Discovery of Potential Adverse Drug Reactions Using Electronic Health Databases

• Main Authors: Pei-FuLi, 李培福
• Other Authors: Sun-Yuan Hsieh
• Format: Others
• Language: en_US
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/82678715922906007483

碩士 === 國立成功大學 === 醫學資訊研究所 === 103 === Adverse drug reactions (ADRs) not only have become one of the leading causes of morbidity and mortality but also have impacted significantly on health care costs. Many approaches have been deployed to monitor drug safety, such as spontaneous reporting system (SRS) databases and electronic health record (EHR) databases. SRS databases suffer from a great number of problems that may lead to biased findings, including incomplete information and underreporting, while EHR databases are believed to have the potential to complement the existing SRS databases. In this thesis, we dedicate to the development of a framework which integrates different ADR signal detection methods to discover potential drug-ADR pairs from EHR databases. Based on the frequencies of occurrences of drugs and ADRs, we propose a weighted technique to reduce the influence of false positives in the extracted potential drug-ADR cases. The evaluation on the one real EHR database shows that our framework with the proposed weighted technique outperforms the prior methods in terms of mean of precision and mean average precision.