臺灣博碩士論文加值系統

因為晚婚和壓力所造成的不孕症人口愈來愈多，台灣於2008年採用人工生殖的人數甚至已突破8000人次，活產嬰兒數也高達3000名，若以當年度新生兒總數約20萬人來估算，人工生殖治療的出生寶寳比率已佔了總出生率1.5%。雖然台灣人工生殖技術懷孕率高達36.5%，活產率則由民國87年的22.2%，逐年提升到97年的27.1%，但在不能保證懷孕的情況之下，動輒數十萬的治療費讓許多不孕婦女怯步，對許多不孕症夫婦而言，是否要進行這些須耗費時間與金錢的治療是個難題，且治療後能成功懷孕的比率又是多少？這些問題一直困擾著不孕症夫婦們。

在治療時，病患年齡與卵子及精子的品質等許多不同因素，都會對人工生殖的成功率造成影響。此外，進行人工生殖的整個流程步驟，其內容複雜且每一細部的環節皆會影響到懷孕率最終成果。因此，本研究將應用資料探勘(Data Mining)中的特徵選取(Feature Selection)技術，如主成份分析法(Principal Component Analysis, PCA)、線性區別分析(Linear Discriminant Analysis, LDA)及決策樹(Decision Tree, DT)結合台北某教學醫院生殖醫學中心所提供的資料，透過分析運算來瞭解人工生殖診療過程中，不同的醫囑診斷、身體素質等是否會成為對懷孕率造成影響的主要因素，希望能從大量的醫療診斷資料中篩選出有意義的屬性，並透過分類(Classification)方法中的類神經網路(Artificial Neuron Network, ANN)進行懷孕率預測，以提供醫師醫療診斷決策資訊，更精確地掌握及安排患者的療程。

Because of the reason by late marriage and pressure cause the infertility population getting more and more. In 2008, Taiwan has using the artificial reproduction technology to treatment infertility that has exceeded 8,000 people, and the number of live births as high as 3000, if we using the year neonatal terms of the total number of about 20 million people to estimate, using artificial reproductive technique of babies born accounted for a total birth rate of baby birth rate of 1.5%. Although Taiwan in the assisted reproductive technology has high pregnancy rates as 36.5%, and from 1998 to 2008, the live birth rate by year raise from 22.2% to 27.1%. However, due to the high cost of the assisted reproductive technology treatments, uncertainty of live birth rate and the pressure it causes to patients physically and mentally, how to predict the possible IVF outcomes becomes an important research topic.

In the treatment process, the pregnancy rate of the artificial reproductive technology will be impacted through by the female patient age, ovum quality or the male patient sperm quality and many different factors etc. In addition, the entire process of artificial reproduction technology treatment, from the patient''s basic information such as age, weight to into the operating room surgical ovum retrieval, fertilization, embryo culture and implantation, every single step will affect the final outcome.

In this research, a hybrid data mining methodology is used to predict the treatment of the assisted reproductive technology outcome. Firstly, Principal Component Analysis (PCA), Linear Discriminant Analysis(LDA) and Decision Tree (DT) will be adopted respectively to select features. And then, the classification methods, Artificial Neural Network (ANN) is used to predict the outcome of IVF. Combination of each feature selection method as well as classification method is compared to test the accuracy of prediction. The IVF dataset used in this research is obtained from one of the teaching hospital in Taiwan. The results of this research will provide a good reference for doctors in ART unit when they are asked to give an answer of success rate to infertility couples.

摘 要 I
ABSTRACT III
誌 謝 V
目錄 VI
表目錄 VIII
圖目錄 IX
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究架構 4
第二章 文獻探討 6
2.1 人工生殖技術 6
2.1.1 影響人工受孕結果主要因素 8
2.2 特徵選取 8
2.2.1 主成份分析法 10
2.2.2 線性區別分析法 11
2.2.3 決策樹 12
2.3 分類方法 13
2.3.1 類神經網路 14
2.4 應用於人工生殖技術之預測、分類等相關文獻介紹 16
第三章 研究方法 24
3.1 研究模型架構 24
3.2 特徵選取 26
3.2.1 主成份分析法 26
3.2.2 線性區別分析法 27
3.2.3 決策樹 28
3.3 分類方法 31
3.3.1 類神經網路 31
第四章 資料處理及研究模型建構 37
4.1 資料淨化及前置處理 37
4.2 研究模型評估方法 41
4.2.1 混淆矩陣 41
4.2.2 接受者操作特徵曲線 42
4.3 研究限制 43
4.4 特徵選取 43
4.4.1 主成份分析法 44
4.4.2 線性區別分析法 50
4.4.3 決策樹 52
4.5 分類方法 55
4.5.1 類神經網路 56
4.5.2 複合式分類模型 58
第五章 結論與未來研究 62
5.1 研究結果 62
5.2 建議及未來研究 69
參考文獻 71

[1]台灣榮民總醫院生殖內分泌，不孕症的治療，擷取自台灣榮民總醫院婦產科http://homepage.vghtpe.gov.tw/~obgy/profile_06.htm
[2]徐明義，不孕症不等於不能懷孕，而是不易懷孕，擷取自 聯合新聞網: http://mag.udn.com/mag/life/storypage.jsp?f_ART_ID=249355，民國99年5月23日
[3]張田勘，“試管嬰兒之父”獲諾獎：人工生殖技術的爭論繼續，擷取自 南方網: http://www.southcn.com/，民國99年10月6日
[4]Nelson，胚胎發育–胚胎形態(I) ，擷取自 e世代送子鳥生殖醫學中心: http://www.e-stork.com.tw/viewArticle.do?id=5599，民國99年1月21日
[5]馬偕紀念醫院婦產部不孕症學科編者，不孕症的認識，民國99年
[6]行政院國民健康局，民國97年台灣地區人工生殖施行報告，民國97年
[7]李強，創建決策樹算法的比較研究—ID3,C4.5,C5.0算法的比較，甘肅科學學報，第84頁至第87頁，民國95年
[8]林清山，多變項分析統計法，東華書局，民國87年
[9]邵奕誠，應用倒傳遞類神經網路與EWMA統計製程管制於冷凍鏈溫度監控之研究，碩士論文，台北：國立臺北科技大學 工業工程與管理研究所，民國97年
[10]張斐章、張麗秋，類神經網路，東華書局，民國94年
[11]陳飛龍，特徵選取為基礎之複合分類預測模式以信用資料為例，博士論文，新竹：國立清華大學 工業工程與工程管理研究所，民國99年7月
[12]陳順宇，多變量分析 (第四版)，華泰文化，民國94年
[13]葉怡成，類神經網路模式應用與實作，儒林出版社，民國92年
[14]葉麗雯，供應商產能有限及價格折扣下多產品多供應商最佳化採購決策，碩士論文，桃園：元智大學，民國94年7月
[15]廖述賢、溫志皓，資料採礦與商業智慧，雙葉書廊，民國97年
[16]蕭昌軒，應用人工智慧技術於預測試管嬰兒治療成功率之研究，碩士論文， 雲林：國立虎尾科技大學 工業工程與管理所，民國98年
[17]蕭昌軒、顧瑞祥，應用資料探勘於試管嬰兒分析之研究，2009年健康與管理學術研討會，民國98年
[18]A. Templeton, J. K. Morris and W. Parslow, (1996). Factors that Affect Outcome of In-vitro Fertilisation Treatment. Lancet, 348, pp. 1402-1406.
[19]B. E. Boser, I. M. Guyon, and V. N. Vapnik, (1992). A training algorithm for optimal margin classifiers. In I. D. Haussler (Ed.), 5th Annual ACM Workshop on COLT (pp. 144-152). Pittsburgh, PA: ACM Press.
[20]B. Baesens , T. Van Gestel, S. Viaene, M. Stepanova, J. Suykens, and J. Vanthienen, (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6), pp. 627-635.
[21]D. Hand, H. Mannila, P. Smyth, (2001). Principles of Data Mining. MIT Press, Cambridge, MA.
[22]L. Dain, R. Auslander and M. Dirnfeld, (2011). The effect of paternal age on assisted reproduction outcome. Fertil Steril, 95(1), pp. 1-8.
[23]D. Nogueira, S. Friedler, M. Schachter, A. Raziel, R. Ron-El and J. Smitz, (2004). Oocyte maturity and preimplantation development in relation to follicle diameter in gonadotropin-releasing hormone agonist or antagonist treatments. European Society of Human Reproduction (ESHRE) 2004 20th Annual Meeting. 85 , pp. 578-583. Berlin, Germany: Fertility and Sterility.
[24]M. Dash and H. Liu, (1997). Feature selection for classification. Int. J. Intell. Data Anal., Vol. No. 3, pp. 131-156.
[25]V. S. Desai , J. N. Crook,, and G. A. Overstreet (1996). A comparison of neural networks and linear scoring models in the credit union environment. European Journal of Operational Research, 95(1), pp. 24-37.
[26]R. A. Fisher, (1936). The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics, 7, 179-188.
[27]K. Fukunaga, (1990). Introduction to Statistical Pattern Recognition. San Diego: Academic Press Inc.
[28]J. H. Holland, (1992). Adaptation in Nature and Artificial Systems: An introductory analysis with applications to biology, control, and artificial intelligence. MIT Press.
[29]M. Hagan, (1996). Neural Network Design. PWS Publishing Company.
[30]D. T. Hand, (2001). A simple generalization of the area under the ROC curve to multiple class classification problems. . Machine Learning(45), pp. 171-186.
[31]G. F. Hughes, (1968). On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inform. Theory.
[32]I. Jurisica, J. Mylopoulos , J. Glasgow ,H. Shapiro and R. F. Casper. (1998). Case-based reasoning in IVF: prediction and knowledge mining. Artificial Intelligence in Medicine(12), pp. 1-24.
[33]J. R. Trimarchi, J. Goodside, L. Passmore, T. Silberstein, L. Hamel and L. Gonzalez. (2003). Comparing Data Mining and Logistic Regression for Predicting IVF Outcome. 59th Annual meeting of the American Society for Reproductive Medicine.
[34]J. R. Quinlan, (1986). Induction of Decision Tree,Machine Learning., 1, pp. 81-106.
[35]I. Jolliffe, (1986). Principal Component Analysis. Springer-Verlag.
[36]J. Davis, P. Illingworth and A. Salam. (2005). Applications of data mining techniques in assisted reproductive technology. 16th Australasian Conference on Information Systems. Sydney.
[37]J. Han, and M. Kamber, (2006). Data Mining: Concepts and Techniques (2 ed.). (J. Gray, Ed.) Morgan Kaufmann Publishers.
[38]R. Kohavi and G. H. John, (1997). Wrappers for feature subset selection. Artificial Intelligence, pp. 273-324.
[39]S. Kotsiantis, (2007). Supervised Machine Learning: A Review of Classification Techniques. Informatica Journal(31), pp. 249-268.
[40]L. Passmore, J. Goodside, L. Hamel, L. Gonzalez, T. Silberstein, and J. Trimarchi. (2003). ASSESSING DECISION TREE MODELS FOR CLINICAL IN−VITRO FERTILIZATION DATA. Dept. of Computer Science and Statistics University of Rhode Island. Technical Report TR03−296.
[41]W. Matheus, G. Frawley and C. Piatetsky-Shapiro, (1992). Knowledge Discovery in Databases: An Overview. AI Magazine, 213-228.
[42]S. J. Kaufmann, J. L. Eastaugh , S. Snowden , S.W. Smye and V. Sharma, (1997). The application of neural networks in predicting the outcome of in-vitro fertilization. Human Reproduction(vol.12 no.7), pp. 1454-1457.
[43]R. Kohavi and F. Provost. (1998). Glossary of Terms. Machine Learning(30), pp. 271-274.
[44]K. A. Spackman, (1989). Signal detection theory: Valuable tools for evaluating inductive learning. Proceedings of the Sixth International Workshop on Machine Learning, pp. 160-163.
[45]E. Van Royen, K. Mangelschots, D. De Neubourg, M. Valkenburg, M. Van de Meerssche, G. Ryckaert, W. Eestermans, J. Gerris, (1999). Characterization of a top quality embryo, a step towards single-embryo transfer. Human Reproduction, 9(14), 2345-2349.
[46]D. West, (2000). Neural network credit scoring models. Computers and Operations Research, 27(11-12), pp. 1131-1152.
[47]M. Zeidenberg, (1990). Neural Networks in Artificial Intelligence. Ellis Horwood Limited.