臺灣博碩士論文加值系統

自民國七十一年起， 癌症即躍居國人十大死因第一位，到今年約二十多年。綜觀民眾癌症發生及死亡情形，皆呈現逐年上升趨勢，其中大腸癌及直腸癌除了發生率逐年上升，死亡率更是十大癌症的前三位。根據估計，在可見的計未來，癌症仍是影響國人健康重要原因之ㄧ
在生物統計的領域�堶情A「存活率」是生命統計的一個範疇，它能夠指出某特定族群人口，在被診斷出罹患某種疾病後，於某時間區間內仍然活著的百分比。例如：一百位罹患大腸癌的病人，在接受手術後的五年內，有六十位還活著，我們簡稱「五年存活率為百分之六十」。存活率對於疾病的預後，是一項重要的指標，存活率越高，當然預後就越好。
在臨床上，要針對一位癌症病人作出準確的存活率預測，有其必要性但是卻相當困難。如果我們對於治療後的預測過於樂觀，往往造成病人及家屬的預期與實際結果有太大的落差，潛藏引發醫療糾紛的危險，同時也會使負責治療後照顧的醫療人員措手不及。另一方面，如果我們對於治療後對存活率的預測過於悲觀，卻可能使病人或家屬放棄治療的選擇，因而錯失治療的良機，所以「過尤不及」。一套客觀而準確的癌症存活率預測系統，不但有助於評估治療模組（treatment modality）的效益、讓病人在可能有限的日子作最好的準備、同時也可以有助於國家衛生政策的制定與推行，所以我認為，是有其臨床實用價值的。
建立癌症診療資料庫的目的，是要收集並追蹤在各醫院診斷及治療之六種癌症照護相關資料，以分析醫院對癌症病人的醫療照護管理、追蹤及預後情形，並適時回饋資料作為醫院了解本院與其他醫院之差異，並進而作為內部品質改善或其他相關研究之參考。以大腸直腸癌的資料庫為例，這個資料庫包含的欄位有六十多個，其中除了一些如：身份證字號及醫療院所代碼等與疾病無關的醫院及個人資料外，大部分都可以作為預後預測的輸入參數
以現在的類神經網路模型，加上癌症登錄資料庫的適當欄位作為輸入變項，可以獲得更好的預測結果。在這個研究�堶情A發展出針對病人本身的存活率預測模型，而其準確度比以往的統計方法都要來得高。

Cancer death proceeded to the leading cause of death since 1982 and the trend of both mortality rate and prevalence are increasing as time. Colorectal cancer is not only has an increasing mortality rate but also be the third leading cause of cancer death recently. The percentage of people in a study or treatment group who are alive for a certain period of time after they were diagnosed with or treated for a disease, such as cancer. The survival rate is often stated as a five-year survival rate, which is the percentage of people in a study or treatment group who are alive five years after diagnosis or treatment. But it is only a number of percentage of people survived not the probability of survival of an individual. Clinically, it is very difficult to predict the survival rate of an individual with cancer because there are many influencing factors and the factors are interacting to each other. In this study, I try to establish an artificial neural network model to predict the survival rate of an individual with colorectal cancer based on a cancer registry database.

第一章 12
緒論 12
1. 研究動機 13
2. 研究目的 14
第二章 17
文獻探討 17
1. 大腸直腸癌的防治 17
2. 預後因子 18
3. 人工智能的歷史 18
4. 類神經網路 20
5. 類神經網路基本架構 24
人工神經元（Artificial neuron） 24
機器學習（machine learning） 25
6. 類神經網路應用於臨床預測 29
第三章 45
研究方法 45
1. 案例資料蒐集與參數決定 45
1.1 參數決定 50
1.2 資料前處理 71
2. 實驗步驟與流程 73
3. 訓練驗證網路與結果分析 78
第四章 79
結果 79
討論 82
第六章 84
結論 84
文獻探討 85

中文部分：
1.朱嘉雯。案例式推理與類神經網路在心電圖診斷之應用研究。真理大學管理科學研究所。民93年。碩士論文
2.葉怡成，「應用類神經網路」，儒林圖書公司，2001年。
3.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。
4.羅華強，「類神經網路MATLAB的應用－類神經網路的介紹」，清蔚科技，2001年，pp.1-10
5.張志華。預測冠狀動脈繞道手術之重大併發症 - 類神經網路模型之建構及分析。台北醫學大學醫學資訊研究所。民92年。碩士論文。
6.行政院衛生署。死亡統計。http://www.doh.gov.tw/lane/statist/83/83stat3-52.html，1994。
7.葉怡成（1999）。「類神經網路模式應用與實作」，六版。臺北：儒林出版社
8.林朝順。建立類神經網路模型以預測propofol用於麻醉誘導時所產生的睡眠效應。台北醫學大學醫學資訊研究所。民91年。碩士論文。

1-45
1.Hill M. Etiology of the adenoma-carcinoma sequence. Major problems in pathology 1978;10:153-62.
2.Hill MJ, Morson BC, Bussey HJ. Aetiology of adenoma--carcinoma sequence in large bowel. Lancet 1978;1:245-7.
3.Greenlee RT, Murray T, Bolden S, Wingo PA. Cancer statistics, 2000. CA: a cancer journal for clinicians 2000;50:7-33.
4.de Dombal FT, Leaper DJ, Staniland JR, McCann AP, Horrocks JC. Computer-aided diagnosis of acute abdominal pain. British medical journal 1972;2:9-13.
5.Hudson DL, Cohen ME, IEEE Engineering in Medicine and Biology Society. Neural networks and artificial intelligence for biomedical engineering. New York: IEEE Press; 2000.
6.Gorry GA, Kassirer JP, Essig A, Schwartz WB. Decision analysis as the basis for computer-aided management of acute renal failure. The American journal of medicine 1973;55:473-84.
7.McCulloh WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 1943;5:115-33.
8.Jain AK, Mao J, Mohiuddin KM. Artificial neural networks: a tutorial. Comput IEEE 1996 Mar:31-44.
9.Basheer IA, Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. Journal of microbiological methods 2000;43:3-31.
10.Hecht-Nielsen R. Cogent confabulation. Neural Netw 2005;18:111-5.
11.Schalkoff RJ. Artificial Neural Networks. New York: McGraw-Hill; 1997.
12.SEER Program (National Cancer Institute (U.S.)), Fritz AG, Ries LAG. The SEER Program code manual. 3rd ed. [Bethesda, Md.?]: Cancer Statistics Branch, Surveillance Program, Division of Cancer Control and Population Sciences, National Cancer Institute, National Institutes of Health, Public Health Service, U.S. Dept. of Health and Human Services; 1998.
13.Beahrs OH. Colorectal cancer staging as a prognostic feature. Cancer 1982;50:2615-7.
14.Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982;143:29-36.
15.Beahrs OH. The American Joint Committee on Cancer. Bulletin of the American College of Surgeons 1984;69:16-7.
16.Beahrs OH. Staging of cancer of the breast as a guide to therapy. Cancer 1984;53:592-4.
17.McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. 1943. Bulletin of mathematical biology 1990;52:99-115; discussion 73-97.
18.Astion ML, Wilding P. Application of neural networks to the interpretation of laboratory data in cancer diagnosis. Clinical chemistry 1992;38:34-8.
19.Gabor AJ, Seyal M. Automated interictal EEG spike detection using artificial neural networks. Electroencephalography and clinical neurophysiology 1992;83:271-80.
20.Goldberg V, Manduca A, Ewert DL, Gisvold JJ, Greenleaf JF. Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence. Medical physics 1992;19:1475-81.
21.O''Leary TJ, Mikel UV, Becker RL. Computer-assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis. Mod Pathol 1992;5:402-5.
22.Ravdin PM, Clark GM. A practical application of neural network analysis for predicting outcome of individual breast cancer patients. Breast Cancer Research & Treatment 1992;22:285-93.
23.Westenskow DR, Orr JA, Simon FH, Bender HJ, Frankenberger H. Intelligent alarms reduce anesthesiologist''s response time to critical faults. Anesthesiology 1992;77:1074-9.
24.Burke HB, Henson DE. The American Joint Committee on Cancer. Criteria for prognostic factors and for an enhanced prognostic system. Cancer 1993;72:3131-5.
25.Fielding LP, Henson DE. Multiple prognostic factors and outcome analysis in patients with cancer. Communication from the American Joint Committee on Cancer. Cancer 1993;71:2426-9.
26.Tourassi GD, Floyd CE, Sostman HD, Coleman RE. Acute pulmonary embolism: artificial neural network approach for diagnosis. Radiology 1993;189:555-8.
27.Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993;187:81-7.
28.Burke HB. Artificial neural networks for cancer research: outcome prediction. Seminars in surgical oncology 1994;10:73-9.
29.Clark GM, Hilsenbeck SG, Ravdin PM, De Laurentiis M, Osborne CK. Prognostic factors: rationale and methods of analysis and integration. Breast cancer research and treatment 1994;32:105-12.
30.Baxt WG. Application of artificial neural networks to clinical medicine. Lancet 1995;346:1135-8.
31.Cross SS, Harrison RF, Kennedy RL. Introduction to neural networks. Lancet 1995;346:1075-9.
32.Dybowski R, Gant V. Artificial neural networks in pathology and medical laboratories. Lancet 1995;346:1203-7.
33.Kaminsky FC, Burke RJ, Haberle KR, Mullins DL. Statistical analysis of data in cervical cytology from the viewpoint of total quality management. Acta cytologica 1995;39:222-31.
34.Baxt WG, Skora J. Prospective validation of artificial neural network trained to identify acute myocardial infarction. Lancet 1996;347:12-5.
35.Cady B, Stone MD, Schuler JG, Thakur R, Wanner MA, Lavin PT. The new era in breast cancer. Invasion, size, and nodal involvement dramatically decreasing as a result of mammographic screening. Arch Surg 1996;131:301-8.
36.Dybowski R, Weller P, Chang R, Gant V. Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm. Lancet 1996;347:1146-50.
37.Barth A, Craig PH, Silverstein MJ. Predictors of axillary lymph node metastases in patients with T1 breast carcinoma. Cancer 1997;79:1918-22.
38.Bottaci L, Drew PJ, Hartley JE, et al. Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions. Lancet 1997;350:469-72.
39.Burke HB, Goodman PH, Rosen DB, et al. Artificial neural networks improve the accuracy of cancer survival prediction. Cancer 1997;79:857-62.
40.Jefferson MF, Pendleton N, Lucas SB, Horan MA. Comparison of a genetic algorithm neural network with logistic regression for predicting outcome after surgery for patients with nonsmall cell lung carcinoma. Cancer 1997;79:1338-42.
41.April Fritz A, CTR, Lynn Ries M. The SEER Program Code Manual. In: National Cancer Institute; 1998.
42.Hecht-Nielsen R. Applications of counterpropagation networks. Neural Networks 1998;1:131-9.
43.Lundin M, Lundin J, Burke HB, Toikkanen S, Pylkkanen L, Joensuu H. Artificial neural networks applied to survival prediction in breast cancer. Oncology 1999;57:281-6.
44.Ramoni M, Sebastiani P, Dybowski R. Robust outcome prediction for intensive-care patients. Methods of information in medicine 2001;40:39-45.
45.Selaru FM, Xu Y, Yin J, et al. Artificial neural networks distinguish among subtypes of neoplastic colorectal lesions. Gastroenterology 2002;122:606-13.