A Comparison of Veterans with Problematic Opioid Use Identified through Natural Language Processing of Clinical Notes versus Using Diagnostic Codes.

Opioid use disorder is known to be under-coded as a diagnosis, yet problematic opioid use can be documented in clinical notes, which are included in electronic health records. We sought to identify problematic opioid use from a full range of clinical notes and compare the demographic and clinical characteristics of patients identified as having problematic opioid use exclusively in clinical notes to patients documented through ICD opioid use disorder diagnostic codes. We developed and applied a natural language processing (NLP) tool that combines rule-based pattern analysis and a trained support vector machine to the clinical notes of a patient cohort (n = 222,371) from two Veteran Affairs service regions to identify patients with problematic opioid use. We also used a set of ICD diagnostic codes to identify patients with opioid use disorder from the same cohort. The NLP tool achieved 96.6% specificity, 90.4% precision/PPV, 88.4% sensitivity/recall, and 94.4% accuracy on unseen test data. NLP exclusively identified 57,331 patients; 6997 patients had positive ICD code identifications. Patients exclusively identified through NLP were more likely to be women. Those identified through ICD codes were more likely to be male, younger, have concurrent benzodiazepine prescriptions, more comorbidities, and more care encounters, and were less likely to be married. Patients in both these groups had substantially elevated comorbidity levels compared with patients not documented through either method as experiencing problematic opioid use. Clinicians may be reluctant to code for opioid use disorder. It is therefore incumbent on the healthcare team to search for documentation of opioid concerns within clinical notes.

Opioid use and opioid use disorder in mono and dual-system users of veteran affairs medical centers.

Introduction: Efforts to achieve opioid guideline concordant care may be undermined when patients access multiple opioid prescription sources. Limited data are available on the impact of dual-system sources of care on receipt of opioid medications. Objective: We examined whether dual-system use was associated with increased rates of new opioid prescriptions, continued opioid prescriptions and diagnoses of opioid use disorder (OUD). We hypothesized that dual-system use would be associated with increased odds for each outcome. Methods: This retrospective cohort study was conducted using Veterans Administration (VA) data from two facilities from 2015 to 2019, and included active patients, defined as Veterans who had at least one encounter in a calendar year (2015-2019). Dual-system use was defined as receipt of VA care as well as VA payment for community care (non-VA) services. Mono users were defined as those who only received VA services. There were 77,225 dual-system users, and 442,824 mono users. Outcomes were three binary measures: new opioid prescription, continued opioid prescription (i.e., received an additional opioid prescription), and OUD diagnosis (during the calendar year). We conducted a multivariate logistic regression accounting for the repeated observations on patient and intra-class correlations within patients. Results: Dual-system users were significantly younger than mono users, more likely to be women, and less likely to report white race. In adjusted models, dual-system users were significantly more likely to receive a new opioid prescription during the observation period [Odds ratio (OR) = 1.85, 95% confidence interval (CI) 1.76-1.93], continue prescriptions (OR = 1.24, CI 1.22-1.27), and to receive an OUD diagnosis (OR = 1.20, CI 1.14-1.27). Discussion: The prevalence of opioid prescriptions has been declining in the US healthcare systems including VA, yet the prevalence of OUD has not been declining at the same rate. One potential problem is that detailed notes from non-VA visits are not immediately available to VA clinicians, and information about VA care is not readily available to non-VA sources. One implication of our findings is that better health system coordination is needed. Even though care was paid for by the VA and presumably closely monitored, dual-system users were more likely to have new and continued opioid prescriptions.

Using comparative effectiveness research to remedy health disparities.

Health disparities are an important and continuing problem of considerable research importance. Comparative effectiveness research (CER) is an excellent vehicle to evaluate interventions to remedy disparities. We classify CER for disparities at three levels of science: basic biology, care and systems, and social and cultural context. In basic biology, genomics will delineate treatments for specific individuals and populations. Care and systems interventions are most important research areas to improve process and quality measures. However, there is evidence that correction of healthcare processes disparities will not be sufficient to improve health and that social and cultural research may be key in this regard. The methodology of CER for disparities is the same as that of other research with randomized controlled trials the gold standard and database analysis, and other observational and quasi-experimental methods important and effective. In addition, mixed methods and multilevel modeling offer promise. Community involvement in research and patient preferences among high-quality choices need to be included in planning of CER.

Commentary: building human capital: discovery, learning, and professional satisfaction.

Physician satisfaction is an important contributor to a well-functioning health system. Mohr and Burgess report that physicians in the Veterans Health Administration (VA) who spend time in research have greater overall job satisfaction, that satisfaction tracks with aggregate facility research funding, and that satisfaction is higher among physicians working in VA facilities located on the same campus or within walking distance of an affiliated medical school. An environment conducive to research therefore not only advances science but also seems to be a key element of physician satisfaction. In addition to advancing scientific discovery and promoting greater physician satisfaction, these findings suggest that an environment of discovery and learning may yield benefits beyond specific academic endeavors and contribute more broadly to supporting health system performance.

The past, present, and future of comparative effectiveness research in the US Department of Veterans Affairs.

A particular challenge for the healthcare provider and the patient is to choose among competing therapeutic approaches for a particular condition. Often, the relative benefits and risks of potential therapies are not uniformly available from the existing scientific information. Many have pointed to the need for more comparative effectiveness research (CER) to aide in these decisions. The US Department of Veterans Affairs (VA) has a long history of conducting CER. The success of the VA CER program has been facilitated by several important aspects of scientific infrastructure related to (1) research question refinement, (2) study design, planning and coordination, (3) evidence synthesis, and (4) implementation research. In publications that had VA coauthors in 2 major medical journals, 25% of the published studies were classified as CER. The most frequent categories of study were pharmaceutical and behavioral interventions. In the future, the CER enterprise will move toward increased input from clinicians in research topic choice and enhanced consideration of other methodologies besides the randomized controlled trial.

Implementation research: a critical component of realizing the benefits of comparative effectiveness research.

Comparative effectiveness research (CER) holds the promise of improving patient-centered care and increasing value in the healthcare system. Achieving these goals, however, depends on effectively implementing the findings of CER. In this article, we draw on lessons from implementation research and our experience in the Veterans Administration (VA) healthcare system to offer recommendations about what is needed to support implementation of CER. There is no single strategy for successful implementation. Implementation efforts must take into account the nature of the evidence, the type of change being implemented, the clinical context in which the findings are being applied, and the specific barriers and facilitators to implementing new practices. The experience of the VA illustrates the importance of taking a systems approach that aligns numerous elements of the healthcare system--guidelines, decision support, performance measures, financial incentives, coverage and benefits policy, and health information technology--to support implementation:. We illustrate these principles with an example of implementing a new model of evidence-based depression care.

The Veterans Affairs experience: comparative effectiveness research in a large health system.

Comparative effectiveness research is a tool to use in achieving patient-centered, high-value health care. However, applying the results to individual patients and health systems raises unique issues. Here, we review lessons learned by the Veterans Health Administration (VHA) in developing and implementing the research in a large integrated health system. Decision makers should examine whether individual studies apply to diverse populations, align tools and incentives to adopt evidence-based practices, and consider both the patient and population perspectives. A key challenge remains how to incorporate comparative evidence and patient values into busy clinical practices.

Comparative effectiveness research: what kind of studies do we need?

Comparative effectiveness research (CER) is increasingly popular, yet discussions of its conduct and consequences often overlook the extensive history of comparing different therapeutic options in patient-oriented research. In particular, research in the Department of Veterans Affairs (VA) has included a decades-long focus on generating information that can enhance medical decision making and improve health outcomes. Categories of such research include multisite randomized controlled trials (conducted by the Cooperative Studies Program) and observational studies involving either primary or secondary data collection. As representative examples from cardiology, a landmark VA clinical trial published in the 1970s evaluated the benefits of coronary artery bypass grafting surgery among patients with angina; a VA trial initiated in the 1990s, and identified formally as CER, demonstrated that percutaneous coronary intervention is not superior to optimal medical therapy; and a database investigation using information from the VA electronic medical record system in the 2000s found that use of proton pump inhibitor medication is associated with the attenuation of the benefits of clopidogrel among patients hospitalized for acute coronary syndrome. A review of these (and other) selected projects, based on their type of study design, serves to highlight the strengths, limitations, and potential of CER.

Advancing evidence-based care for diabetes: lessons from the Veterans Health Administration.

The Veterans Health Administration (VHA) is a unique laboratory for using the electronic health record (EHR) to transform health care and accelerate discovery. This is particularly evident in the care of veterans with diabetes, who constitute a quarter of those served by the VHA. Although EHRs have enabled rapid learning, additional factors were necessary, including the lead participation of clinician-investigators, accountability through performance measurement, a delivery system focused on population health, and favorable economic externalities. "Off-the-shelf" technology is unlikely to generate similar benefits if these attributes are not in place.