Literature DB >> 24406261

Influenza detection from emergency department reports using natural language processing and Bayesian network classifiers.

Ye Ye1, Fuchiang Rich Tsui1, Michael Wagner1, Jeremy U Espino2, Qi Li3.   

Abstract

OBJECTIVES: To evaluate factors affecting performance of influenza detection, including accuracy of natural language processing (NLP), discriminative ability of Bayesian network (BN) classifiers, and feature selection.
METHODS: We derived a testing dataset of 124 influenza patients and 87 non-influenza (shigellosis) patients. To assess NLP finding-extraction performance, we measured the overall accuracy, recall, and precision of Topaz and MedLEE parsers for 31 influenza-related findings against a reference standard established by three physician reviewers. To elucidate the relative contribution of NLP and BN classifier to classification performance, we compared the discriminative ability of nine combinations of finding-extraction methods (expert, Topaz, and MedLEE) and classifiers (one human-parameterized BN and two machine-parameterized BNs). To assess the effects of feature selection, we conducted secondary analyses of discriminative ability using the most influential findings defined by their likelihood ratios.
RESULTS: The overall accuracy of Topaz was significantly better than MedLEE (with post-processing) (0.78 vs 0.71, p<0.0001). Classifiers using human-annotated findings were superior to classifiers using Topaz/MedLEE-extracted findings (average area under the receiver operating characteristic (AUROC): 0.75 vs 0.68, p=0.0113), and machine-parameterized classifiers were superior to the human-parameterized classifier (average AUROC: 0.73 vs 0.66, p=0.0059). The classifiers using the 17 'most influential' findings were more accurate than classifiers using all 31 subject-matter expert-identified findings (average AUROC: 0.76>0.70, p<0.05).
CONCLUSIONS: Using a three-component evaluation method we demonstrated how one could elucidate the relative contributions of components under an integrated framework. To improve classification performance, this study encourages researchers to improve NLP accuracy, use a machine-parameterized classifier, and apply feature selection methods. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

Entities:  

Mesh:

Year:  2014        PMID: 24406261      PMCID: PMC4147621          DOI: 10.1136/amiajnl-2013-001934

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  21 in total

1.  Creating a text classifier to detect radiology reports describing mediastinal findings associated with inhalational anthrax and other disorders.

Authors:  Wendy Webber Chapman; Gregory F Cooper; Paul Hanbury; Brian E Chapman; Lee H Harrison; Michael M Wagner
Journal:  J Am Med Inform Assoc       Date:  2003-06-04       Impact factor: 4.497

2.  Automated encoding of clinical documents based on natural language processing.

Authors:  Carol Friedman; Lyudmila Shagina; Yves Lussier; George Hripcsak
Journal:  J Am Med Inform Assoc       Date:  2004-06-07       Impact factor: 4.497

3.  Diagnosing community-acquired pneumonia with a Bayesian network.

Authors:  D Aronsky; P J Haug
Journal:  Proc AMIA Symp       Date:  1998

4.  An efficient bayesian method for predicting clinical outcomes from genome-wide data.

Authors:  Gregory F Cooper; Pablo Hennings-Yeomans; Shyam Visweswaran; Michael Barmada
Journal:  AMIA Annu Symp Proc       Date:  2010-11-13

5.  Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network.

Authors:  Katherine M Newton; Peggy L Peissig; Abel Ngo Kho; Suzette J Bielinski; Richard L Berg; Vidhu Choudhary; Melissa Basford; Christopher G Chute; Iftikhar J Kullo; Rongling Li; Jennifer A Pacheco; Luke V Rasmussen; Leslie Spangler; Joshua C Denny
Journal:  J Am Med Inform Assoc       Date:  2013-03-26       Impact factor: 4.497

6.  Comparison of natural language processing biosurveillance methods for identifying influenza from encounter notes.

Authors:  Peter L Elkin; David A Froehling; Dietlind L Wahner-Roedler; Steven H Brown; Kent R Bailey
Journal:  Ann Intern Med       Date:  2012-01-03       Impact factor: 25.391

7.  Automated tuberculosis detection.

Authors:  G Hripcsak; C A Knirsch; N L Jain; A Pablos-Mendez
Journal:  J Am Med Inform Assoc       Date:  1997 Sep-Oct       Impact factor: 4.497

8.  The eMERGE Network: a consortium of biorepositories linked to electronic medical records data for conducting genomic studies.

Authors:  Catherine A McCarty; Rex L Chisholm; Christopher G Chute; Iftikhar J Kullo; Gail P Jarvik; Eric B Larson; Rongling Li; Daniel R Masys; Marylyn D Ritchie; Dan M Roden; Jeffery P Struewing; Wendy A Wolf
Journal:  BMC Med Genomics       Date:  2011-01-26       Impact factor: 3.063

9.  Probabilistic, Decision-theoretic Disease Surveillance and Control.

Authors:  Michael Wagner; Fuchiang Tsui; Gregory Cooper; Jeremy U Espino; Hendrik Harkema; John Levander; Ricardo Villamarin; Ronald Voorhees; Nicholas Millett; Christopher Keane; Anind Dey; Manik Razdan; Yang Hu; Ming Tsai; Shawn Brown; Bruce Y Lee; Anthony Gallagher; Margaret Potter
Journal:  Online J Public Health Inform       Date:  2011-12-22

10.  pROC: an open-source package for R and S+ to analyze and compare ROC curves.

Authors:  Xavier Robin; Natacha Turck; Alexandre Hainard; Natalia Tiberti; Frédérique Lisacek; Jean-Charles Sanchez; Markus Müller
Journal:  BMC Bioinformatics       Date:  2011-03-17       Impact factor: 3.307

View more
  16 in total

1.  Trends in biomedical informatics: automated topic analysis of JAMIA articles.

Authors:  Dong Han; Shuang Wang; Chao Jiang; Xiaoqian Jiang; Hyeon-Eui Kim; Jimeng Sun; Lucila Ohno-Machado
Journal:  J Am Med Inform Assoc       Date:  2015-11       Impact factor: 4.497

2.  The effects of natural language processing on cross-institutional portability of influenza case detection for disease surveillance.

Authors:  Jeffrey P Ferraro; Ye Ye; Per H Gesteland; Peter J Haug; Fuchiang Rich Tsui; Gregory F Cooper; Rudy Van Bree; Thomas Ginter; Andrew J Nowalk; Michael Wagner
Journal:  Appl Clin Inform       Date:  2017-05-31       Impact factor: 2.342

3.  Automated influenza case detection for public health surveillance and clinical diagnosis using dynamic influenza prevalence method.

Authors:  Fuchiang Tsui; Ye Ye; Victor Ruiz; Gregory F Cooper; Michael M Wagner
Journal:  J Public Health (Oxf)       Date:  2018-12-01       Impact factor: 2.341

4.  Clinical Informatics Researcher's Desiderata for the Data Content of the Next Generation Electronic Health Record.

Authors:  Timothy I Kennell; James H Willig; James J Cimino
Journal:  Appl Clin Inform       Date:  2017-12-21       Impact factor: 2.342

5.  A method for detecting and characterizing outbreaks of infectious disease from clinical reports.

Authors:  Gregory F Cooper; Ricardo Villamarin; Fu-Chiang Rich Tsui; Nicholas Millett; Jeremy U Espino; Michael M Wagner
Journal:  J Biomed Inform       Date:  2014-08-30       Impact factor: 6.317

6.  Content Coding of Psychotherapy Transcripts Using Labeled Topic Models.

Authors:  Garren Gaut; Mark Steyvers; Zac E Imel; David C Atkins; Padhraic Smyth
Journal:  IEEE J Biomed Health Inform       Date:  2015-11-25       Impact factor: 5.772

7.  Detection and Prevention of Virus Infection.

Authors:  Ying Wang; Bairong Shen
Journal:  Adv Exp Med Biol       Date:  2022       Impact factor: 2.622

8.  Disaster and Pandemic Management Using Machine Learning: A Survey.

Authors:  Vinay Chamola; Vikas Hassija; Sakshi Gupta; Adit Goyal; Mohsen Guizani; Biplab Sikdar
Journal:  IEEE Internet Things J       Date:  2020-12-15       Impact factor: 10.238

9.  Comparison of machine learning classifiers for influenza detection from emergency department free-text reports.

Authors:  Arturo López Pineda; Ye Ye; Shyam Visweswaran; Gregory F Cooper; Michael M Wagner; Fuchiang Rich Tsui
Journal:  J Biomed Inform       Date:  2015-09-16       Impact factor: 6.317

10.  An end-to-end hybrid algorithm for automated medication discrepancy detection.

Authors:  Qi Li; Stephen Andrew Spooner; Megan Kaiser; Nataline Lingren; Jessica Robbins; Todd Lingren; Huaxiu Tang; Imre Solti; Yizhao Ni
Journal:  BMC Med Inform Decis Mak       Date:  2015-05-06       Impact factor: 2.796

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.