Explore effects between Human Papillomavirus Vaccine and Adverse Event using Association Rule

• Main Authors: LEE, JU-CHI, 李如琪
• Other Authors: HU, YA-HAN
• Format: Others
• Language: zh-TW
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/848wg8

碩士 === 國立中正大學 === 資訊管理學系碩士在職專班 === 106 === Ever since the first cervical cancer vaccine was approved by U.S. FDA in 2006, more than 100 million doses of the HPV vaccines Gardasil™ and Cervarix™ have been distributed in 120 countries. Despite the reassuring results on vaccine safety provided by large trials and post-marketing studies, barriers to vaccination still exist, largely coming from parental and girls’ anxiety regarding serious adverse events (AEs) and fear of unknown side effects. With the VAERS (Vaccine Adverse Event Reporting System) online database, we can shift from the old time epidemiological analysis and prediction with statistical approaches to the analysis of the existing medical records with data mining techniques. Thus, we can find out the hidden information related to association rules, which can be a great help to doctors’ medical practice or a valuable health reference to the general public. We proposed an association rule mining framework based on association rules to investigate if there is any correlation between HPV vaccines and adverse events. In the study, data collection was conducted using life-threatening events and adverse events reactions after vaccination. The experts then reviewed the collected data to obtain levels of support and confidence for non-resolved adverse events analysis. Association analysis of different symptoms based on the levels was then performed to establish the association rules between the HPV vaccines and adverse events in different occasions with different symptoms. The association rules can thus act as warnings and references for vaccine recipients.