Olga V. Patterson

Association Between HIV Infection and the Risk of Heart Failure With Reduced Ejection Fraction and Preserved Ejection Fraction in the Antiretroviral Therapy Era: Results From the Veterans Aging Cohort Study

Importance With improved survival, heart failure (HF) has become a major complication for individuals with human immunodeficiency virus (HIV) infection. It is unclear if this risk extends to different types of HF in the antiretroviral therapy (ART) era. Determining whether HIV infection is associated with HF with reduced ejection fraction (HFrEF), HF with preserved ejection fraction (HFpEF), or both is critical because HF types differ with respect to underlying mechanism, treatment, and prognosis. Objectives To investigate whether HIV infection increases the risk of future HFrEF and HFpEF and to assess if this risk varies by sociodemographic and HIV-specific factors. Design, Setting, and Participants This study evaluated 98 015 participants without baseline cardiovascular disease from the Veterans Aging Cohort Study, an observational cohort of HIV-infected veterans and uninfected veterans matched by age, sex, race/ethnicity, and clinical site, enrolled on or after April 1, 2003, and followed up through September 30, 2012. The dates of the analysis were October 2015 to November 2016. Exposure Human immunodeficiency virus infection. Main Outcomes and Measures Outcomes included HFpEF (EF≥50%), borderline HFpEF (EF 40%-49%), HFrEF (EF<40%), and HF of unknown type (EF missing). Results Among 98 015 participants, the mean (SD) age at enrollment in the study was 48.3 (9.8) years, 97.0% were male, and 32.2% had HIV infection. During a median follow-up of 7.1 years, there were 2636 total HF events (34.6% were HFpEF, 15.5% were borderline HFpEF, 37.1% were HFrEF, and 12.8% were HF of unknown type). Compared with uninfected veterans, HIV-infected veterans had an increased risk of HFpEF (hazard ratio [HR], 1.21; 95% CI, 1.03-1.41), borderline HFpEF (HR, 1.37; 95% CI, 1.09-1.72), and HFrEF (HR, 1.61; 95% CI, 1.40-1.86). The risk of HFrEF was pronounced in veterans younger than 40 years at baseline (HR, 3.59; 95% CI, 1.95-6.58). Among HIV-infected veterans, time-updated HIV-1 RNA viral load of at least 500 copies/mL compared with less than 500 copies/mL was associated with an increased risk of HFrEF, and time-updated CD4 cell count less than 200 cells/mm3 compared with at least 500 cells/mm3 was associated with an increased risk of HFrEF and HFpEF. Conclusions and Relevance Individuals who are infected with HIV have an increased risk of HFpEF, borderline HFpEF, and HFrEF compared with uninfected individuals. The increased risk of HFrEF can manifest decades earlier than would be expected in a typical uninfected population. Future research should focus on prevention, risk stratification, and identification of the mechanisms for HFrEF and HFpEF in the HIV-infected population.

Using multiple sources of data for surveillance of postoperative venous thromboembolism among surgical patients treated in Department of Veterans Affairs hospitals, 2005-2010

BACKGROUND There are limitations to using administrative data to identify postoperative venous thromboembolism (VTE). We used a novel approach to quantify postoperative VTE events among Department of Veterans Affairs (VA) surgical patients during 2005-2010. METHODS We used VA administrative data to exclude patients with VTE during 12 months prior to surgery. We identified probable postoperative VTE events within 30 and 90 days post-surgery in three settings: 1) pre-discharge inpatient, using a VTE diagnosis code and a pharmacy record for anticoagulation; 2) post-discharge inpatient, using a VTE diagnosis code followed by a pharmacy record for anticoagulation within 7 days; and 3) outpatient, using a VTE diagnosis code and either anticoagulation or a therapeutic procedure code with natural language processing (NLP) to confirm acute VTE in clinical notes. RESULTS Among 468,515 surgeries without prior VTE, probable VTEs were documented within 30 and 90 days in 3,931 (0.8%) and 5,904 (1.3%), respectively. Of probable VTEs within 30 or 90 days post-surgery, 47.8% and 62.9%, respectively, were diagnosed post-discharge. Among post-discharge VTE diagnoses, 86% resulted in a VA hospital readmission. Fewer than 25% of outpatient records with both VTE diagnoses and anticoagulation prescriptions were confirmed by NLP as acute VTE events. CONCLUSION More than half of postoperative VTE events were diagnosed post-discharge; analyses of surgical discharge records are inadequate to identify postoperative VTE. The NLP results demonstrate that the combination of VTE diagnoses and anticoagulation prescriptions in outpatient administrative records cannot be used to validly identify postoperative VTE events.

Increased Echocardiographic Pulmonary Pressure in HIV-infected and -uninfected Individuals in the Veterans Aging Cohort Study

Rationale: The epidemiology and prognostic impact of increased pulmonary pressure among HIV‐infected individuals in the antiretroviral therapy era is not well described. Objectives: To examine the prevalence, clinical features, and outcomes of increased echocardiographic pulmonary pressure in HIV‐infected and ‐uninfected individuals. Methods: This study evaluated 8,296 veterans referred for echocardiography with reported pulmonary artery systolic pressure (PASP) estimates from the Veterans Aging Cohort study, an observational cohort of HIV‐infected and ‐uninfected veterans matched by age, sex, race/ethnicity, and clinical site. The primary outcome was adjusted mortality by HIV status. Measurements and Main Results: PASP was reported in 2,831 HIV‐infected and 5,465 HIV‐uninfected veterans (follow‐up [mean ± SD], 3.8 ± 2.6 yr). As compared with uninfected veterans, HIV‐infected veterans with HIV viral load greater than 500 copies/ml (odds ratio, 1.27; 95% confidence interval [CI], 1.05–1.54) and those with CD4 cell count less than 200 cells/&mgr;l (odds ratio, 1.28; 95% CI, 1.02–1.60) had a higher prevalence of PASP greater than or equal to 40 mm Hg. As compared with uninfected veterans with a PASP less than 40 mm Hg, HIV‐infected veterans with a PASP greater than or equal to 40 mm Hg had an increased risk of death (adjusted hazard ratio, 1.78; 95% CI, 1.57–2.01). This risk persisted even among participants without prevalent comorbidities (adjusted hazard ratio, 3.61; 95% CI, 2.17–6.01). The adjusted risk of mortality in HIV‐infected veterans was higher at all PASP values than in uninfected veterans, including at values currently considered to be normal. Conclusions: HIV‐infected people with high HIV viral loads or low CD4 cell counts have a higher prevalence of increased PASP than uninfected people. Mortality risk in HIV‐infected veterans increases at lower values of PASP than previously recognized and is present even among those without prevalent comorbidities. These findings may inform clinical decision‐making regarding screening and surveillance of pulmonary hypertension in HIV‐infected individuals.

Unlocking echocardiogram measurements for heart disease research through natural language processing

BackgroundIn order to investigate the mechanisms of cardiovascular disease in HIV infected and uninfected patients, an analysis of echocardiogram reports is required for a large longitudinal multi-center study.ImplementationA natural language processing system using a dictionary lookup, rules, and patterns was developed to extract heart function measurements that are typically recorded in echocardiogram reports as measurement-value pairs. Curated semantic bootstrapping was used to create a custom dictionary that extends existing terminologies based on terms that actually appear in the medical record. A novel disambiguation method based on semantic constraints was created to identify and discard erroneous alternative definitions of the measurement terms. The system was built utilizing a scalable framework, making it available for processing large datasets.ResultsThe system was developed for and validated on notes from three sources: general clinic notes, echocardiogram reports, and radiology reports. The system achieved F-scores of 0.872, 0.844, and 0.877 with precision of 0.936, 0.982, and 0.969 for each dataset respectively averaged across all extracted values. Left ventricular ejection fraction (LVEF) is the most frequently extracted measurement. The precision of extraction of the LVEF measure ranged from 0.968 to 1.0 across different document types.ConclusionsThis system illustrates the feasibility and effectiveness of a large-scale information extraction on clinical data. New clinical questions can be addressed in the domain of heart failure using retrospective clinical data analysis because key heart function measurements can be successfully extracted using natural language processing.

Document sublanguage clustering to detect medical specialty in cross-institutional clinical texts

This paper reports on a set of studies designed to identify sublanguages in documents for domain-specific processing across institutions. Psychological evidence indicates that humans use context-specific linguistic information when they read. Natural Language Processing (NLP) pipelines are successful within specific domains (i.e., contexts). To limit the number of domain-specific NLP systems, a natural focus would be on sublanguages. Sublanguages are identified by shared lexical and semantic features.[1] Patterson and Hurdle[2] developed a sublanguage identification system that functioned well for 12 clinical specialties at the University of Utah. The current work compares sublanguages across institutions. Using a clinical NLP pipeline augmented by a new document corpus from the University of Pittsburg (UPitt), new documents were assigned to clusters based on the minimum cosine-distance to a Utah cluster centroid. The UPitt documents were divided into a nine-group specialty corpus. Across institutions, five of the specialty groups fell within the expected clusters. We find that clustering encounters difficulty due to documents with mixed sublanguages; naming convention differences across institutions; and document types used across specialties. The findings indicate that clinical specialty sublanguages can be identified across institutions.

Classifying the Indication for Colonoscopy Procedures: A Comparison of NLP Approaches in a Diverse National Healthcare System.

In order to measure the level of utilization of colonoscopy procedures, identifying the primary indication for the procedure is required. Colonoscopies may be utilized not only for screening, but also for diagnostic or therapeutic purposes. To determine whether a colonoscopy was performed for screening, we created a natural language processing system to identify colonoscopy reports in the electronic medical record system and extract indications for the procedure. A rule-based model and three machine-learning models were created using 2,000 manually annotated clinical notes of patients cared for in the Department of Veterans Affairs. Performance of the models was measured and compared. Analysis of the models on a test set of 1,000 documents indicates that the rule-based system performance stays fairly constant as evaluated on training and testing sets. However, the machine learning model without feature selection showed significant decrease in performance. Therefore, rule-based classification system appears to be more robust than a machine-learning system in cases when no feature selection is performed.

Measuring physician adherence with gout quality indicators: a role for natural language processing.

To evaluate physician adherence with gout quality indicators (QIs) for medication use and monitoring, and behavioral modification (BM).

Development of a Natural Language Processing Engine to Generate Bladder Cancer Pathology Data for Health Services Research

OBJECTIVE To take the first step toward assembling population-based cohorts of patients with bladder cancer with longitudinal pathology data, we developed and validated a natural language processing (NLP) engine that abstracts pathology data from full-text pathology reports. METHODS Using 600 bladder pathology reports randomly selected from the Department of Veterans Affairs, we developed and validated an NLP engine to abstract data on histology, invasion (presence vs absence and depth), grade, the presence of muscularis propria, and the presence of carcinoma in situ. Our gold standard was based on an independent review of reports by 2 urologists, followed by adjudication. We assessed the NLP performance by calculating the accuracy, the positive predictive value, and the sensitivity. We subsequently applied the NLP engine to pathology reports from 10,725 patients with bladder cancer. RESULTS When comparing the NLP output to the gold standard, NLP achieved the highest accuracy (0.98) for the presence vs the absence of carcinoma in situ. Accuracy for histology, invasion (presence vs absence), grade, and the presence of muscularis propria ranged from 0.83 to 0.96. The most challenging variable was depth of invasion (accuracy 0.68), with an acceptable positive predictive value for lamina propria (0.82) and for muscularis propria (0.87) invasion. The validated engine was capable of abstracting pathologic characteristics for 99% of the patients with bladder cancer. CONCLUSION NLP had high accuracy for 5 of 6 variables and abstracted data for the vast majority of the patients. This now allows for the assembly of population-based cohorts with longitudinal pathology data.

A Framework for Leveraging “Big Data” to Advance Epidemiology and Improve Quality: Design of the VA Colonoscopy Collaborative

Objective: To describe a framework for leveraging big data for research and quality improvement purposes and demonstrate implementation of the framework for design of the Department of Veterans Affairs (VA) Colonoscopy Collaborative. Methods: We propose that research utilizing large-scale electronic health records (EHRs) can be approached in a 4 step framework: 1) Identify data sources required to answer research question; 2) Determine whether variables are available as structured or free-text data; 3) Utilize a rigorous approach to refine variables and assess data quality; 4) Create the analytic dataset and perform analyses. We describe implementation of the framework as part of the VA Colonoscopy Collaborative, which aims to leverage big data to 1) prospectively measure and report colonoscopy quality and 2) develop and validate a risk prediction model for colorectal cancer (CRC) and high-risk polyps. Results: Examples of implementation of the 4 step framework are provided. To date, we have identified 2,337,171 Veterans who have undergone colonoscopy between 1999 and 2014. Median age was 62 years, and 4.6 percent (n = 106,860) were female. We estimated that 2.6 percent (n = 60,517) had CRC diagnosed at baseline. An additional 1 percent (n = 24,483) had a new ICD-9 code-based diagnosis of CRC on follow up. Conclusion: We hope our framework may contribute to the dialogue on best practices to ensure high quality epidemiologic and quality improvement work. As a result of implementation of the framework, the VA Colonoscopy Collaborative holds great promise for 1) quantifying and providing novel understandings of colonoscopy outcomes, and 2) building a robust approach for nationwide VA colonoscopy quality reporting.

Epidemiology of nontuberculous mycobacterial infections in the U.S. Veterans Health Administration

Objective We identified patients with non-tuberculous mycobacterial (NTM) disease in the US Veterans Health Administration (VHA), examined the distribution of diseases by NTM species, and explored the association between NTM disease and the frequency of clinic visits and mortality. Methods We combined mycobacterial isolate (from natural language processing) with ICD-9-CM diagnoses from VHA data between 2008 and 2012 and then applied modified ATS/IDSA guidelines for NTM diagnosis. We performed validation against a reference standard of chart review. Incidence rates were calculated. Two nested case-control studies (matched by age and location) were used to measure the association between NTM disease and each of 1) the frequency of outpatient clinic visits and 2) mortality, both adjusted by chronic obstructive pulmonary disease (COPD), other structural lung diseases, and immunomodulatory factors. Results NTM cases were identified with a sensitivity of 94%, a specificity of >99%. The incidence of NTM was 12.6/100k patient-years. COPD was present in 68% of pulmonary NTM. NTM incidence was highest in the southeastern US. Extra-pulmonary NTM rates increased during the study period. The incidence rate ratio of clinic visits in the first year after diagnosis was 1.3 [95%CI 1.34–1.35]. NTM patients had a hazard ratio of mortality of 1.4 [95%CI 1.1–1.9] in the 6 months after NTM identification compared to controls and 1.99 [95%CI 1.8–2.3] thereafter. Conclusions In VHA, pulmonary NTM disease is commonly associated with COPD, with the highest rates in the southeastern US. After adjustment, NTM patients had more clinic visits and greater mortality compared to matched patients.