Dataset Information

Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs.

ABSTRACT: BACKGROUND:We developed an accurate, stakeholder-informed, automated, natural language processing (NLP) system to measure the quality of heart failure (HF) inpatient care, and explored the potential for adoption of this system within an integrated health care system. OBJECTIVE:To accurately automate a United States Department of Veterans Affairs (VA) quality measure for inpatients with HF. METHODS:We automated the HF quality measure Congestive Heart Failure Inpatient Measure 19 (CHI19) that identifies whether a given patient has left ventricular ejection fraction (LVEF) <40%, and if so, whether an angiotensin-converting enzyme inhibitor or angiotensin-receptor blocker was prescribed at discharge if there were no contraindications. We used documents from 1083 unique inpatients from eight VA medical centers to develop a reference standard (RS) to train (n=314) and test (n=769) the Congestive Heart Failure Information Extraction Framework (CHIEF). We also conducted semi-structured interviews (n=15) for stakeholder feedback on implementation of the CHIEF. RESULTS:The CHIEF classified each hospitalization in the test set with a sensitivity (SN) of 98.9% and positive predictive value of 98.7%, compared with an RS and SN of 98.5% for available External Peer Review Program assessments. Of the 1083 patients available for the NLP system, the CHIEF evaluated and classified 100% of cases. Stakeholders identified potential implementation facilitators and clinical uses of the CHIEF. CONCLUSIONS:The CHIEF provided complete data for all patients in the cohort and could potentially improve the efficiency, timeliness, and utility of HF quality measurements.

SUBMITTER: Garvin JH

PROVIDER: S-EPMC5789165 | biostudies-literature | 2018 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs.

Garvin Jennifer Hornung JH Kim Youngjun Y Gobbel Glenn Temple GT Matheny Michael E ME Redd Andrew A Bray Bruce E BE Heidenreich Paul P Bolton Dan D Heavirland Julia J Kelly Natalie N Reeves Ruth R Kalsy Megha M Goldstein Mary Kane MK Meystre Stephane M SM

JMIR medical informatics 20180115 1

<h4>Background</h4>We developed an accurate, stakeholder-informed, automated, natural language processing (NLP) system to measure the quality of heart failure (HF) inpatient care, and explored the potential for adoption of this system within an integrated health care system.<h4>Objective</h4>To accurately automate a United States Department of Veterans Affairs (VA) quality measure for inpatients with HF.<h4>Methods</h4>We automated the HF quality measure Congestive Heart Failure Inpatient Measur ...[more]

PMID: 29335238

Similar Datasets

Project description:ImportanceThe benefits of maintenance dialysis for older adults with end-stage renal disease (ESRD) are uncertain. Whether the setting of pre-ESRD nephrology care influences initiation of dialysis and mortality is not known.ObjectiveTo compare initiation of dialysis and mortality among older veterans with incident kidney failure who received pre-ESRD nephrology care in fee-for-service Medicare vs the Department of Veterans Affairs (VA).Design, setting, and participantsRetrospective cohort study of patients from the US Medicare and VA health care systems evaluated 11 215 veterans aged 67 years or older with incident kidney failure between January 1, 2008, and December 31, 2011. Data analysis was performed March 15, 2016, through September 20, 2017.ExposuresPre-ESRD nephrology care in Medicare vs VA health care systems.Main outcome and measuresDialysis treatment and death within 2 years.ResultsOf the 11 215 patients included in the study, 11 085 (98.8%) were men; mean (SD) age was 79.1 (6.9) years. Within 2 years of incident kidney failure, 7071 (63.0%) of the patients started dialysis and 5280 (47.1%) died. Patients who received pre-ESRD nephrology care in Medicare were more likely to undergo dialysis compared with patients who received pre-ESRD nephrology care in VA (82% vs 53%; adjusted risk difference, 28 percentage points; 95% CI, 26-30 percentage points). Differences in dialysis initiation between Medicare and VA were more pronounced among patients aged 80 years or older and patients with dementia or metastatic cancer, and less pronounced among patients with paralysis (P < .05 for interaction). Two-year mortality was higher for patients who received pre-ESRD care in Medicare compared with VA (53% vs 44%; adjusted risk difference, 5 percentage points; 95% CI, 3-7 percentage points). The findings were similar in a propensity-matched analysis.Conclusions and relevanceVeterans who receive pre-ESRD nephrology care in Medicare receive dialysis more often yet are also more likely to die within 2 years compared with those in VA. The VA's integrated health care system and financing appear to favor lower-intensity treatment for kidney failure in older patients without a concomitant increase in mortality.

Project description:ContextIdentifying tranquil areas is important for landscape planning and policy-making. Research demonstrated discrepancies between modelled potential tranquil areas and where people experience tranquillity based on field surveys. Because surveys are resource-intensive, user-generated text data offers potential for extracting where people experience tranquillity.ObjectivesWe explore and model the relationship between landscape ecological measures and experienced tranquillity extracted from user-generated text descriptions.MethodsGeoreferenced, user-generated landscape descriptions from Geograph.UK were filtered using keywords related to tranquillity. We stratify resulting tranquil locations according to dominant land cover and quantify the influence of landscape characteristics including diversity and naturalness on explaining the presence of tranquillity. Finally, we apply natural language processing to identify terms linked to tranquillity keywords and compare the similarity of these terms across land cover classes.ResultsEvaluation of potential keywords yielded six keywords associated with experienced tranquillity, resulting in 15,350 extracted tranquillity descriptions. The two most common land cover classes associated with tranquillity were arable and horticulture, and improved grassland, followed by urban and suburban. In the logistic regression model across all land cover classes, freshwater, elevation and naturalness were positive predictors of tranquillity. Built-up area was a negative predictor. Descriptions of tranquillity were most similar between improved grassland and arable and horticulture, and most dissimilar between arable and horticulture and urban.ConclusionsThis study highlights the potential of applying natural language processing to extract experienced tranquillity from text, and demonstrates links between landscape ecological measures and tranquillity as a perceived landscape quality.Supplementary informationThe online version of this article (10.1007/s10980-020-01181-8) contains supplementary material, which is available to authorized users.

Project description:BackgroundHeterogeneity of existing physician burnout studies impairs analyses of longitudinal trends, geographic distribution, and organizational factors impacting physician burnout. The Department of Veterans Affairs (VA) is one of the largest integrated healthcare systems in the USA, offering a unique opportunity to study burnout across VA sites and time.ObjectiveTo characterize longitudinal burnout trends of VA physicians and assess organizational characteristics and geographic distribution associated with physician burnout.DesignLongitudinal study of the VA All Employee Survey during 2013-2017.ParticipantsSelf-identified physicians practicing in one of nine clinical service areas at 140 VA sites nationwide.Main measuresWe identified burnout using a validated definition adapted from the Maslach Burnout Inventory and characterized burnout trends for physicians in different clinical service areas. We used clustering analysis to categorize sites based on their burnout rates over time, and compared organizational characteristics and geographic distribution of high, medium, and low burnout categories.Key resultsWe identified 40,382 physician responses from 140 VA sites. Mean burnout rates across all physicians ranged from 34.3% in 2013 to a high of 39.0% in 2014. Primary care physicians had the highest burnout. High burnout sites were more likely to be rural and non-teaching, have lower complexity (i.e., offer fewer advanced clinical services), and have fewer unique patients per site.ConclusionsVA physician burnout was lower than previously described in many non-VA studies and was relatively stable over time. These findings may be due to unique characteristics of the VA practice environment. Nonetheless, with over a third of VA physicians reporting burnout, organizational interventions are needed. Primary care physicians and those practicing at small, rural sites have higher rates of burnout and may warrant more focused attention. Our results can guide targeted interventions to promote VA physician well-being and inform efforts to address burnout in diverse clinical settings.

Project description:BackgroundThe Veterans Access Research Consortium (VARC), a Department of Veterans Affairs (VA) Consortium of Research focused on access to healthcare, has been funded by VA's Health Services Research and Development Service (HSR&D) to develop a research roadmap for healthcare access. The goal of the roadmap is to identify operationally aligned research questions that are most likely to lead to meaningful improvements in Veterans' healthcare access.ObjectivesTo describe the process of soliciting diverse stakeholder perspectives about key priorities on which VA's HSR&D access agenda should focus and identify the results of that process.MethodsWe used a modified Delphi approach to engage researchers and VA operational partners in a process to develop recommendations regarding the access-related research questions VA should prioritize. We then collaborated with three Veteran Engagement Groups (VEGs) across the country to solicit Veterans' reactions to the Delphi results and their perspectives about access-related issues affecting access to VA health care.ResultsThe Delphi panel consisted of 22 research and operational experts, both internal and external to VA. The Delphi process resulted in five research questions identified by the panelists as highest priority for VA to pursue, each representing one of the following domains: (1) measurement of access, (2) barriers to access, (3) equity and subpopulations, (4) effective interventions to improve access, and (5) consequences of poor/better access. Veterans' perspectives focused primarily on the barriers to access domain. Veterans indicated several barriers that might be addressed through research or operational initiatives, including poor communication about services, weak connections to and partnerships with local community care facilities, and poor provision of telehealth resources and education.ConclusionsEngaging multiple methods to solicit stakeholder perspectives enables more nuanced understanding of access-related priorities for VA. Future research should consider utilizing such an approach to identify additional research and/or operational priorities.

Dataset Information

Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs.

Publications

Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets