Responsive image
博碩士論文 etd-0824104-162427 詳細資訊
Title page for etd-0824104-162427
論文名稱
Title
資料探勘在用藥安全上的應用: 預測泛可黴素在腎衰竭病患上的用量適當性
Applications of Data Mining on Drug Safety: Predicting Proper Dosage of Vancomycin for Patients with Renal Insufficiency and Impairment
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
40
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2004-07-28
繳交日期
Date of Submission
2004-08-24
關鍵字
Keywords
倒傳遞類神經網路、用藥安全、決策樹、分類分析、資料探勘
Data Mining, AdaBoost, Drug Safety, Bagging, Backpropagation Network, Classification Analysis, Decision Tree Induction
統計
Statistics
本論文已被瀏覽 5751 次,被下載 8032
The thesis/dissertation has been browsed 5751 times, has been downloaded 8032 times.
中文摘要
中文摘要
用藥疏失常造成醫療資源浪費問題,進而增加不少的社會成本。泛可黴素因藥物作用範圍狹窄,若無法充分掌握藥物的作用結果,常會引起藥物在人體的毒性反應或抗藥性的副作用。在臨床上,醫療機構雖以藥物血中濃度監測程序(TDM)協助醫藥人員監控藥物在病患身上的作用結果,藉以調整藥物的用量與使用方式。然而,對於初次使用泛可黴素的病患而言,TDM程序卻無法有效地協助醫藥人員事先評估泛可黴素對於病患的影響,因此造成TDM程序在確保全面用藥安全上的限制。
資料探勘技術已經廣泛地被應用在各項醫療研究上,也印證資料探勘從資料中所萃取潛在知識可用於醫療決策輔助的可行性。本研究嘗試運用資料探勘技術中的C4.5決策樹分析法及倒傳式類神經網路,從醫療單位對泛可黴素進行TDM監控的歷史案例中,建構出可用以預測泛可黴素在病患身上的作用結果之分類模式,用以協助醫藥人員掌握泛可黴素的療效,進而提升泛可黴素的用藥安全及用藥品質、降低可能的醫療資源浪費。
實驗結果顯示,利用Bagging及AdaBoost兩項分類效能提昇技術可提昇以C4.5或倒傳遞類神經網路所建構的單一分類器,其中利用C4.5+AdaBoost所建構之委員會機器預測模型,其整體正確辨識率也達到79.65%,比專家原有預測正確率的41.38%更準確的預測出用量的適當性;該委員會機器對於藥物用量適當的Y類別及藥物用量不適當的N類別也都有78.75%及80.28%的類別正確預測率。因此,本研究所用以建構用藥適當性的預測模式的方法,應能協助醫藥人員建構適當的用藥預測模型,而產生有效的用藥決策建議。
Abstract
Abstract
Drug misuses result in medical resource wastes and significant society costs. Due to the narrow therapeutic range of vancomycin, appropriate vancomycin dosage is difficult to determine. When inappropriate dosage is used, such side effects as poisoning reaction or drug resistance may occur. Clinically, medical professionals adjust drug protocols of vancomycin based on the Therapeutic Drug Monitoring (TDM) results. TDM is usually defined as the clinical use of drug blood concentration measurements as an aid in dosage finding and adjustment. However, TDM cannot be applied to first-time treatments and, in case, dosage decisions need to reply on medical professionals’ clinical experiences and judgments.
Data mining has been applied in various medical and healthcare applications. In this study, we will employ a decision-tree induction (specifically, C4.5) and a backpropagation neural network technique for predicting the appropriateness of vancomycin usage for patients with renal insufficiency and impairment. In addition, we will evaluate whether the use of the boosting and bagging algorithms will improve predictive accuracy.
Our empirical evaluation results suggest that use of the boosting and bagging algorithms could improve predictive accuracy. Specifically, use of C4.5 in conjunction with the AdaBoost algorithm achieves an overall accuracy of 79.65%, which significantly improves that of the existing practice, recording an accuracy rate at 41.38%. With respect to the appropriateness category (“Y”) and the inappropriateness category (“N”), C4.5 in conjunction with the AdaBoost algorithm can achieve a recall rate at 78.75% and 80.25%, respectively. Hence, the incorporation of data mining techniques to decision support would enhance the drug safety, which in turn, would improve patient safety and reduce subsequent medical resource wastes.
目次 Table of Contents
目 錄

第一章 緒論 1
第一節 研究背景 1
第二節 研究動機與目的 2
第三節 論文結構 4
第二章 文獻探討 5
第一節 抗微生物制劑-泛可黴素 ………………………………………5
第二節 藥物血中濃度監測 ..........................................................................7
第三節 分類分析技術.......................................................................................10
一、C4.5決策樹...................................................................................10
二、倒傳遞類神經網路.............................................................…......12
第四節 Bagging與AdaBoost分類效能提昇技術 ……….………………14
第三章 分類預測模式的建構 ……………………...........................................18
第一節 病患的藥物血中濃度的分類 ………………..…………………18
第二節 分類預測模型的建構過程 .………….........................................20
第四章 實證評估 ....................................................................................................21
第一節 實證資料集合描述 ...........................................................................21
第二節 模式效能衡量指標與實驗程序 ........................................................22
第三節 實驗平台與程序 ..………………….…………….........................23
第四節 實證評估結果分析 ……………………………………………….25
一、單一分類器的實證結果 ..................................................................25
二、以AdaBoost增強分類效能的實證結果 ………………..……....26
三、以Bagging增強分類效能的實證結果 …….................................27
第五節 各種分類器的效能比較分析 ……………………………………..27
第五章 結論 .............................................................................................................30
第一節 綜合結論及貢獻 .................................................................................30
第二節 未來研究方向 ………………………………..............................…30
參考文獻 …………………………………………………………………………32
附錄 …………………………………………………………………………..…..35
參考文獻 References
參考文獻
英文文獻:
[B96] Breiman, L., “Bagging Predictors,” Machine Learning, Vol.24, No.2, 1996, pp.123-140.
[C97] Corrigan, B. W., Mayo, P. R. and Jamali, F., “Application of a neural network for gentamicin concentration prediction in a generalhospital population,” The Drug Monitoring, Vol.19, No.1, 1997, pp.25-28.
[F97] Freund, Y. and Schapire, R.E., “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, Vol.55, 1997, 119-139.
[F01] Fasel, I., “AdaBoost,” www.cs.ucsd.edu/classes/fa01/cse291/AdaBoost.pdf, Oct 23, 2001
[G02] Ganzert, S., and Guttmann, J., “Analysis of respiratory pressure-volume curves in intensive care medicine using inductive machine learning,” Artificial Intelligence in Medicine, Vol.26, No.1-2, 2002, pp.69-86.
[K99] Kukar, M., Kononenko, I., and Groselj, C., “Analysing and Improving the Diagnosis of Ischaemic Heart disease with Machining Learning,” Artificial Intelligence in Medicine, Vol.16, No.1, 1999, pp.25-50.
[K00] Kristin, M. T., Chen, H., and Chow, H. H., “Estimating Drug/Plasma Concentration Levels by Applying Neural Networks to Pharmacokinetic Data Sets,” Decision Support Systems, Vol.30, No.2, 2000, pp.139-151.
[L01] Lin, F. R., Chou, S. P. and Chen, Y., “Mining Time DependencyPatterns in Clinical pathways,” International Journal of MedicalInformatics, Vol.62, No.1, 2001, pp.11-25.
[M84] Matzke, G.. R., Mcgory,R.W., and Halstenson,C.E., “Pharmacokinetics of vancomycin in patients with various degree of renal function,” Antimicrob Agents Chemother, Vol.25, No.4, 1984, pp.4337.
[M91] Moellering, R. C., Krogstadf, D. J, and Greenblatt, D. J.,“Vancomycin therapy in patients with impaired renal function: a nomogram for dosage,” Annals of Internal Medicine, Vol.94, 1981, pp.343-346.

[Q93] Quinlan, J. R., C4.5: Programs for Machine Learning, Morgan Kaufmann, San Mateo, CA, 1993.
[Q86] Quinlan, J. R., “Induction of Decision Tree,” Machine Learning, Vol.1,1986, pp.81-106.
[R99] Ronco, A. L., “Use of Artificial Neural Networks in Modeling Association of discriminant Factors: Towards An Intelligent Selective Breast Cancer Screening,” Artificial Intelligence in Medicine, Vol.16, No.3, 1999, pp.299-309.
[R82] Rotschafer, J.C., Crossley, K, and Zaske, D. E., “Pharmacokinetics of vancomycin: observation in 28 patients and dosage recommendations,” Antimicrob Agents Chemother, Vol.22, 1982, pp.391-394.
[R86] Rumelhart, D. E., Hinton, G. E., and Williams, R. J., “Learning Internal Representations by Back-propagating Errors,” Parallel Distributed Processing: Explorations in the Microstructure of Cognition, MIT Press, Vol.1, 1986, pp.318-362.
[S99] Simon, H., Neural Networks:A Comprehensive Foundation, 1999, pp.351-355.
[W00] Witten, I. H. and Frank, E., Data Mining: Practical machine learning tools with Java implementations, Morgan Kaufmann, San Francisco, 2000.


中文文獻:
[陳昭姿92] 陳昭姿,抗微生物劑的過去與未來,藥學雜誌,第三十一期,1992年,pp.23-24。
[齊玉美03] 齊玉美,「不對稱性分類分析之研究」, 國立中山大學資訊管理研究所論文, 2003年。
[袁繼銓03] 袁繼銓,「以類神經網路預測燒傷病患住院日之研究」, 國立中山大學資訊管理研究所論文,2003年。
[熊正輝00] 熊正輝,「以類神經網路為工具預估癌症末期病人之存活」, 財團法人安寧照顧基金會研究成果,2000年。
[李惠君01] 李惠君,「使用連續性靜脈-靜脈血液過濾療法的重症病人Vancomycin劑量的調整」, 國立台灣大學醫學院藥學研究所碩士論文,1998年。
[葉怡成01] 葉怡成,「應用類神經網路」,儒林圖書公司,2001。
[葉怡成02] 葉怡成,「類神經網路模式應用與實作」,儒林書局,2002。
[衛生署統計資料] 衛生署中央健保局網站。http://www.nhi.gov.tw。
電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:校內立即公開,校外一年後公開 off campus withheld
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code