A Data Mining Approach for Signal Detection and Analysis
- 286 Downloads
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.
KeywordsAnatomical Therapeutic Chemical Neural Network Architecture Report Drug Adverse Reaction Information Component Suspected Adverse Drug Reaction
- 3.Bate A, Orre R, Lindquist M, et al. Explanation of data mining methods [online]. Available from URL: http://www.bmj.com/cgi/content/full/322/7296/1207/DC1 [Accessed 2001 Oct 15]
- 4.Bate A, Orre R, Lindquist M, et al. Pattern recognition using a recurrent neural network and its application to the WHO database [abstract]. Pharmacoepidemiol Drug Saf 2001; 10(S1): S163Google Scholar
- 9.Bate A, Lindquist M, Orre R, et al. Automated classification of signals as group effects or drug specific on the WHO database [abstract]. 8th Annual Meeting European Society of Pharmacovigilance; 2000 Sep; Verona; Elsevier, 2000Google Scholar
- 10.Guidelines for ATC classification and DDD assignment. 3rd ed. Oslo: WHO Collaborating Centre for Drug Statistics Methodology, 2000Google Scholar