A Comparison of Methods of Data Mining Algorithms Directed Predictive Pharmacosafety Networks for Adverse Drug Event Detection

Abstract

Adverse drug events (ADEs) detection is the critical concern in the field of pharmacovigilance, and it is also necessary to optimize the ADEs prediction to reduce the drug related morbidity and mortality. Here we propose a novel methods of data mining algorithms directed predictive pharmacosafety networks (PPNs) to compare their predictive performance and investigate the differences between data mining algorithms. The combinations of 152 cancer drugs and 633 ADEs in the 2010 FDA Adverse Event Reporting System(FAERS) data is the training data, and 2011-2015 FAERS data is the validation data. We find that performance of empirical Bayes geometric mean (EBGM) is closer to proportional reporting ratio (PRR), and greater than reporting odds ratio (ROR) in ADE detection. Further, only information component (IC) directed the PPNs have better predictive performance comparing to other data mining algorithms, the predictive performance of which reaches to AUROC =0.908 comparing to the existing AUROC =0.823, and the performance of IC is greater than EBGM in ADE detection.