본문 바로가기
KERD
논문KCI 등재

우수 의약품 제조 기준 위반 패턴 인식을 위한 연관규칙과 텍스트 마이닝 기반 t-SNE분석

Violation Pattern Analysis for Good Manufacturing Practice for Medicine using t-SNE Based on Association Rule and Text Mining

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

주제분류학제간연구

초록

Purpose: The purpose of this study is to effectively detect violations that occur simultaneously against Good Manufacturing Practice, which were concealed by drug manufacturers. Methods: In this study, we present an analysis framework for analyzing regulatory violation patterns using Association Rule Mining (ARM), Text Mining, and t-distributed Stochastic Neighbor Embedding (t-SNE) to increase the effectiveness of on-site inspection. Results: A number of simultaneous violation patterns was discovered by applying Association Rule Mining to FDA’s inspection data collected from October 2008 to February 2022. Among them there were ‘concurrent violation patterns’ derived from similar regulatory ranges of two or more regulations. These patterns do not help to predict violations that simultaneously appear but belong to different regulations. Those unnecessary patterns were excluded by applying t-SNE based on text-mining. Conclusion: Our proposed approach enables the recognition of simultaneous violation patterns during the on-site inspection. It is expected to decrease the detection time by increasing the likelihood of finding intentionally concealed violations.

Abstract

Purpose: The purpose of this study is to effectively detect violations that occur simultaneously against Good Manufacturing Practice, which were concealed by drug manufacturers. Methods: In this study, we present an analysis framework for analyzing regulatory violation patterns using Association Rule Mining (ARM), Text Mining, and t-distributed Stochastic Neighbor Embedding (t-SNE) to increase the effectiveness of on-site inspection. Results: A number of simultaneous violation patterns was discovered by applying Association Rule Mining to FDA’s inspection data collected from October 2008 to February 2022. Among them there were ‘concurrent violation patterns’ derived from similar regulatory ranges of two or more regulations. These patterns do not help to predict violations that simultaneously appear but belong to different regulations. Those unnecessary patterns were excluded by applying t-SNE based on text-mining. Conclusion: Our proposed approach enables the recognition of simultaneous violation patterns during the on-site inspection. It is expected to decrease the detection time by increasing the likelihood of finding intentionally concealed violations.

참고문헌 (27)

  1. Abdellah, A., "Pharmaceutical good manufacturing practice regulatory affairs in Sudan : continuous debate between regulatory authority and manufacturers", Pharmaceutical Regulatory Affairs, 5(1), pp.166~ (2016)
  2. Agrawal, R., "Mining association rules between sets of items in large databases", Proceedings of the 1993 ACM SIGMOD International Conference on Management of data, pp.207~216 (1993)
  3. 반은미, "미국 및 유럽의 의약품 GMP 실사 동향 연구", 약 학 회 지, 63(1), pp.15~23 (2019), 대한약학회[DOI]
  4. 최광연, "감사품질이 감사성과에 미치는 요인에 관한 연구", 품질경영학회지, 46(1), pp.113~132 (2018), 한국품질경영학회[DOI]
  5. Han, J., "Discovery of multiple-level association rules from large databases", Proceedings of 1995International Conference on Very Large Data Bases, 95, pp.420~431 (1995)
  6. Han, X., "Mapping the mouse cell atlas by microwell-seq", Cell, 172(5), pp.1091~1107 (2018)
  7. International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use (ICH), "PHARMACEUTICAL QUALITY SYSTEM, (ICH Publication Code. Q10)", ICH, ~ (2008)
  8. 김상웅, "탐색적 자료 분석 및 연관규칙 분석을 활용한 잔류농약 부적합 농업인 유형 분석", 품질경영학회지, 49(1), pp.81~95 (2021), 한국품질경영학회[DOI]
  9. Kobak, D., "The art of using t-SNE for single-cell transcriptomics", Nature Communications, 10(1), pp.1~14 (2019)
  10. Kumar, S., "The role of regulatory GMP audit in pharmaceutical companies", International Journal of Research and Development in Pharmacy and Life Sciences, 2(4), pp.493~498 (2013)
  11. 이슬비, "국내 의료기기 제조업체의 ISO13485:2016 교육 프로그램 개발 및 교육 효과 연구", 품질경영학회지, 50(3), pp.503~515 (2022), 한국품질경영학회[DOI]
  12. 임지은, "EU GMP 실사 부적합 영향 요인 분석연구- Active Substance, Human Medicinal Product를 중심으로 -", 약 학 회 지, 65(1), pp.46~55 (2021), 대한약학회[DOI]
  13. Lin, W., "Efficient adaptive-support association rule mining for recommender systems", Data Mining and Knowledge Discovery, 6(1), pp.83~105 (2002)
  14. Linna A, "Developing a tool for the preparation of GMP audit of pharmaceutical contract manufacturer", European Journal of Pharmaceutics and Biopharmaceutics, 69(2), pp.786~792 (2008)
  15. Lodha, S., "Exploratory analysis of legal case citation data using node embedding", ICIC Express Letters, 13(10), pp.883~889 (2019)
  16. Onan, A., "An improved ant algorithm with LDA-based representation for text document clustering", Journal of Information Science, 43(2), pp.275~292 (2017)
  17. P. Bafna, "Document clustering: TF-IDF approach", 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), pp.61~66 (2016)
  18. Quality System Requirements for Pharmaceutical Inspectorates, "Pharmaceutical Inspection Convention Pharmaceutical Inspection Co-operation Scheme (PIC", S), S, pp.2009, ~[DOI]
  19. Standard operating procedure Team inspections, "Pharmaceutical Inspection Convention Pharmaceutical Inspection Co-operation Scheme (PIC", S), S, pp.2009, ~[DOI]
  20. A recommended model for risk-based inspection planning in the GMP environment, "Pharmaceutical Inspection Convention Pharmaceutical Inspection Co-operation Scheme(PIC", S), S, pp.2012, ~[DOI]
  21. 성윤석, "텍스트마이닝과 연관규칙을 이용한 외부감사 실시내용의 그룹별 핵심어 추출", 품질경영학회지, 50(1), pp.77~89 (2022), 한국품질경영학회[DOI]
  22. Tao, F., "Weighted association rule mining using weighted support and significance framework", Proceedings of the ninth ACM SIGKDD International Conference on Knowledge discovery and data mining, pp.661~666 (2003)
  23. Van der Maaten, L., "Visualizing data using t-SNE", Journal of Machine Learning Research, 9(11) (2008)
  24. Waldron, K, "Managing risk to the patient : recoding quality risk management for the pharmaceutical and biopharmaceutical industries", Doctor, pp.2017
  25. Wang, W., "WAR : weighted association rules for Item intensities", Knowledge and Information Systems, 6(2), pp.203~229 (2004)
  26. Wattenberg, M, "How to use t-SNE effectively", Distill, 1(10), pp.e2~ (2016)
  27. Xi, W., "A feature extraction and visualization method for fault detection of marine diesel engines", Measurement, 116, pp.429~437 (2018)

관련 논문AI추천

이 간행물의 다른 논문 (13건)