以類神經網路及分類迴歸樹輔助肝癌病患預測存活情形

Prediction of Survival in Patients with Liver Cancer Using Artificial Neural Networks and Classification and Regression Trees

10.6288/TJPH2011-30-05-08

陳正美(Cheng-Mei Chen)；徐建業(Chien-Yeh Hsu)；邱泓文(Hung-Wen Chiu)；白其卉(Chyi-Huey Bai)；吳柏動(Po-Husn Wu)

肝癌 ； 類神經網路 ； 分類迴歸樹 ； 預測模型 ； Liver Cancer ； Artificial Neural Networks ； Classification and Regression Trees ； Prediction Model

台灣公共衛生雜誌

30卷5期（2011 / 10 / 15）

481 - 493

繁體中文

This study created a survival prediction model for liver cancer using data mining algorithms. Methods: The data were collected from the cancer registry of a medical center in Northern Taiwan between 2004 and 2008. A total of 227 patients were newly diagnosed with liver cancer during this time. Following a literature review, expert consultation, and collection of patients' data, nine variables pertaining to liver cancer survival rates were analyzed using t-tests and chi-square tests. Six variables were significant. An artificial neural network (ANN) and a classification and regression tree (CART) algorithm were adopted as prediction models. The models were tested in three conditions: one variable (clinical stage alone), six significant variables, and all nine variables (significant and non-significant). Five-year survival was the output prediction. Results: The ANN model with nine input variables was a superior predictor of survival (p＜0.001). The area under the receiver operating characteristic (ROC) was 0.843, and 0.78, 0.76, and 0.80 for accuracy, sensitivity, and specificity respectively. Conclusions: An artificial neural network was more accurate than a CART system in predicting liver cancer survival. In the future, we suggest developing a computer system using the nine input variables in the ANN prediction model to predict liver cancer survival. The system would use an ANN algorithm to automatically calculate the prediction result and assist patients in understanding their potential treatment outcomes and survival.

This study created a survival prediction model for liver cancer using data mining algorithms. Methods: The data were collected from the cancer registry of a medical center in Northern Taiwan between 2004 and 2008. A total of 227 patients were newly diagnosed with liver cancer during this time. Following a literature review, expert consultation, and collection of patients' data, nine variables pertaining to liver cancer survival rates were analyzed using t-tests and chi-square tests. Six variables were significant. An artificial neural network (ANN) and a classification and regression tree (CART) algorithm were adopted as prediction models. The models were tested in three conditions: one variable (clinical stage alone), six significant variables, and all nine variables (significant and non-significant). Five-year survival was the output prediction. Results: The ANN model with nine input variables was a superior predictor of survival (p＜0.001). The area under the receiver operating characteristic (ROC) was 0.843, and 0.78, 0.76, and 0.80 for accuracy, sensitivity, and specificity respectively. Conclusions: An artificial neural network was more accurate than a CART system in predicting liver cancer survival. In the future, we suggest developing a computer system using the nine input variables in the ANN prediction model to predict liver cancer survival. The system would use an ANN algorithm to automatically calculate the prediction result and assist patients in understanding their potential treatment outcomes and survival.

1. 陳錫杰、蘇慧芳、李中一、賴美淑、謝碧晴(2010)。醫師的遵循行為可促進病患的存活嗎？以台灣非小細胞肺癌病患為例。台灣衛誌，29，118-30。
   連結：
2. 陳明杰、王豐裕、胡志棠、黃世哲、陳健麟：CLIP評分系統與東台灣肝癌患者之預後。http://www.skh.org.tw/gi/an_meet/一般演講(4)/肝癌-II/103-1.pdf。引用2010/10/14。Chen MJ, Wang FY, Hu JT, Huang SJ, Chen JL. Validation of CLIP scoring system for prognosis of patients with hepatoma in Eastern Taiwan. Available at: http://www.skh.org.tw/gi/an_meet/一般演講(4)/肝癌-II/103-1.pdf. Accessed October 14, 2010. [In Chinese]
3. 巫沛倉：類神經網路簡介。 http://www.im.isu.edu.tw/faculty/pwu/expert/ann.ppt。引用 2010/11/22。Wu PC. Introduction of artificial neural network.Available at: http://www.im.isu.edu.tw/faculty/pwu/expert/ann.ppt . Accessed November 22, 2010. [In Chinese]
4. Burke, H. B.,Goodman, P. H.,Rosen, D. B.(1997).Artificial neural networks improve the accuracy of cancer survival prediction.Cancer,79,857-62.
5. Chen, C. M.,Hsu, C. Y.(2011).Predict liver cancer patients' survival using classification and regression trees.Proceedings of Experimental Biology,USA:
6. Chen, C. M.,Hsu, C. Y.,Chao, C. J.(2011).Developing a computer system to help decision making on liver cancer treatments.Proceedings of Experimental Biology,USA:
7. Collette, S.,Bonnetain, F.,Paoletti, X.(2008).Prognosis of advanced hepatocellular carcinoma:comparison of three staging systems in two French clinical trials.Ann Oncol,19,1117-26.
8. Davies, P. C.(1994).Design issues in neural network development.Neurovest J,5,21-5.
9. Dayhoff, J. E.,DeLeo, J. M.(2001).Artificial neural networks opening the black box.Cancer,91(8 Suppl),1615-35.
10. Hirai, K.,Kawazoe, Y.,Yamashita, K.(1986).Transcatheter arterial embolization for spontaneous rupture of hepatocellular carcinoma.Am J Gastroenterol,4,275-9.
11. Huitzil-Melendez, F. D.,Capanu, M.,O''Reilly, E. M.(2010).Advanced hepatocellular carcinoma: which staging systems best predict prognosis?.J Clin Oncol,28,2889-95.
12. Lau, H.,Fan, S. T.,Ng, I. O.,Wong, J.(1998).Long term prognosis after hepatectomy for hepatocellular carcinoma: a survival analysis of 204 consecutive patients.Cancer,83,2302-11.
13. Lee, J. H.,Han, S. Y.,Jo, J. H.(2007).Prognostic factors for survival in patients with hepatocellular carcinoma after radiofrequency ablation.Korean J Gastroenterol,49,17-23.
14. Lin, C. C.,Wang, Y. C.,Chen, J. Y.(2008).Artificial neural network prediction of clozapine response with combined pharmacogenetic and clinical data.Comput Methods Programs Biomed,91,91-9.
15. Lin, T. M.,Chen, C. J.,Tsai, S. F.,Tsai, T. H.(1988).Hepatoma in Taiwan.J Natl Public Health Assoc(ROC),8,91-100.
16. Miller, A. S.,Blott, B. H.,Hames, T. K.(1992).Review of neural network applications in medical imaging and signal processing.Med Biol Eng Comput,30,449-64.
17. Okuda, K.,Ohtsuki, T.,Obata, H.(1985).Natural history of hepatocellular carcinoma and prognosis in relation to treatment. Study of 850 patients..Cancer,56,918-28.
18. Sato, F.,Shimada, Y.,Selaru, F. M.(2005).Prediction of survival in patients with esophageal carcinoma using artificial neural networks.Cancer,103,1596-605.
19. Snow, P. B.,Kerr, D. J.,Brandt, J. M.,Rodvold, D. M.(2001).Neural network and regression predictions of 5-year survival after colon carcinoma treatment.Cancer,91(8 Suppl),1673-8.
20. Snow, P. B.,Smith, D. S.,Catalona, W. J.(1994).Artificial neural network in the diagnosis and prognosis of prostate cancer: a pilot study.J Urol,152,1923-6.
21. Tandon, P.,Garcia-Tsao, G.(2009).Prognostic indicators in hepatocellular carcinoma: a systematic review of 72 studies.Liver Int,29,502-10.
22. Yang, H. I.,Sherman, M.,Su, J.(2010).Nomograms for risk of hepatocellular carcinoma in patients with chronic hepatitis B virus infection.J Clin Oncol,28,2437-44.
23. 王琪珍、藍忠孚、陳建仁(1994)。台灣地區肝癌、肺癌、胃癌多重危險因子之世代研究。中華衛誌，13，308-14。
24. 周嘉揚(2008)。肝切除治療肝細胞癌。中華癌醫會誌，24，311-7。
25. 林志陵、高嘉宏(2008)。肝癌的流行病學。中華癌醫會誌，24，277-81。
26. 林裕民、張鴻俊、廖朝聖、陳瑞灝、楊國卿(2009)。TACE對TNM不同期別肝癌存活率之影響—癌症登記資料分析。中華民國消化系聯合學術演講年會，台北=Taipei:
27. 徐千彝、霍德義(2010)。肝癌的預後評估及分期系統。臨床醫學，66，216-24。
28. 陳正美、徐建業(2010)。肝癌病患選擇治療方式的偏好評估與決策支援系統建置。台灣國際醫學資訊聯合研討會，台北=Taipei:
29. 游崇善、黃聖方、江國賢(2009)。應用腹部電腦斷層掃瞄影像之肝臟腫瘤自動輔助診斷系統。台灣國際醫學資訊研討會，台北=Taipei:
30. 廖述賢、溫志皓(2009)。資料採礦與商業智慧。台北=Taipei:雙葉書廊=Yeh Yeh Book Gallery。
31. 蔡蕙如、柯明中、張偉斌、劉德明(2007)。應用類神經網路與分類迴歸樹於肝癌分類模式。北市醫學雜誌，4，658-67。
32. 鄭慧雲、朱正心、林錫泉(2001)。肝癌破裂的臨床經驗與預後因子之分析。內科學誌，12，14-8。
33. 盧瑜芬(2006)。台北=Taipei，國防醫學院公共衛生研究所=School of Public Health, National Defense Medical Center。

1. 黃婷萱、李天行、呂奇傑(2016)。以資料探勘技術進行糖尿病與乳癌關聯性分析之研究。Journal Of Data Analysis，11(5)，77-96。
2. 張雅婷,林榮禾,林敬順(2022)。應用資料探勘技術建立組合型乳癌預測模式。慈惠學報，18，17-31。