Signalling paediatric side effects using an ensemble of simple study designs

Reps, Jenna M. and Garibaldi, Jonathan M. and Aickelin, Uwe and Soria, Daniele and Gibson, Jack E. and Hubbard, Richard B. (2014) Signalling paediatric side effects using an ensemble of simple study designs. Drug Safety, 37 (3). pp. 163-170. ISSN 0114-5916

Full text not available from this repository.


Background: Children are frequently prescribed medication `o-label', meaning there has not been sucient testing of the medication to determine its safety or eectiveness. The main reason this safety knowledge is lacking is due to

ethical restrictions that prevent children from being included in the majority of clinical trials.

Methods: Multiple measures of association are calculated for each drug and medical event pair and these are used as features that are fed into a classifier to determine the likelihood of the drug and medical event pair corresponding to an adverse drug reaction. The classier is trained using known adverse drug reactions or known non-adverse drug reaction relationships.

Results: The novel ensemble framework obtained a false positive rate of 0:149, a sensitivity of 0:547 and a specificity of 0:851 when implemented on a reference set

of drug and medical event pairs. The novel framework consistently outperformed each individual simple study design.

Conclusion: This research shows that it is possible to exploit the mechanism of causality and presents a framework for signalling adverse drug reactions eectively.

Item Type: Article
Additional Information: The final publication is available at Springer via
Keywords: Biomedical Informatics, Data Mining
Schools/Departments: University of Nottingham, UK > Faculty of Medicine and Health Sciences > School of Medicine > Division of Epidemiology and Public Health
University of Nottingham, UK > Faculty of Science > School of Computer Science
Identification Number:
Depositing User: Aickelin, Professor Uwe
Date Deposited: 29 Sep 2014 21:28
Last Modified: 04 May 2020 16:42

Actions (Archive Staff Only)

Edit View Edit View