, cancer case management and suicide and overdose prevention, illustrate how text processing can be practically implemented at scale for diverse clinical applications using shared services. RESULTS: Insights from these use cases underline both commonalities and differences, providing a replicable model for future text processing applications. CONCLUSIONS: This project enables more efficient initiation, testing, and future deployment of text processing models, streamlining the integration of these use cases into healthcare operations. This project implementation is in a large integrated health delivery system in the United States, but we expect the lessons learned to be relevant to any health system, including smaller local and regional health systems in the United States.

Project STEP: Implementing the Veterans Health Administration's Stepped Care Model of Pain Management.

Objective: The "stepped care model of pain management" (SCM-PM) prioritizes the role of primary care providers in optimizing pharmacological management and timely and equitable access to patient-centered, evidence-based nonpharmacological approaches, when indicated. Over the past several years, the Veterans Health Administration (VHA) has supported implementation of SCM-PM, but few data exist regarding changes in pain care resulting from implementation. We examined trends in prescribing and referral practices of primary care providers with hypotheses of decreased opioid prescribing, increased nonopioid prescribing, and increased referrals to specialty care for nonpharmacological services. Design: An initiative was designed to foster implementation and systematic evaluation of the SCM-PM over a five-year period at the VA Connecticut Healthcare System (VACHS) while fostering collaborative, partnered initiatives to promote organizational improvements in the delivery of pain care. Subjects: Participants were veterans receiving care at VACHS with at least one pain intensity rating ≥4/10 over the course of the study period (7/2008-6/2013). Methods: We used electronic health record data to examine changes in indicators of pain care including pharmacy and health care utilization data. Results: We observed hypothesized changes in long-term opioid and nonopioid analgesic prescribing and increased utilization of nonpharmacological treatments such as physical therapy, occupational therapy, and clinical health psychology. Conclusions: Through a multifaceted comprehensive implementation approach, primary care providers demonstrated increases in guideline-concordant pain care practices. Findings suggest that engagement of interdisciplinary teams and partnerships to promote organizational improvements is a useful strategy to increase the use of integrated, multimodal pain care for veterans, consistent with VHA's SCM-PM.

A Clinical Decision Support System for Monitoring Post-Colonoscopy Patient Follow-Up and Scheduling.

This paper describes a natural language processing (NLP)-based clinical decision support (CDS) system that is geared towards colon cancer care coordinators as the end users. The system is implemented using a metadata- driven Structured Query Language (SQL) function (discriminant function). For our pilot study, we have developed a training corpus consisting of 2,085 pathology reports from the VA Connecticut Health Care System (VACHS). We categorized reports as "actionable"- requiring close follow up, or "non-actionable"- requiring standard or no follow up. We then used 600 distinct pathology reports from 6 different VA sites as our test corpus. Analysis of our test corpus shows that our NLP approach yields 98.5% accuracy in identifying cases that required close clinical follow up. By integrating this into our cancer care tracking system, our goal is to ensure that patients with worrisome pathology receive appropriate and timely follow-up and care.

Utilizing patient data from the veterans administration electronic health record to support web-based clinical decision support: informatics challenges and issues from three clinical domains.

BACKGROUND: The US Veterans Administration (VA) has developed a robust and mature computational infrastructure in support of its electronic health record (EHR). Web technology offers a powerful set of tools for structuring clinical decision support (CDS) around clinical care. This paper describes informatics challenges and design issues that were confronted in the process of building three Web-based CDS systems in the context of the VA EHR. METHODS: Over the course of several years, we implemented three Web-based CDS systems that extract patient data from the VA EHR environment to provide patient-specific CDS. These were 1) the VACS (Veterans Aging Cohort Study) Index Calculator which estimates prognosis for HIV+ patients, 2) Neuropath/CDS which assists in the medical management of patients with neuropathic pain, and 3) TRIM (Tool to Reduce Inappropriate Medications) which identifies potentially inappropriate medications in older adults and provides recommendations for improving the medication regimen. RESULTS: The paper provides an overview of the VA EHR environment and discusses specific informatics issues/challenges that arose in the context of each of the three Web-based CDS systems. We discuss specific informatics methods and provide details of approaches that may be useful within this setting. CONCLUSIONS: Informatics issues and challenges relating to data access and data availability arose because of the particular architecture of the national VA infrastructure and the need to link to that infrastructure from local Web-based CDS systems. Idiosyncrasies of VA patient data, especially the medication data, also posed challenges. Other issues related to specific functional needs of individual CDS systems. The goal of this paper is to describe these issues so that our experience may serve as a useful foundation to assist others who wish to build such systems in the future.

Disparities in hepatitis C testing in U.S. veterans born 1945-1965.

BACKGROUND & AIMS: Universal one-time antibody testing for hepatitis C virus (HCV) infection has been recommended by the centers for disease control (CDC) and the United States preventative services task force (USPSTF) for Americans born 1945-1965 (birth cohort). Limited data exists addressing national HCV testing practices. We studied patterns and predictors of HCV testing across the U.S. within the birth cohort utilizing data from the national corporate data warehouse of the U.S. Veterans Administration (VA) health system. METHODS: Testing was defined as any HCV test including antibody, RNA or genotype performed during 2000-2013. RESULTS: Of 6,669,388 birth cohort veterans, 4,221,135 (63%) received care within the VA from 2000-2013 with two or more visits. Of this group, 2,139,935 (51%) had HCV testing with 8.1% HCV antibody and 5.4% RNA positive. Significant variation in testing was observed across centers (range: 7-83%). Older, male, African-Americans, with established risk factors and receiving care from urban centers of excellence were more likely to be tested. Among veterans free of other established risk factors (HIV negative, HBV negative, ALT ⩽40U/L, FIB-4 ⩽1.45, or APRI <0.5), HCV antibody and RNA were positive in 2.8% and 0.9%, respectively, comparable to established national average. At least 2.4-4.4% of veterans had scores suggesting advanced fibrosis (APRI ⩾1.5 or FIB-4 >3.25) with >30-43% having positive HCV RNA but >16-20% yet to undergo testing for HCV. CONCLUSIONS: Significant disparities are observed in HCV testing within the United States VA health system. Examination of the predictors of testing and HCV positivity may help inform national screening policies. LAY SUMMARY: Analysis of United States Veterans Administration data show significant disparities in hepatitis C virus testing of veterans born 1945-1965 (birth cohort). A fifth of those not tested had evidence of advanced liver fibrosis. Our data suggests some predictors for this disparity and will potentially help inform future policy measures in the era of universal birth cohort testing for HCV.

Pilot of decision support to individualize colorectal cancer screening recommendations.

OBJECTIVES: To test the feasibility of using an electronic medical record (EMR)-based decision support system (DSS) that incorporates morbidity and frailty information to individualize colorectal cancer (CRC) screening recommendations. STUDY DESIGN: Our framework used the payoff time, defined as the minimum time until the benefits of screening exceed the harms. METHODS: Subjects were 24 patients eligible for CRC screening and 22 primary care providers (PCPs). Measures included PCP satisfaction with existing reminder systems and with decision support. RESULTS: The run-in phase, during which the intervention was inactive but its performance was verified, had 14 patients enrolled. The intervention phase, during which payoff time and life expectancy calculations were used to recommend for or against CRC screening, had 10 patients enrolled. Of the 10 patients enrolled in the intervention phase, the DSS recommended in favor of CRC screening for 6 patients. (The PCPs also recommended it for those 6 patients, although 3 refused the screening.) The DSS recommended against CRC screening for 4 patients, while the PCPs recommended against it for 3 of those 4 and ordered the screening for 1 patient. PCPs who had patients enrolled in the intervention phase indicated interest in having payoff time information for all patients eligible for CRC screening. This pilot study was small and was not powered to determine the effect of the intervention on screening behavior. CONCLUSIONS: Colorectal cancer screening involves balancing immediate harms with longer-term benefits; EMR decision support may facilitate personalized benefit/harm assessment. The payoff time framework is feasible for implementation in EMR decision support.

Comparison of two VA laboratory data repositories indicates that missing data vary despite originating from the same source.

BACKGROUND: Assessing accuracy and completeness of data is an important component of conducting research. VA Healthcare System benefits from a highly developed electronic medical information system. The Immunology Case Registry was designed to monitor costs and quality of HIV care. The Decision Support System was developed to monitor utilization and costs of veterans in care. Because these systems extract data from the same source using independent methods, they provide an opportunity to compare the accuracy and completeness of each. OBJECTIVE: To compare overlapping laboratory data from the Veterans Affairs Health Information System between 2 data repositories. RESEARCH DESIGN: For hemoglobin, CD4 lymphocyte counts (CD4), HIV RNA viral load, aspartate aminotransferase, alanine aminotransferase, glycosylated hemoglobin, creatinine, and white blood count, we calculated the percent of individuals with a value from each source. For results in both repositories, we calculated Pearson's correlation coefficients. SUBJECTS: A total of 22,647 HIV+ veterans in the Virtual Cohort with a visit in fiscal year 2002. RESULTS: For 6 out of 9 tests, 68% to 72% of the observations overlapped. For CD4, viral load, and glycosylated hemoglobin less than 31% of observations overlapped. Overlapping results were nearly perfectly correlated except for CD4. CONCLUSIONS: Six of the laboratory tests demonstrated remarkably similar amounts of overlap, though Immunology Case Registry and Decision Support System both have missing data. Findings indicate that validation of laboratory data should be conducted before its use in quality and efficiency projects. When 2 databases are not available for comparison, other methods of validation should be implemented.

Measuring performance directly using the veterans health administration electronic medical record: a comparison with external peer review.

BACKGROUND: Electronic medical records systems (EMR) contain many directly analyzable data fields that may reduce the need for extensive chart review, thus allowing for performance measures to be assessed on a larger proportion of patients in care. OBJECTIVE: This study sought to determine the extent to which selected chart review-based clinical performance measures could be accurately replicated using readily available and directly analyzable EMR data. METHODS: A cross-sectional study using full chart review results from the Veterans Health Administration's External Peer Review Program (EPRP) was merged to EMR data. RESULTS: Over 80% of the data on these selected measures found in chart review was available in a directly analyzable form in the EMR. The extent of missing EMR data varied by site of care (P<0.01). Among patients on whom both sources of data were available, we found a high degree of correlation between the 2 sources in the measures assessed (correlations of 0.89-0.98) and in the concordance between the measures using performance cut points (kappa: 0.86-0.99). Furthermore, there was little evidence of bias; the differences in values were not clinically meaningful (difference of 0.9 mg/dL for low-density lipoprotein cholesterol, 1.2 mm Hg for systolic blood pressure, 0.3 mm Hg for diastolic, and no difference for HgbA1c). CONCLUSIONS: Directly analyzable data fields in the EMR can accurately reproduce selected EPRP measures on most patients. We found no evidence of systematic differences in performance values among these with and without directly analyzable data in the EMR.