텍스트마이닝을 이용한 약물유해반응 보고자료 분석 = Analysis of Adverse Drug Reaction Reports using Text Mining

다국어 초록 (Multilingual Abstract)

Background: As personalized healthcare industry has attracted much attention, big data analysis of healthcare data is essential.
Lots of healthcare data such as product labeling, biomedical literature and social media data are unstructured, extractingmeaningful information from the unstructured text data are becoming important. In particular, text mining for adverse drug reactions(ADRs) reports is able to provide signal information to predict and detect adverse drug reactions. There has been no study on textanalysis of expert opinion on Korea Adverse Event Reporting System (KAERS) databases in Korea. Methods: Expert opinion text ofKAERS database provided by Korea Institute of Drug Safety & Risk Management (KIDS-KD) are analyzed. To understand the wholetext, word frequency analysis are performed, and to look for important keywords from the text TF-IDF weight analysis areperformed. Also, related keywords with the important keywords are presented by calculating correlation coefficient. Results: Amongtotal 90,522 reports, 120 insulin ADR report and 858 tramadol ADR report were analyzed. The ADRs such as dizziness, headache,vomiting, dyspepsia, and shock were ranked in order in the insulin data, while the ADR symptoms such as vomiting, 어지러움,dizziness, dyspepsia and constipation were ranked in order in the tramadol data as the most frequently used keywords. Conclusion:Using text mining of the expert opinion in KIDS-KD, frequently mentioned ADRs and medications are easily recovered. Text mining inADRs research is able to play an important role in detecting signal information and prediction of ADRs.

참고문헌 (Reference)

1 김현희, "토픽 네트워크 분석을 활용한 데이터 마이닝 연구 동향 분석" 한국컴퓨터정보학회 21 (21): 141-148, 2016

2 김현희, "키워드 네트워크의 클릭 분석을 이용한 특허 데이터 분석" 한국데이터정보과학회 27 (27): 1273-1284, 2016

3 "tm Package text Mining in R"

4 Warrer P, "Using text-mining techniques in electronic patient records to identify ADRs from medicine use" 73 : 674-684, 2011

5 Evans SJ, "Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports" 10 : 483-486, 2001

6 Wu L, "Twitter Opinion Mining for Adverse Drug Reactions" 2015

7 Botsis T, "Text mining for the Vaccine Adverse Event Reporting System : medical text classification using informative feature selection" 18 : 631-638, 2011

8 Harpaz R, "Text Mining for Adverse Drug Events: the Promise, Challenges, and State of the Art" 37 : 777-790, 2014

9 DeMonaco HJ., "Patient- and physician-oriented web sites and drug surveillance:Bisphosphonates and severe bone, joint, and muscle pain" 169 : 1164-1166, 2009

10 Harpaz R, "Mining multi-item drug adverse effect associations in spontaneous reporting systems" 11 (11): S7-, 2010

11 Ibrahim H, "Mining association patterns of druginteractions using post marketing FDA's spontaneous reporting data" 60 : 294-308, 2016

12 Manning CD, "Introduction to Information" Cambridge University Press 109-, 2008

13 Fang R, "Computational Health Informatics in the Big Data Age: A Survey" 49 : 12-, 2016

14 Duh MS, "Can social media data lead to earlier detection of drug-related adverse events?" 25 : 1425-1433, 2016

15 Raghupathi W, "Big Data Analytics in Healthcare : Promise and Potential" 2 : 3-, 2014

16 Korkontzelos I, "Analysis of the effect of sentiment analysis on extracting adverse drug reactions from tweets and forum posts" 62 : 148-158, 2016

17 Wysowski DK, "Alendronate and risedronate: Reports of severe bone, joint, and muscle pain" 165 : 346-347, 2005

18 van Puijenbroek EP, "A comparison of measures of disproportionality for signal detection in spontaneous reporting systems for adverse drug reactions" 11 : 3-10, 2002

19 Bate A, "A Bayesian neural network method for adverse drug reaction signal generation" 54 : 315-321, 1998