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

Garvin, Jennifer H.; Kim, Youngjun; Gobbel, Glenn T.; Matheny, Michael E.; Redd, Andrew; Bray, Bruce E.; Heidenreich, Paul A.; Bolton, Dan; Heavirland, Julia; Kelly, Natalie; Reeves, Ruth; Kalsy, Megha; Goldstein, Mary K.; Meystre, Stéphane M.

doi:10.2196/medinform.9150

Cited by 32 publications

(20 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…▪ 72 non-intervention studies [ 150 , 151 , 154 , 157 , 159 , 161 , 163 – 166 , 169 , 170 , 172 – 175 , 177 , 180 , 181 , 186 – 193 , 195 – 200 , 204 , 210 , 213 , 215 , 216 , 218 , 224 , 226 – 233 , 237 – 242 , 246 – 248 , 253 , 256 , 257 , 262 , 264 , 267 , 271 , 272 , 275 , 286 , 293 – 295 , 298 , 302 ]…”

Section: Resultsunclassified

The use of the PARIHS framework in implementation research and practice—a citation analysis of the literature

et al. 2020

View full text Add to dashboard Cite

Background: The Promoting Action on Research Implementation in Health Services (PARIHS) framework was developed two decades ago and conceptualizes successful implementation (SI) as a function (f) of the evidence (E) nature and type, context (C) quality, and the facilitation (F), [SI = f (E,C,F)]. Despite a growing number of citations of theoretical frameworks including PARIHS, details of how theoretical frameworks are used remains largely unknown. This review aimed to enhance the understanding of the breadth and depth of the use of the PARIHS framework. Methods: This citation analysis commenced from four core articles representing the key stages of the framework's development. The citation search was performed in Web of Science and Scopus. After exclusion, we undertook an initial assessment aimed to identify articles using PARIHS and not only referencing any of the core articles. To assess this, all articles were read in full. Further data extraction included capturing information about where (country/ countries and setting/s) PARIHS had been used, as well as categorizing how the framework was applied. Also, strengths and weaknesses, as well as efforts to validate the framework, were explored in detail. Results: The citation search yielded 1613 articles. After applying exclusion criteria, 1475 articles were read in full, and the initial assessment yielded a total of 367 articles reported to have used the PARIHS framework. These articles were included for data extraction. The framework had been used in a variety of settings and in both high-, middle-, and low-income countries. With regard to types of use, 32% used PARIHS in planning and delivering an intervention, 50% in data analysis, 55% in the evaluation of study findings, and/or 37% in any other way. Further analysis showed that its actual application was frequently partial and generally not well elaborated. Conclusions: In line with previous citation analysis of the use of theoretical frameworks in implementation science, we also found a rather superficial description of the use of PARIHS. Thus, we propose the development and adoption of reporting guidelines on how framework(s) are used in implementation studies, with the expectation that this will enhance the maturity of implementation science.

show abstract

Section: Resultsunclassified

The use of the PARIHS framework in implementation research and practice—a citation analysis of the literature

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Absence of readily available EF measurements limits research on HF in routine EHR data. Several natural language processing models could be used to extract data on left ventricular systolic function reported as free text in EHR 21,22 . For those instances that this information is not available, simple prediction models for EF might be used to gain more knowledge on HF phenotypic information in EHRs, claim databases, trials, and large cohorts.…”

Section: Discussionmentioning

confidence: 99%

A registry‐based algorithm to predict ejection fraction in patients with heart failure

et al. 2020

View full text Add to dashboard Cite

Aims Left ventricular ejection fraction (EF) is required to categorize heart failure (HF) [i.e. HF with preserved (HFpEF), mid-range (HFmrEF), and reduced (HFrEF) EF] but is often not captured in population-based cohorts or non-HF registries. The aim was to create an algorithm that identifies EF subphenotypes for research purposes. Methods and results We included 42 061 HF patients from the Swedish Heart Failure Registry. As primary analysis, we performed two logistic regression models including 22 variables to predict (i) EF≥ vs. <50% and (ii) EF≥ vs. <40%. In the secondary analysis, we performed a multivariable multinomial analysis with 22 variables to create a model for all three separate EF subphenotypes: HFrEF vs. HFmrEF vs. HFpEF. The models were validated in the database from the CHECK-HF study, a cross-sectional survey of 10 627 patients from the Netherlands. The C-statistic (discrimination) was 0.78 [95% confidence interval (CI) 0.77-0.78] for EF ≥50% and 0.76 (95% CI 0.75-0.76) for EF ≥40%. Similar results were achieved for HFrEF and HFpEF in the multinomial model, but the C-statistic for HFmrEF was lower: 0.63 (95% CI 0.63-0.64). The external validation showed similar discriminative ability to the development cohort. Conclusions Routine clinical characteristics could potentially be used to identify different EF subphenotypes in databases where EF is not readily available. Accuracy was good for the prediction of HFpEF and HFrEF but lower for HFmrEF. The proposed algorithm enables more effective research on HF in the big data setting.

show abstract

“…Our analysis showed that the most popular stand-alone (or plug-in) annotation tools are Knowtator, MMAX2 and UAM Corpus. On one hand, Knowtator, which is a plug-in for the Protégé tool, is still popular in the biomedical domain given its good support for ontologies, and was recently used for an extension of the CRAFT corpus [ 98 ], as well as in a couple of clinical corpora [ 99 , 100 ]. On the other hand, MMAX2 was usually used for the annotation of linguistic elements, especially for coreferential and anaphorical relations [ 101 , 102 ].…”

Section: Discussionmentioning

confidence: 99%

An extensive review of tools for manual annotation of documents

Neves

Ševa

2019

Briefings in Bioinformatics

View full text Add to dashboard Cite

Motivation Annotation tools are applied to build training and test corpora, which are essential for the development and evaluation of new natural language processing algorithms. Further, annotation tools are also used to extract new information for a particular use case. However, owing to the high number of existing annotation tools, finding the one that best fits particular needs is a demanding task that requires searching the scientific literature followed by installing and trying various tools. Methods We searched for annotation tools and selected a subset of them according to five requirements with which they should comply, such as being Web-based or supporting the definition of a schema. We installed the selected tools (when necessary), carried out hands-on experiments and evaluated them using 26 criteria that covered functional and technical aspects. We defined each criterion on three levels of matches and a score for the final evaluation of the tools. Results We evaluated 78 tools and selected the following 15 for a detailed evaluation: BioQRator, brat, Catma, Djangology, ezTag, FLAT, LightTag, MAT, MyMiner, PDFAnno, prodigy, tagtog, TextAE, WAT-SL and WebAnno. Full compliance with our 26 criteria ranged from only 9 up to 20 criteria, which demonstrated that some tools are comprehensive and mature enough to be used on most annotation projects. The highest score of 0.81 was obtained by WebAnno (of a maximum value of 1.0).

show abstract

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

Cited by 32 publications

References 45 publications

The use of the PARIHS framework in implementation research and practice—a citation analysis of the literature

The use of the PARIHS framework in implementation research and practice—a citation analysis of the literature

A registry‐based algorithm to predict ejection fraction in patients with heart failure

An extensive review of tools for manual annotation of documents

Contact Info

Product

Resources

About