臺灣博碩士論文加值系統

如何避免藥品調劑疏失是醫療照護中一個很重要的議題，因為它造成了無數傷亡的發生並耗費了可觀的金錢成本。在本篇論文中，我們提出了一個混合式資料探勘方法並且實做了一套系統來解決這個問題。我們的方法分成兩個部分，模型建置(HDMmodel)與藥品分群(HDMclustering)。在模型建置(HDMmodel)的部分，我們使用了J48決策樹分類法以及統計上的羅吉斯迴歸，針對調劑疏失的歷史資料加以分析，來得到決策樹模型及羅吉斯迴歸式，以供後面使用。而在藥品分群(HDMclustering)中，我們利用前面所得到的羅吉斯迴歸式以及PoCluster的技術，將彼此之間容易發生錯誤的藥品加以群聚，得到分群的結果。根據分群的結果，容易發生錯誤的藥品將會被我們的系統發現並加以警示；除此之外，我們的系統也將根據決策樹模型提供一些可能發生錯誤的原因，供藥局管理者作為思考預防調劑疏失對策時的參考。最後，我們使用了南部某醫學中心提供的實際資料來做實驗，對我們的方法加以評估。結果顯示：我們的方法可以有效地找出藥局裡容易發生調劑疏失的藥品，協助管理者有效地減少調劑疏失的發生。

One important issue in medical care is the prevention of drug dispensing errors since they caused numerous injuries and deaths with expensive cost. In this thesis, we propose a hybrid data mining approach with an implemented system to solve this problem. Our approach consists of two main modules, HDMmodel and HDMclustering. In HDMmodel, J48 and logistic regression are used to derive the decision tree and regression function from the given dispensing error cases and drug database. In HDMclustering, similar drugs, which are easily confused with each other, are then gathered together into clusters by the clustering technique named PoCluster and the extracted logistic regression function. Risky drug pairs that may cause dispensing errors are then alerted in our implemented system with interpretable prevention rules. Finally, by the experimental evaluation on real datasets in a medical center, our approach is shown to be capable of diagnosing the potential dispensing errors effectively.

中文摘要 I
ABSTRACT II
ACKNOWLEDGEMENT III
CONTENTS IV
LIST OF TABLES VI
LIST OF FIGURES VII
CHAPTER 1 INTRODUCTION 1
1.1 MOTIVATION 1
1.2 PROBLEM DEFINITION 2
1.3 CONTRIBUTIONS 3
1.4 THESIS STRUCTURE 3
CHAPTER 2 RELATED WORK 4
2.1 DEFINITIONS OF DISPENSING ERRORS 4
2.2 REASONS FOR DISPENSING ERRORS 4
2.3 SIMILARITY MEASUREMENTS 5
2.4 CLASSIFICATION MODELS 6
2.4.1 Logistic Regression Model 6
2.4.2 J48 Model 7
2.4.3 Support Vector Machine Model 7
2.5 A CLUSTERING APPROACH (POCLUSTER) 8
CHAPTER 3 HYBRID DATA MINING (HDM) METHOD 15
3.1 INPUT DATA DESCRIPTIONS 15
3.1.1 Error Pair Cases 15
3.1.2 Drug Database 16
3.2 SYSTEM ARCHITECTURE 17
3.3 HDMMODEL 18
3.3.1 A Brief Introduction 18
3.3.2 Control Group Generation 19
3.3.3 Transaction Generation 19
3.3.4 Classification Model Building 23
3.4 HDMCLUSTERING 25
3.4.1 A Brief Introduction 25
3.4.2 Generation of thirteen drug-drug matrices 26
3.4.3 Combination of thirteen matrices to a single similarity matrix 27
3.4.4 Transformation of the continuous similarity matrix into a discrete dissimilarity matrix 28
3.4.5 PoCluster generation 29
CHAPTER 4 EXPERIMENTAL EVALUATION 31
4.1 EXPERIMENTAL DATASET 31
4.2 EXPERIMENTAL DESIGN 32
4.3 RESULTS AND DISCUSSIONS 33
4.3.1 Missing Value Processing 33
4.3.2 Comparison of Three Models on Accuracy 34
4.3.3 Impact of Environmental and Drug-Property Attributes on Accuracy 36
4.3.4 Implemented System 39
4.4 SUMMARY 46
CHAPTER 5 CONCLUSIONS AND FUTURE WORK 47
REFERENCES 48
VITA 51

[1]Ashcroft, D. M., Quinlan, P., and Blenkinsopp, A., “Prospective study of the incidence, nature and causes of dispensing errors in community pharmacies,” Pharmacoepidemiology and drug safety, Vol. 14, No. 5, pp. 327-332, 2005.
[2]Ben-Dor, A., Shamir, R., and Yakhini, Z., “Clustering gene expression patterns,” The Annual International Conference on Computational Molecular Biology, pp. 281-97, 1999.
[3]Cavell, G. F., and Oborne, C. A., “Anonymously reported medication errors: the tip of the iceberg,” The Internal Journal of Pharmacy Practice, R52, 2001.
[4]Chang, C. C., and Lin, C. J., “LIBSVM: a library for support vector machines,” 2001. Software available at http://www.csie.ntu.edu.tw/cjlinl/libsvm
[5]Chua, S. S., Wong, I. C. et al. “A feasibility study for recording of dispensing errors and near misses in four UK primary care pharmacies,” Drug safety, Vol. 26, No. 11, pp. 803-813, 2003.
[6]Ester, M., Kriegel, H. P., Sander, J., and Xu, X., “A density-based algorithm for discovering clusters in large spatial databases with noise,” The International Conference on knowledge Discovery and Data Mining, pp. 226-231, 1996.
[7]Gadd, T. N., “PHONIX: The Algorithm,” Program–Electronic Library and Information Systems, Vol. 24, No. 4, pp. 222-237, 1990.
[8]Hall, P. A. V., and Dowling, G. R., “Approximate String Matching,” Computing Surveys, Vol. 12, No. 4, pp. 381-402, 1980.
[9]Kaufman, L., and Rousseeuw, P. J., “Find groups in data: an introduction to cluster analysis,” John Wiley & Sons, 1990.
[10]Kenagy, J. W., and Stein, G. C., “Naming, labeling, and packaging of pharmaceuticals,” American Journal of Health-System Pharmacy, Vol. 58, No. 21, pp. 2033-2041, 2001.
[11]Kistner, U. A., and Keith, M. R., Sergeant, K. A., and Hokanson, J. A., “Accuracy of dispensing in a high-volume, hospital-based outpatient pharmacy,” American Journal of Hospital Pharmacy, Vol. 51, No. 22, pp. 2793-2797, 1994.
[12]Kohn, C. D., “To error is human: building a safer health system,” National Academy Press, 1999.
[13]Kondrak, G., “A new algorithm for the alignment of phonetic sequences,” NAACL-2000: First Meeting of the North American Chapter of the Association for Computational Linguistics, pp. 288-295, 2000.
[14]Lambert, B. L., Lin, S. J., Chang, K. Y., and Gandhi, S. K., “Similarity as a risk factor in drug-name confusion errors: the look-alike (orthographic) and sound-alike (phonetic) model,” Med Care, Vol. 37, No. 12, pp. 1214-1225, 1999.
[15]Lazarou, J., Pomeranz, B. H., and Corey, P. N., “Incidence of adverse drug reactions in hospitalized patients,” Journal of the American Medical Association, pp. 1200-1205, 1998.
[16]Liu, J., Zhang, Q., Wang, W., McMillan, L., and Prins, J., “Clustering Pair-wise Dissimilarity Data into Partially Ordered Sets,” The International Conference on Knowledge Discovery and Data Mining, pp. 637-642, 2006.
[17]Long, G., and Johnson, C., “A pilot study for reducing medication errors,” QRB Quality review bulletin, Vol. 7, No. 4, pp. 6-9, 1981.
[18]Manzalawy, Y. E. and Honavar, V., “WLSVM : Integrating LibSVM into Weka Environment,” 2005. Software available at http://www.cs.iastate.edu/~yasser/wlsvm
[19]McEnery, A., and Oakes, M. P., “Sentence and Word Alignment in the CRATER Project: Methods and Assessment in J. Thomas & M. Short (eds) Using Corpora for Language Research,” Longman, pp. 211-231, 1996.
[20]McQueen, J. B., “Some Methods of Classification and Analysis of Mutivariate Observations,” The 5th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281-297, 1967.
[21]Melamed, D. I., “Bitext Maps and Alignment via Pattern Recognition,” Computational Linguistics, Vol. 25, No. 1, pp. 107-130, 1999.
[22]Peterson, G. M., Wu, M. S., and Bergin, J. K., “Pharmacists attitudes towards dispensing errors: their causes and prevention,” Journal of clinical pharmacy and therapeutics, Vol. 24, No. 1, pp. 57-71, 1999.
[23]Quinlan, J. R., “C4.5: programs for machine learning,” Morgan Kaufmann Publishers, 1993.
[24]Quinlan, J. R., “Induction of Decision Trees,” Kluwer Academic Publishers, Vol. 1, Issue 1, pp. 81-106, 2003.
[25]Rudman, W. J. et al, “The use of data mining tools in identifying medication error near misses and adverse drug events,” Health Information Management, Vol. 23, pp. 94-101, 2002.
[26]Thomas, E. J., Studdert, D. M., Newhouse, J. P., et al, “Costs of medical injuries in Utah and Colorado,” Inquiry, 1999.
[27]Tseng, Vincent S. and Kao, C. P., “Efficiently mining gene expression data via a novel parameterless clustering method,” The IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 2, No. 4, pp. 355-365, 2005.
[28]Tuohy, N., and Paparella, S., “Look-alike and sound-alike drugs: errors just waiting to happen,” Journal of emergency nursing, Vol. 31, No. 6, pp. 569-571, 2005.
[29]Ukkonen, E., “Finding approximate patterns in strings,” Journal of Algorithms, Vol. 6, pp. 132-137, 1985.
[30]Vapnik, V., “The Nature of Statical Learning Theory,” Springer Verlag, 1995.
[31]Wagner, R. A., and Fischer, M. J., “The string-to-string correction problem,” Journal of the ACM, Vol. 21, No. 1, pp. 168-173, 1974.
[32]Witten, I. H., and Frank, E., “Data Mining: Practical machine learning tools and techniques,” 2nd Edition, Morgan Kaufmann, 2005.
[33]張慧真, 醫院藥局藥品調劑疏失之探討--以南部某醫學中心為例, 國立成功大學高階管理碩士在職專班碩士論文, 2006年7月