系統識別號 U0026-2508201519050300
論文名稱(中文) 利用電子健康資料庫發現潛在藥物不良反應
論文名稱(英文) Discovery of Potential Adverse Drug Reactions Using Electronic Health Databases
校院名稱 成功大學
系所名稱(中) 醫學資訊研究所
系所名稱(英) Institute of Medical Informatics
學年度 103
學期 2
出版年 104
研究生(中文) 李培福
研究生(英文) Pei-Fu Li
學號 q56024048
學位類別 碩士
語文別 英文
論文頁數 47頁
口試委員 指導教授-謝孫源
中文關鍵字 藥物不良反應  藥物安全  電子健康資料庫  資料探勘 
英文關鍵字 adverse drug reaction  drug safety  electronic health databases  data mining 
中文摘要 藥物不良反應已經成為患病和死亡的主要原因之一,並對健康照護造成龐大耗損。目前已有許多方法使用在藥物安全監測,如自發性通報系統資料庫和電子健康紀錄資料庫。自發性通報系統資料庫具有資訊不完全、通報不足等問題,可能導致偏差的結果,而據信電子健康紀錄資料庫能夠輔助既有的自發性通報系統資料庫。因此,本研究致力於發展一種新式的分析架構及流程,整合各種藥物不良反應訊號偵測方法,以發現電子健康紀錄資料庫中潛在的藥物副作用。根據藥物和藥物不良反應的出現頻率,我們提出一個加權技術,以降低偽陽性潛在藥物不良反應案例造成的影響。我們採用全民健康保險研究資料庫進行實驗評估,結果顯示此分析架構及流程,在套用我們所提出的加權技術之下,比起先前的方法有更佳的精確率平均值及平均精確率平均值。
英文摘要 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.
論文目次 中文摘要 I
Abstract II
Acknowledgements III
Contents IV
List of Tables VI
List of Figures VII
Chapter 1 Introduction 1
1.1 Background 1
1.2 Motivation 3
1.3 Problem Statement 4
1.4 Research Aims 5
1.5 Thesis Organization 5
Chapter 2 Related Work 6
2.1 Disproportionality Analysis 6
2.2 Temporal Pattern Discovery 7
2.3 Association Rule Mining 8
2.4 Unexpected Temporal Association Rule Mining 8
2.5 Supervised Learning Algorithms 9
Chapter 3 Proposed Framework 10
3.1 Overview of the Proposed Framework 10
3.2 Drug/ADR Code Transformation 14
3.2.1 Granularity of Drug/ADR Coding 14
3.2.2 Drug Classification Systems 15
3.2.3 ADR Classification Systems 16
3.3 Extraction of Potential Drug-ADR Cases 17
3.3.1 Therapeutic Indications 18
3.3.2 Temporal Restrictions 18
3.3.3 Frequencies of Occurrences of Drugs and ADRs 20
3.4 ADR Signal Detection 22
3.4.1 Odds Ratio 22
3.4.2 Proportional Reporting Ratio 23
3.4.3 Reporting Ratio 23
3.4.4 Leverage 24
Chapter 4 Experimental Evaluation 25
4.1 Dataset Description 25
4.1.1 LHID 2000 25
4.1.2 Side Effect Database 27
4.2 Performance Measures 30
4.3 Experimental Results 31
4.3.1 Comparisons in Terms of Average Hit Rate 31
4.3.2 Comparisons in Terms of Mean Average Precision 36
4.4 Summary of Experimental Results 40
Chapter 5 Conclusions and Future Work 41
5.1 Conclusions 41
5.2 Future Work 42
References 43
參考文獻 [1] Alvarez-Requejo, A., Carvajal, A., Begaud, B., Moride, Y., Vega, T., & Arias, L. M. Under-reporting of adverse drug reactions Estimate based on a spontaneous reporting scheme and a sentinel system. European journal of clinical pharmacology, 54(6), pp. 483-488, 1998.
[2] Brown, E. G., Wood, L., & Wood, S. The medical dictionary for regulatory activities (MedDRA). Drug Safety, 20(2), pp. 109-117, 1999.
[3] Coloma, P. M., Schuemie, M. J., Trifirò, G., Gini, R., Herings, R., Hippisley‐Cox, J., Mazzaglia, G., Giaquinto, C., Corrao, G., & Pedersen, L. Combining electronic healthcare databases in Europe to allow for large‐scale drug safety monitoring: the EU‐ADR Project. Pharmacoepidemiology and drug safety, 20(1), pp. 1-11, 2011.
[4] Edwards, I. R., & Aronson, J. K. Adverse drug reactions: definitions, diagnosis, and management. The Lancet, 356(9237), pp. 1255-1259, 2000.
[5] Goldman, S. A. Limitations and strengths of spontaneous reports data. Clinical therapeutics, 20, pp. C40-C44, 1998.
[6] Hazell, L., & Shakir, S. A. Under-reporting of adverse drug reactions. Drug Safety, 29(5), pp. 385-396, 2006.
[7] Jin, H., Chen, J., Kelman, C., He, H., McAullay, D., & O’Keefe, C. M. Mining unexpected associations for signalling potential adverse drug reactions from administrative health databases. In Advances in Knowledge Discovery and Data Mining, pp. 867-876, 2006.
[8] Jin, H. W., Chen, J., He, H., Kelman, C., McAullay, D., & O'Keefe, C. M. Signaling potential adverse drug reactions from administrative health databases. IEEE Transactions on Knowledge and Data Engineering, 22(6), pp. 839-853, 2010.
[9] Jin, H., Chen, J., He, H., Williams, G. J., Kelman, C., & O'Keefe, C. M. Mining unexpected temporal associations: applications in detecting adverse drug reactions. IEEE Transactions on Information Technology in Biomedicine, 12(4), pp. 488-500, 2008.
[10] Karch, F. E., & Lasagna, L. Adverse drug reactions: a critical review. Jama, 234(12), pp. 1236-1241, 1975.
[11] Kuhn, M., Campillos, M., Letunic, I., Jensen, L. J., & Bork, P. A side effect resource to capture phenotypic effects of drugs. Molecular systems biology, 6(1), pp. 343, 2010.
[12] Kuhn, M., Szklarczyk, D., Pletscher-Frankild, S., Blicher, T. H., von Mering, C., Jensen, L. J., & Bork, P. STITCH 4: integration of protein–chemical interactions with user data. Nucleic acids research, pp. 401-407, 2013.
[13] Kuo, M. H., Kushniruk, A. W., Borycki, E. M., & Greig, D. Application of the Apriori algorithm for adverse drug reaction detection. Studies in health technology and informatics, 148, pp. 95-101, 2008.
[14] Lin, W. Y., & Lo, C. F. Co-training and ensemble based duplicate detection in adverse drug event reporting systems. IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 7-8, 2013.
[15] Lindberg, D. A., Humphreys, B. L., & McCray, A. T. The Unified Medical Language System. Methods of information in medicine, 32(4), pp. 281-291, 1993.
[16] Le, H. V., Poole, C., Brookhart, M. A., Schoenbach, V. J., Beach, K. J., Layton, J. B., & Stürmer, T. Effects of aggregation of drug and diagnostic codes on the performance of the high-dimensional propensity score algorithm: an empirical example. BMC medical research methodology, 13(1), pp. 142, 2013.
[17] Maclure, M. The case-crossover design: a method for studying transient effects on the risk of acute events. American journal of epidemiology, 133(2), pp. 144-153, 1991.
[18] Norén, G. N., Hopstadius, J., Bate, A., Star, K., & Edwards, I. R. Temporal pattern discovery in longitudinal electronic patient records. Data Mining and Knowledge Discovery, 20(3), pp. 361-387, 2010.
[19] Platt, R., Wilson, M., Chan, K. A., Benner, J. S., Marchibroda, J., & McClellan, M. The new Sentinel Network—improving the evidence of medical-product safety. New England Journal of Medicine, 361(7), pp. 645-647, 2009.
[20] Reps, J. M., Aickelin, U., & Garibaldi, J. M. Tuning a multiple classifier system for side effect discovery using genetic algorithms. IEEE Congress on In Evolutionary Computation, pp. 910-917, 2014.
[21] Reps, J. M., Garibaldi, J. M., Aickelin, U., Gibson, J. E., & Hubbard, R. B. A supervised adverse drug reaction signalling framework imitating Bradford Hill’s causality considerations. Journal of biomedical informatics, 56, pp. 356-368, 2015.
[22] Reps, J. M., Garibaldi, J. M., Aickelin, U., Soria, D., Gibson, J. E., & Hubbard, R. B. Comparison of algorithms that detect drug side effects using electronic healthcare databases. Soft Computing, 17(12), pp. 2381-2397, 2013.
[23] Robb, M. A., Racoosin, J. A., Sherman, R. E., Gross, T. P., Ball, R., Reichman, M. E., ... & Woodcock, J. The US Food and Drug Administration's Sentinel Initiative: expanding the horizons of medical product safety. Pharmacoepidemiology and drug safety, 21(S1), pp. 9-11, 2012.
[24] Stang, P. E., Ryan, P. B., Racoosin, J. A., Overhage, J. M., Hartzema, A. G., Reich, C., & Welebob, E. Advancing the science for active surveillance: rationale and design for the Observational Medical Outcomes Partnership. Annals of internal medicine, 153(9), pp. 600-606, 2010.
[25] Trifiro, G., Fourrier-Reglat, A., Sturkenboom, M. C., Diaz Acedo, C., Van Der Lei, J., & EU-ADR Group. The EU-ADR project: preliminary results and perspective. Stud Health Technol Inform, 148, pp. 43-49, 2009.
[26] van Roon, E. N., Flikweert, S., le Comte, M., Langendijk, P. N., Kwee-Zuiderwijk, W. J., Smits, P., & Brouwers, J. R. Clinical relevance of drug-drug interactions. Drug safety, 28(12), pp. 1131-1139, 2005.
[27] World Health Organization. International drug monitoring: the role of national centres, report of a WHO meeting, 1972.
[28] World Health Organization. Anatomical therapeutic chemical (ATC) classification with defined daily doses (DDDs). WHO, Collaborating centre for drug statistics methodology, 2001.
[29] World Health Organization. Introduction to drug utilization research. World Health Organization, pp. 33-37, 2003.
[30] World Health Organization. The importance of pharmacovigilance, 2002.
[31] World Health Organization, & Practice Management Information Corporation. ICD-9-CM: International Classification of Diseases, 9th Revision: Clinical Modification (Vol. 1). PMIC, Practice Management Information Corporation, 1998.
[32] Zorych, I., Madigan, D., Ryan, P., & Bate, A. Disproportionality methods for pharmacovigilance in longitudinal observational databases. Statistical methods in medical research, 22(1), pp. 39-56, 2013.
[33] Adverse Event Reporting System. Available at (http://www.fda.gov/cder/aers/default.htm)
[34] Longitudinal Health Insurance Database 2000. Available at (http://nhird.nhri.org.tw/en/Data_Subsets.html)
[35] National Health Insurance Research Database. Available at (http://nhird.nhri.org.tw/)
  • 同意授權校內瀏覽/列印電子全文服務,於2020-08-31起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2020-08-31起公開。

  • 如您有疑問,請聯絡圖書館