A data mining approach for signal detection and analysis

• Published in: Drug safety Vol. 25; no. 6; pp. 393 - 397
• Main Authors: BATE, Andrew, LINDQUIST, Marie, EDWARDS, I. Ralph, ORRE, Roland
• Format: Conference Proceeding Journal Article
• Language: English
• Published: Auckland Adis international 2002
• Subjects: Adverse Drug Reaction Reporting Systems - statistics & numerical data; Algorithms; Analysis. Health state; Bayes Theorem; Biological and medical sciences; Clinical trial. Drug monitoring; Confidence Intervals; Databases, Factual - statistics & numerical data; Epidemiology; Evaluation Studies as Topic; General aspects; General pharmacology; Humans; Medical sciences; Neural Networks (Computer); Pharmacology. Drug treatments; Public health. Hygiene; Public health. Hygiene-occupational medicine; Statistics as Topic - methods; World Health Organization; Human; Investigation method; Toxicity; Database; Bayes network; Active ingredient; Review; Pharmacovigilance; Data mining; Signal detection; Public health
• ISSN: 0114-5916
• DOI: 10.2165/00002018-200225060-00002

The WHO database contains over 2.5 million case reports, analysis of this data set is performed with the intention of signal detection. This paper presents an overview of the quantitative method used to highlight dependencies in this data set. The method Bayesian confidence propagation neural network (BCPNN) is used to highlight dependencies in the data set. The method uses Bayesian statistics implemented in a neural network architecture to analyse all reported drug adverse reaction combinations. This method is now in routine use for drug adverse reaction signal detection. Also this approach has been extended to highlight drug group effects and look for higher order dependencies in the WHO data. Quantitatively unexpectedly strong relationships in the data are highlighted relative to general reporting of suspected adverse effects; these associations are then clinically assessed.