Literature DB >> 28293864

Using Probabilistic Record Linkage of Structured and Unstructured Data to Identify Duplicate Cases in Spontaneous Adverse Event Reporting Systems.

Kory Kreimeyer1, David Menschik2, Scott Winiecki2, Wendy Paul2, Faith Barash2, Emily Jane Woo2, Meghna Alimchandani2, Deepa Arya2, Craig Zinderman2, Richard Forshee2, Taxiarchis Botsis2.   

Abstract

INTRODUCTION: Duplicate case reports in spontaneous adverse event reporting systems pose a challenge for medical reviewers to efficiently perform individual and aggregate safety analyses. Duplicate cases can bias data mining by generating spurious signals of disproportional reporting of product-adverse event pairs.
OBJECTIVE: We have developed a probabilistic record linkage algorithm for identifying duplicate cases in the US Vaccine Adverse Event Reporting System (VAERS) and the US Food and Drug Administration Adverse Event Reporting System (FAERS).
METHODS: In addition to using structured field data, the algorithm incorporates the non-structured narrative text of adverse event reports by examining clinical and temporal information extracted by the Event-based Text-mining of Health Electronic Records system, a natural language processing tool. The final component of the algorithm is a novel duplicate confidence value that is calculated by a rule-based empirical approach that looks for similarities in a number of criteria between two case reports.
RESULTS: For VAERS, the algorithm identified 77% of known duplicate pairs with a precision (or positive predictive value) of 95%. For FAERS, it identified 13% of known duplicate pairs with a precision of 100%. The textual information did not improve the algorithm's automated classification for VAERS or FAERS. The empirical duplicate confidence value increased performance on both VAERS and FAERS, mainly by reducing the occurrence of false-positives.
CONCLUSIONS: The algorithm was shown to be effective at identifying pre-linked duplicate VAERS reports. The narrative text was not shown to be a key component in the automated detection evaluation; however, it is essential for supporting the semi-automated approach that is likely to be deployed at the Food and Drug Administration, where medical reviewers will perform some manual review of the most highly ranked reports identified by the algorithm.

Mesh:

Year:  2017        PMID: 28293864     DOI: 10.1007/s40264-017-0523-4

Source DB:  PubMed          Journal:  Drug Saf        ISSN: 0114-5916            Impact factor:   5.606


  15 in total

1.  Can Natural Language Processing Improve the Efficiency of Vaccine Adverse Event Report Review?

Authors:  B Baer; M Nguyen; E J Woo; S Winiecki; J Scott; D Martin; T Botsis; R Ball
Journal:  Methods Inf Med       Date:  2015-09-23       Impact factor: 2.176

2.  Extending the Fellegi-Sunter probabilistic record linkage method for approximate field comparators.

Authors:  Scott L DuVall; Richard A Kerber; Alun Thomas
Journal:  J Biomed Inform       Date:  2009-08-13       Impact factor: 6.317

3.  Evaluation of record linkage between a large healthcare provider and the Utah Population Database.

Authors:  Scott L DuVall; Alison M Fraser; Kerry Rowe; Alun Thomas; Geraldine P Mineau
Journal:  J Am Med Inform Assoc       Date:  2011-09-16       Impact factor: 4.497

4.  Vaccine adverse event text mining system for extracting features from vaccine safety reports.

Authors:  Taxiarchis Botsis; Thomas Buttolph; Michael D Nguyen; Scott Winiecki; Emily Jane Woo; Robert Ball
Journal:  J Am Med Inform Assoc       Date:  2012-08-25       Impact factor: 4.497

5.  Performance of probabilistic method to detect duplicate individual case safety reports.

Authors:  Philip Michael Tregunno; Dorthe Bech Fink; Cristina Fernandez-Fernandez; Edurne Lázaro-Bengoa; G Niklas Norén
Journal:  Drug Saf       Date:  2014-04       Impact factor: 5.606

6.  Decision support environment for medical product safety surveillance.

Authors:  Taxiarchis Botsis; Christopher Jankosky; Deepa Arya; Kory Kreimeyer; Matthew Foster; Abhishek Pandey; Wei Wang; Guangfan Zhang; Richard Forshee; Ravi Goud; David Menschik; Mark Walderhaug; Emily Jane Woo; John Scott
Journal:  J Biomed Inform       Date:  2016-07-28       Impact factor: 6.317

7.  Linking mothers and infants within electronic health records: a comparison of deterministic and probabilistic algorithms.

Authors:  Eric Baldwin; Karin Johnson; Heidi Berthoud; Sascha Dublin
Journal:  Pharmacoepidemiol Drug Saf       Date:  2014-11-18       Impact factor: 2.890

8.  Probabilistic record linkage is a valid and transparent tool to combine databases without a patient identification number.

Authors:  Nora Méray; Johannes B Reitsma; Anita C J Ravelli; Gouke J Bonsel
Journal:  J Clin Epidemiol       Date:  2007-05-17       Impact factor: 6.437

Review 9.  Under-reporting of adverse drug reactions : a systematic review.

Authors:  Lorna Hazell; Saad A W Shakir
Journal:  Drug Saf       Date:  2006       Impact factor: 5.228

10.  Accuracy of Probabilistic Linkage Using the Enhanced Matching System for Public Health and Epidemiological Studies.

Authors:  Robert W Aldridge; Kunju Shaji; Andrew C Hayward; Ibrahim Abubakar
Journal:  PLoS One       Date:  2015-08-24       Impact factor: 3.240

View more
  8 in total

1.  "Artificial Intelligence" for Pharmacovigilance: Ready for Prime Time?

Authors:  Robert Ball; Gerald Dal Pan
Journal:  Drug Saf       Date:  2022-05-17       Impact factor: 5.228

2.  Analysis of a pharmacist-led adverse drug event management model for pharmacovigilance in an academic medical center hospital in China.

Authors:  Wei He; Difei Yao; Yangmin Hu; Haibin Dai
Journal:  Ther Clin Risk Manag       Date:  2018-10-30       Impact factor: 2.423

3.  Assessment of pancreatitis associated with tocilizumab use using the United States Food and Drug Administration Adverse Event Reporting System database.

Authors:  Ashwin Kamath; Sahana D Acharya; Rashmi R Rao; Sheetal D Ullal
Journal:  Sci Rep       Date:  2021-09-22       Impact factor: 4.379

4.  Anaphylaxis rates associated with COVID-19 vaccines are comparable to those of other vaccines.

Authors:  Helena C Maltezou; Cleo Anastassopoulou; Sophia Hatziantoniou; Gregory A Poland; Athanasios Tsakris
Journal:  Vaccine       Date:  2021-11-27       Impact factor: 3.641

5.  Temporal relationship of myocarditis and pericarditis following COVID-19 vaccination: A pragmatic approach.

Authors:  Cleo Anastassopoulou; Sophia Hatziantoniou; Charalambos Vlachopoulos; Nicholas Spanakis; Costas Tsioufis; Athanasios Tsakris; George Lazaros
Journal:  Int J Cardiol       Date:  2022-04-15       Impact factor: 4.039

6.  Usefulness of Vaccine Adverse Event Reporting System for Machine-Learning Based Vaccine Research: A Case Study for COVID-19 Vaccines.

Authors:  James Flora; Wasiq Khan; Jennifer Jin; Daniel Jin; Abir Hussain; Khalil Dajani; Bilal Khan
Journal:  Int J Mol Sci       Date:  2022-07-26       Impact factor: 6.208

7.  Detecting early safety signals of infliximab using machine learning algorithms in the Korea adverse event reporting system.

Authors:  Jeong-Eun Lee; Ju Hwan Kim; Ji-Hwan Bae; Inmyung Song; Ju-Young Shin
Journal:  Sci Rep       Date:  2022-09-01       Impact factor: 4.996

8.  The Power of the Case Narrative - Can it be Brought to Bear on Duplicate Detection?

Authors:  G Niklas Norén
Journal:  Drug Saf       Date:  2017-07       Impact factor: 5.606

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.