TY - JOUR
T1 - Using Probabilistic Record Linkage of Structured and Unstructured Data to Identify Duplicate Cases in Spontaneous Adverse Event Reporting Systems
AU - Kreimeyer, Kory
AU - Menschik, David
AU - Winiecki, Scott
AU - Paul, Wendy
AU - Barash, Faith
AU - Woo, Emily Jane
AU - Alimchandani, Meghna
AU - Arya, Deepa
AU - Zinderman, Craig
AU - Forshee, Richard
AU - Botsis, Taxiarchis
N1 - Funding Information:
The authors thank Ezekiel Maier for several conversations and suggestions that have enhanced the technical aspects of this work. This work was supported in part by the appointment of Kory Kreimeyer to the Research Participation Program administered by the Oak Ridge Institute for Science and Education through an interagency agreement between the US Department of Energy and the US Food and Drug Administration. Kory Kreimeyer, David Menschik, Scott Winiecki, Wendy Paul, Faith Barash, Emily Jane Woo, Meghna Alimchandani, Deepa Arya, Craig Zinderman, Richard Forshee, and Taxiarchis Botsis have no conflicts of interest directly relevant to the content of this article.
Publisher Copyright:
© 2017, Springer International Publishing Switzerland 2017(outside the USA).
PY - 2017/7/1
Y1 - 2017/7/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85015203844&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85015203844&partnerID=8YFLogxK
U2 - 10.1007/s40264-017-0523-4
DO - 10.1007/s40264-017-0523-4
M3 - Article
C2 - 28293864
AN - SCOPUS:85015203844
SN - 0114-5916
VL - 40
SP - 571
EP - 582
JO - Drug Safety
JF - Drug Safety
IS - 7
ER -