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

Norén, G. Niklas

doi:10.1007/s40264-017-0548-8

Cited by 7 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach employs supervised machine learning models to train algorithms using labelled data that differentiate duplicate and non-duplicate pairs. These models then use the knowledge gained from labelled data to predict whether new record pairs are duplicates or not based on learned patterns 5 64–66. Natural language processing techniques have been developed to augment computerised duplicate detection using the narrative in adverse event reports 66.…”

Section: Resultsmentioning

confidence: 99%

“…Manual confirmation is always necessary following the detection of potential duplicates. Well-documented reports, with elaborate case narratives, make the confirmation process easier 5 64 66. However, reports with limited information require that reporters are contacted for additional information, which necessitates the timely review of submitted reports 6.…”

Section: Resultsmentioning

confidence: 99%

“…Pharmacovigilance is crucial for drug safety as it promotes the prevention, detection and evaluation of suspected adverse reactions to minimise their impact on patient health 1 2. One of the challenges of pharmacovigilance is the duplication of cases in pharmacovigilance databases, which distorts drug safety and efficacy assessment, and disrupts decision-making 3–5. Duplication is defined as multiple, unconnected records that refer to the same potential adverse event 3 4 6.…”

Section: Introductionmentioning

confidence: 99%

“…Advances in technology, for example, machine learning and natural language processing, hold promise in augmenting the efficiency and precision of pharmacovigilance efforts, particularly in the deduplication of large and complex pharmacovigilance databases 5 31 32. Deduplication methods are, however, impeded by the high extent of incomplete case information which makes it difficult to conduct reliable duplicate analysis 4.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Navigating duplication in pharmacovigilance databases: a scoping review

Kiguba,

Isabirye,

Mayengo

et al. 2024

BMJ Open

View full text Add to dashboard Cite

ObjectivesPharmacovigilance databases play a critical role in monitoring drug safety. The duplication of reports in pharmacovigilance databases, however, undermines their data integrity. This scoping review sought to provide a comprehensive understanding of duplication in pharmacovigilance databases worldwide.DesignA scoping review.Data sourcesReviewers comprehensively searched the literature in PubMed, Web of Science, Wiley Online Library, EBSCOhost, Google Scholar and other relevant websites.Eligibility criteriaPeer-reviewed publications and grey literature, without language restriction, describing duplication and/or methods relevant to duplication in pharmacovigilance databases from inception to 1 September 2023.Data extraction and synthesisWe used the Joanna Briggs Institute guidelines for scoping reviews and conformed with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews. Two reviewers independently screened titles, abstracts and full texts. One reviewer extracted the data and performed descriptive analysis, which the second reviewer assessed. Disagreements were resolved by discussion and consensus or in consultation with a third reviewer.ResultsWe screened 22 745 unique titles and 156 were eligible for full-text review. Of the 156 titles, 58 (47 peer-reviewed; 11 grey literature) fulfilled the inclusion criteria for the scoping review. Included titles addressed the extent (5 papers), prevention strategies (15 papers), causes (32 papers), detection methods (25 papers), management strategies (24 papers) and implications (14 papers) of duplication in pharmacovigilance databases. The papers overlapped, discussing more than one field. Advances in artificial intelligence, particularly natural language processing, hold promise in enhancing the efficiency and precision of deduplication of large and complex pharmacovigilance databases.ConclusionDuplication in pharmacovigilance databases compromises risk assessment and decision-making, potentially threatening patient safety. Therefore, efficient duplicate prevention, detection and management are essential for more reliable pharmacovigilance data. To minimise duplication, consistent use of worldwide unique identifiers as the key case identifiers is recommended alongside recent advances in artificial intelligence.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Navigating duplication in pharmacovigilance databases: a scoping review

Kiguba,

Isabirye,

Mayengo

et al. 2024

BMJ Open

View full text Add to dashboard Cite

show abstract

“…One of the major drawbacks of the FAERS database is the presence of duplicate case reports. An as-is use of the database without excluding duplicate reports is likely to significantly affect the study results 14 . We overcome this drawback by employing a deduplication procedure along with systematic extraction of cases with the drug-adverse event combination to enhance the data reliability.…”

mentioning

confidence: 99%

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

Kamath

Acharya

Rao

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Tocilizumab (TCZ) is used to treat rheumatoid arthritis and other systemic inflammatory disorders. There is some evidence suggesting the occurrence of pancreatitis following TCZ use. We aimed to determine the reporting of pancreatitis following TCZ use in comparison with other drugs using the United States Food and Drug Administration Adverse Event Reporting System (FAERS) database. We extracted adverse event reports submitted to FAERS during 2013–2019. A reporting odds ratio (ROR) with the lower bound 95% confidence interval (CI) > 1 and a lower limit of a two-sided 95% interval of information component (IC025) more than zero was considered significant. Following deduplication, 3,383,910 adverse event reports were available; 144 (0.004%) reports were of pancreatic adverse events associated with TCZ use, and 15,907 (0.47%) associated with other drugs. Of the 144 cases, 74 (51.39%) received concomitant medications with pancreatotoxic potential. The likelihood of reporting of pancreatic events, compared with any other adverse event, with TCZ use was 1.32 times higher than that with other drugs. The lower bound of the 95% CI of the ROR and IC remained above the criteria of significance throughout the study period, except 2013. The findings suggest disproportionately high reporting of pancreatitis in patients receiving TCZ as compared with other drugs. This marginally high reporting is not likely to be of immediate clinical concern and needs to be interpreted cautiously.

show abstract