Application of Hyper-geometric Hypothesis-based Quantication and Markov Blanket Feature Selection Methods to Generate Signals for Adverse Drug Reaction Detection

Pharmacovigilance is the science relating to all concerns about drug safety, especially ofmanaging the risk associated with medications. It serves as a complementary approach toclinical trial. Spontaneous Reporting Systems (SRS) had been constructed world-widely tofacilitate tracking the risk of post-marketing drugs. Data mining algorithms had been usedfor years in detecting possible adverse eects of drugs by analyzing the large amount of datain SRS.This study consists of two parts. One is to propose a statistically sound bivariate analysismethod. The objective is to provide a method with a sound theoretical base and an ability ofconguring itself for dierent demanded performances. The bivariate analysis method pro-posed in the study is termed Hyper-geometric Hypothesis-based method. This new method isinspired by statistical acceptance sampling techniques used in quality control. It is proposedas an alternative to conventional disproportionality analysis methods such as reporting oddsratio (ROR) and proportional reporting ratio (PRR). The second is to investigate the eec-tiveness of a feature selection approach to reduce false alarms through the identication ofconfounding drugs. Confounding drug is one of the major sources for false signals generatedby established methods. The feature selection method is based on the concept of a Markovblanket that removes features that do not have unique contribution to distinguishing thetarget concept. It is proposed as an alternative to the emerging Bayesian logistic regressionmethod for detecting adverse drug reaction.Experiments have been conducted using the Adverse Event Reporting System (AERS) main-tained by the US Food and Drug Administration. The results showed that the performanceof the Hyper-geometric Hypothesis based quantication method was comparable to that ofROR and PRR by adopting the threshold, P-value = 0.0409, which had been trained throughthe experiment data. The feature selection approach was able to partially detect confound-ing drugs in the meantime it left a number of dangerous drugs not alarmed. In contrast,Bayesian logistic regression method fails to live up to returning any results to make alarmson drugs.

Name thesis:degree_name

MS

Level thesis:degree_level

masters

Discipline thesis:degree_discipline

Engineering and Applied Science: Mechanical Engineering

Grantor dc:publisher

University of Cincinnati

Year dc:date

2012

Author dc:creator

• Zhang, Yi

Contributors dc:contributor

• Huang, Hongdao

• Mechanical Engineering
• Pharmacovigilance
• Data Mining
• Feature Selection

Statement dc:rights

• unrestricted
• This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.

Language dc:language

English

Repository record dc:identifier

http://rave.ohiolink.edu/etdc/view?acc_num=ucin1353343669

OAI identifier oai:identifier

oai:etd.ohiolink.edu:ucin1353343669