Literature DB >> 33079591

Development of a Portable Tool to Identify Patients With Atrial Fibrillation Using Clinical Notes From the Electronic Medical Record.

Rashmee U Shah1, R Kannan Mutharasan2, Faraz S Ahmad2, Anna G Rosenblatt3, Hawkins C Gay2, Benjamin A Steinberg1, Mark Yandell4,5, Martin Tristani-Firouzi6,7, Jake Klewer8, Rebeka Mukherjee1, Donald M Lloyd-Jones9.   

Abstract

BACKGROUND: The electronic medical record contains a wealth of information buried in free text. We created a natural language processing algorithm to identify patients with atrial fibrillation (AF) using text alone. METHODS AND
RESULTS: We created 3 data sets from patients with at least one AF billing code from 2010 to 2017: a training set (n=886), an internal validation set from site no. 1 (n=285), and an external validation set from site no. 2 (n=276). A team of clinicians reviewed and adjudicated patients as AF present or absent, which served as the reference standard. We trained 54 algorithms to classify each patient, varying the model, number of features, number of stop words, and the method used to create the feature set. The algorithm with the highest F-score (the harmonic mean of sensitivity and positive predictive value) in the training set was applied to the validation sets. F-scores and area under the receiver operating characteristic curves were compared between site no. 1 and site no. 2 using bootstrapping. Adjudicated AF prevalence was 75.1% at site no. 1 and 86.2% at site no. 2. Among 54 algorithms, the best performing model was logistic regression, using 1000 features, 100 stop words, and term frequency-inverse document frequency method to create the feature set, with sensitivity 92.8%, specificity 93.9%, and an area under the receiver operating characteristic curve of 0.93 in the training set. The performance at site no. 1 was sensitivity 92.5%, specificity 88.7%, with an area under the receiver operating characteristic curve of 0.91. The performance at site no. 2 was sensitivity 89.5%, specificity 71.1%, with an area under the receiver operating characteristic curve of 0.80. The F-score was lower at site no. 2 compared with site no. 1 (92.5% [SD, 1.1%] versus 94.2% [SD, 1.1%]; P<0.001).
CONCLUSIONS: We developed a natural language processing algorithm to identify patients with AF using text alone, with >90% F-score at 2 separate sites. This approach allows better use of the clinical narrative and creates an opportunity for precise, high-throughput cohort identification.

Entities:  

Keywords:  algorithm; artificial intelligence; atrial fibrillation; electronic medical record; natural language processing; prevalence

Mesh:

Year:  2020        PMID: 33079591      PMCID: PMC7646941          DOI: 10.1161/CIRCOUTCOMES.120.006516

Source DB:  PubMed          Journal:  Circ Cardiovasc Qual Outcomes        ISSN: 1941-7713


  12 in total

1.  Rethinking EHR interfaces to reduce click fatigue and physician burnout.

Authors:  Roger Collier
Journal:  CMAJ       Date:  2018-08-20       Impact factor: 8.262

Review 2.  A systematic review of validated methods for identifying atrial fibrillation using administrative data.

Authors:  Paul N Jensen; Karin Johnson; James Floyd; Susan R Heckbert; Ryan Carnahan; Sascha Dublin
Journal:  Pharmacoepidemiol Drug Saf       Date:  2012-01       Impact factor: 2.890

3.  Electronic health records contributing to physician burnout.

Authors:  Roger Collier
Journal:  CMAJ       Date:  2017-11-13       Impact factor: 8.262

4.  Identification of metastatic cancer in claims data.

Authors:  Beth L Nordstrom; Joanna L Whyte; Marilyn Stolar; Catherine Mercaldi; Joel D Kallich
Journal:  Pharmacoepidemiol Drug Saf       Date:  2012-05       Impact factor: 2.890

5.  A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments.

Authors:  Jennifer A Pacheco; Luke V Rasmussen; Richard C Kiefer; Thomas R Campion; Peter Speltz; Robert J Carroll; Sarah C Stallings; Huan Mo; Monika Ahuja; Guoqian Jiang; Eric R LaRose; Peggy L Peissig; Ning Shang; Barbara Benoit; Vivian S Gainer; Kenneth Borthwick; Kathryn L Jackson; Ambrish Sharma; Andy Yizhou Wu; Abel N Kho; Dan M Roden; Jyotishman Pathak; Joshua C Denny; William K Thompson
Journal:  J Am Med Inform Assoc       Date:  2018-11-01       Impact factor: 4.497

6.  Misclassification of Myocardial Injury as Myocardial Infarction: Implications for Assessing Outcomes in Value-Based Programs.

Authors:  Cian McCarthy; Sean Murphy; Joshua A Cohen; Saad Rehman; Maeve Jones-O'Connor; David S Olshan; Avinainder Singh; Muthiah Vaduganathan; James L Januzzi; Jason H Wasfy
Journal:  JAMA Cardiol       Date:  2019-05-01       Impact factor: 14.676

7.  Caveats for the use of operational electronic health record data in comparative effectiveness research.

Authors:  William R Hersh; Mark G Weiner; Peter J Embi; Judith R Logan; Philip R O Payne; Elmer V Bernstam; Harold P Lehmann; George Hripcsak; Timothy H Hartzog; James J Cimino; Joel H Saltz
Journal:  Med Care       Date:  2013-08       Impact factor: 2.983

8.  A Simple and Portable Algorithm for Identifying Atrial Fibrillation in the Electronic Medical Record.

Authors:  Shaan Khurshid; John Keaney; Patrick T Ellinor; Steven A Lubitz
Journal:  Am J Cardiol       Date:  2015-11-06       Impact factor: 2.778

9.  Impact of Different Electronic Cohort Definitions to Identify Patients With Atrial Fibrillation From the Electronic Medical Record.

Authors:  Rashmee U Shah; Rebeka Mukherjee; Yue Zhang; Aubrey E Jones; Jennifer Springer; Ian Hackett; Benjamin A Steinberg; Donald M Lloyd-Jones; Wendy W Chapman
Journal:  J Am Heart Assoc       Date:  2020-02-26       Impact factor: 5.501

10.  Comparison of 2 Natural Language Processing Methods for Identification of Bleeding Among Critically Ill Patients.

Authors:  Maxwell Taggart; Wendy W Chapman; Benjamin A Steinberg; Shane Ruckel; Arianna Pregenzer-Wenzler; Yishuai Du; Jeffrey Ferraro; Brian T Bucher; Donald M Lloyd-Jones; Matthew T Rondina; Rashmee U Shah
Journal:  JAMA Netw Open       Date:  2018-10-05
View more
  1 in total

Review 1.  Systematic review of current natural language processing methods and applications in cardiology.

Authors:  Meghan Reading Turchioe; Alexander Volodarskiy; Jyotishman Pathak; Drew N Wright; James Enlou Tcheng; David Slotwiner
Journal:  Heart       Date:  2022-05-25       Impact factor: 7.365

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.