Improved Adverse Drug Event Prediction Through Information Component Guided Pharmacological Network Model (IC-PNM).

Xiangmin Ji,Weixing Feng,Lang Li,Jin Li,Aditi Shendre,Lei Wang,Pengyue Zhang,Liyan Hua,Xueying Wang

doi:10.1109/tcbb.2019.2928305

Abstract

Improving adverse drug event (ADE) prediction is highly critical in pharmacovigilance research. We propose a novel information component guided pharmacological network model (IC-PNM) to predict drug-ADE signals. This new method combines the pharmacological network model and information component, a Bayes statistics method. We use 33,947 drug-ADE pairs from the FDA Adverse Event Reporting System (FAERS) 2010 data as the training data, and the new 21,065 drug-ADE pairs from FAERS 2011-2015 as the validations samples. The IC-PNM data analysis suggests that both large and small sample size drug-ADE pairs are needed in training the predictive model for its prediction performance to reach an area under the receiver operating characteristic curve [Formula: see text]. On the other hand, the IC-PNM prediction performance improved to [Formula: see text] if we removed the small sample size drug-ADE pairs from the prediction model during validation.

Highlights

IMPROVING adverse drug event (ADE) prediction has always been a primary focus of pharmacovigilance research
The Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) 2010 data was used as the training set and included 33,947 drug-ADE combinations
The FAERS 2011-2015 data was used as the validation set and included a total of 21,065 new drugADE combinations, which were not part of the 2010 FAERS data

Summary

Introduction

IMPROVING adverse drug event (ADE) prediction has always been a primary focus of pharmacovigilance research. Many ADEs cannot be detected during the preapproval stages of a clinical trial. Spontaneous reporting systems (SRS) are highly efficient approaches for collecting ADE cases during post-approval surveillance. The U.S Food and Drug Administration’s (FDA) Adverse Event Reporting System (FAERS) [2] is one of the prominent SRS databases, which contains information on adverse drug events. This database was designed to support FDA’s posting-marketing safety surveillance program for drug and biologic products. Drug-ADE signals can be detected using the FAERS database by employing computational methods. Not all drug-ADE signals detected through these methods are true

Methods

Results

Conclusion