• 1.四川大學(xué)華西醫(yī)院 循證醫(yī)學(xué)與流行病學(xué)教研室;;
  •  2.心血管外科,成都 610041;

疾病預(yù)后常受到多種因素影響,且各因素之間又存在著復(fù)雜的非線性關(guān)系。人工神經(jīng)網(wǎng)絡(luò)(artificial neural network,ANN)是一種模擬生物神經(jīng)元工作方式的人工智能模型,具有較強(qiáng)智能化處理多因素非線性能力。目前神經(jīng)網(wǎng)絡(luò)模型越來越多地應(yīng)用于臨床醫(yī)學(xué)領(lǐng)域,特別是疾病預(yù)后的預(yù)測(cè)。我們就人工神經(jīng)網(wǎng)絡(luò)的基本原理及其在疾病預(yù)后研究方面的應(yīng)用進(jìn)行綜述。

引用本文: 陳杰,周勤,陳進(jìn),石應(yīng)康,董力. 人工神經(jīng)網(wǎng)絡(luò)在疾病預(yù)后研究中的應(yīng)用進(jìn)展. 中國胸心血管外科臨床雜志, 2013, 20(1): 95-99. doi: 復(fù)制

1.  蔣宗禮, 主編. 人工神經(jīng)網(wǎng)絡(luò)導(dǎo)論. 北京:高等教育出版社, 2001. 7-10.
2.  叢爽, 面向, 主編. MATLAB 工具箱的神經(jīng)網(wǎng)絡(luò)理論與應(yīng)用. 第3版. 合肥:中國科技技術(shù)大學(xué)出版社, 2009. 1-7.
3.  方積乾, 陸盈, 主編. 現(xiàn)代醫(yī)學(xué)統(tǒng)計(jì)學(xué). 北京:人民衛(wèi)生出版社, 2002. 708-709.
4.  韓立群, 主編. 人工神經(jīng)網(wǎng)絡(luò)教程. 北京:北京郵電大學(xué)出版社, 2006. 4-5.
5.  Advantages TJ. Disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol, 1996, 49 (11):1225-1231.
6.  陳進(jìn), 石應(yīng)康, 董力. 疾病預(yù)后因素研究設(shè)計(jì)在心臟瓣膜置換術(shù)后抗凝治療臨床研究中的應(yīng)用. 中國胸心血管外科臨床雜志, 2011, 18 (4):286-288.
7.  王家良, 王波, 主編. 臨床流行病學(xué):臨床科研設(shè)計(jì), 測(cè)量與評(píng)價(jià). 第3版. 上海:上海科學(xué)技術(shù)出版社, 2009. 434-435.
8.  孫振球, 徐勇勇, 主編. 醫(yī)學(xué)衛(wèi)生統(tǒng)計(jì). 第3版. 北京:人民衛(wèi)生出版社, 2010. 318.
9.  Mcculloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biol, 1990, 52 (1â):99-115.
10.  Minsky M, Papert S, Chief editor. Perceptron (expanded edition). Cambridge, MA:MIT Press, 1988. 1969.
11.  Rumelhart D, Hintont GE, Williams RJ. Learning representations by back-propagating errors. Nature, 1986, 323 (9):533-536.
12.  施彥, 韓力群, 廉小親, 主編. 神經(jīng)網(wǎng)絡(luò)設(shè)計(jì)方法與實(shí)例分析. 北京:北京郵電大學(xué)出版社, 2009. 307-361.
13.  Peng SY, Peng SK. Predicting adverse outcomes of cardiac surgery with the application of artificial neural networks. Anaesthesia, 2008, 63 (7):705-713.
14.  Akl A, Ismail AM, Ghoneim M. Prediction of graft survival of living-donor kidney transplantation:nomograms or artificial neural networks ? Transplantation, 2008, 86 (10):1401-1406.
15.  Nilsson J, Ohlsson M, Thulin L, et al. Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks. J Thorac Cardiovasc Surg, 2006, 132 (1):12-19.
16.  Nashef S, Roques F, Hammill BG, et al. Validation of European system for cardiac operative risk evaluation (EuroSCORE)in North American cardiac surgery. Eur J Cardio-thoracic Surg, 2002, 22 (1):101-105.
17.  Gogbashian A, Sedrakyan A, Treasure T. Euroscore:a systematic review of international performance. Euro J Cardio-thoracic Surg, 2004, 25 (5):695-700.
18.  Yoshimura M, Takahashi Y, Uchida K, et al. Prediction of survival in prostate cancer patients by bone scan index using computer-assisted diagnosis system. Eur J Nucl Med Mol Imaging, 2011, 38 (Suppl 2):S414.
19.  Scholl S, Biã¨che I, Pallud C, et al. Relevance of multiple biological parameters in breast cancer prognosis. Breast, 1996, 5 (1):21-30.
20.  Ei MM, Akl A, Mosbah A, et al. Prediction of survival after radical cystectomy for invasive bladder carcinoma:risk group stratification, nomograms or artificial neural networks?J Urol, 2009, 182 (2):466-472.
21.  袁金秋, 劉雅莉, 楊克虎. 基于人工神經(jīng)網(wǎng)絡(luò)的數(shù)據(jù)挖掘技術(shù)在臨床中應(yīng)用進(jìn)展. 圖書與情報(bào), 2010 (3):95-98.
22.  范炤, 呂吉元, 陳澤華, 等. 基于BP人工神經(jīng)網(wǎng)絡(luò)的急性前壁心肌梗塞冠脈內(nèi)支架術(shù)一年預(yù)后模型研究. 中國衛(wèi)生統(tǒng)計(jì), 2010, 27 (1):71-73, 82.
23.  張鳴. 初步構(gòu)建基于我國肝移植受體的生存評(píng)估模型及其與MELD的比較研究. 成都:四川大學(xué), 2006. 1-87.
24.  蔡煜東, 官家文, 甘駿人, 等. 人工神經(jīng)網(wǎng)絡(luò)方法在乳腺癌死亡率研究中的應(yīng)用. 中國生物醫(yī)學(xué)工程學(xué)報(bào), 1994, 13 (4):364-366.
25.  黃德生, 周寶森, 劉延齡, 等. BP人工神經(jīng)網(wǎng)絡(luò)用于肺鱗癌預(yù)后預(yù)測(cè). 中國衛(wèi)生統(tǒng)計(jì), 2000, 17 (6):337-340.
26.  姜成華, 王正國, 朱佩芳, 等. 基于神經(jīng)網(wǎng)絡(luò)的創(chuàng)傷預(yù)后仿真模型. 中華創(chuàng)傷雜志, 1997, 13 (3):42-44.
27.  De Laurentiis M, De Placido S, Bianco AR, et al. A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients. Clin Cancer Res, 1999, 5 (12):4133-4139.
28.  Piaggi P, Lippi C, Fierabracci P, et al. Artificial neural networks in the outcome prediction of adjustable gastric banding in obese women. PLoS One, 2010, 5 (10):e13624.
29.  Tu JV, Guerriere MJ. Use of a neural network as a predictive instrument for length of stay in the intensive care unit following cardiac surgery. Comput Biomed Res, 1993, 26 (3):220-229.
30.  Lin E, Hwang Y, Wang SC, et al. An artificial neural network approach to the drug efficacy of interferon treatments. Pharmacogenomics, 2006, 7 (7):1017-1024.
31.  Chang HH, Chen PS, Giacomini KM. A neural network model for predicting treatment response of antidepressant in patients with major depressive disorder. Biol Psychiatry, 2012, 71 (8):286S.
32.  Solomon I, Maharshak N, Chechik G, et al. Applying an artificial neural network to warfarin maintenance dose prediction. Isr Med Assoc J, 2004, 6 (12):732-735.
33.  Dipti I, Peter BS, Almassy RJ, et al. Artificial neural networks:Current status in cardiovascular medicine. J Am Coll Cardiol, 1996, 28 (2):515-521.
  1. 1.  蔣宗禮, 主編. 人工神經(jīng)網(wǎng)絡(luò)導(dǎo)論. 北京:高等教育出版社, 2001. 7-10.
  2. 2.  叢爽, 面向, 主編. MATLAB 工具箱的神經(jīng)網(wǎng)絡(luò)理論與應(yīng)用. 第3版. 合肥:中國科技技術(shù)大學(xué)出版社, 2009. 1-7.
  3. 3.  方積乾, 陸盈, 主編. 現(xiàn)代醫(yī)學(xué)統(tǒng)計(jì)學(xué). 北京:人民衛(wèi)生出版社, 2002. 708-709.
  4. 4.  韓立群, 主編. 人工神經(jīng)網(wǎng)絡(luò)教程. 北京:北京郵電大學(xué)出版社, 2006. 4-5.
  5. 5.  Advantages TJ. Disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol, 1996, 49 (11):1225-1231.
  6. 6.  陳進(jìn), 石應(yīng)康, 董力. 疾病預(yù)后因素研究設(shè)計(jì)在心臟瓣膜置換術(shù)后抗凝治療臨床研究中的應(yīng)用. 中國胸心血管外科臨床雜志, 2011, 18 (4):286-288.
  7. 7.  王家良, 王波, 主編. 臨床流行病學(xué):臨床科研設(shè)計(jì), 測(cè)量與評(píng)價(jià). 第3版. 上海:上??茖W(xué)技術(shù)出版社, 2009. 434-435.
  8. 8.  孫振球, 徐勇勇, 主編. 醫(yī)學(xué)衛(wèi)生統(tǒng)計(jì). 第3版. 北京:人民衛(wèi)生出版社, 2010. 318.
  9. 9.  Mcculloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biol, 1990, 52 (1â):99-115.
  10. 10.  Minsky M, Papert S, Chief editor. Perceptron (expanded edition). Cambridge, MA:MIT Press, 1988. 1969.
  11. 11.  Rumelhart D, Hintont GE, Williams RJ. Learning representations by back-propagating errors. Nature, 1986, 323 (9):533-536.
  12. 12.  施彥, 韓力群, 廉小親, 主編. 神經(jīng)網(wǎng)絡(luò)設(shè)計(jì)方法與實(shí)例分析. 北京:北京郵電大學(xué)出版社, 2009. 307-361.
  13. 13.  Peng SY, Peng SK. Predicting adverse outcomes of cardiac surgery with the application of artificial neural networks. Anaesthesia, 2008, 63 (7):705-713.
  14. 14.  Akl A, Ismail AM, Ghoneim M. Prediction of graft survival of living-donor kidney transplantation:nomograms or artificial neural networks ? Transplantation, 2008, 86 (10):1401-1406.
  15. 15.  Nilsson J, Ohlsson M, Thulin L, et al. Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks. J Thorac Cardiovasc Surg, 2006, 132 (1):12-19.
  16. 16.  Nashef S, Roques F, Hammill BG, et al. Validation of European system for cardiac operative risk evaluation (EuroSCORE)in North American cardiac surgery. Eur J Cardio-thoracic Surg, 2002, 22 (1):101-105.
  17. 17.  Gogbashian A, Sedrakyan A, Treasure T. Euroscore:a systematic review of international performance. Euro J Cardio-thoracic Surg, 2004, 25 (5):695-700.
  18. 18.  Yoshimura M, Takahashi Y, Uchida K, et al. Prediction of survival in prostate cancer patients by bone scan index using computer-assisted diagnosis system. Eur J Nucl Med Mol Imaging, 2011, 38 (Suppl 2):S414.
  19. 19.  Scholl S, Biã¨che I, Pallud C, et al. Relevance of multiple biological parameters in breast cancer prognosis. Breast, 1996, 5 (1):21-30.
  20. 20.  Ei MM, Akl A, Mosbah A, et al. Prediction of survival after radical cystectomy for invasive bladder carcinoma:risk group stratification, nomograms or artificial neural networks?J Urol, 2009, 182 (2):466-472.
  21. 21.  袁金秋, 劉雅莉, 楊克虎. 基于人工神經(jīng)網(wǎng)絡(luò)的數(shù)據(jù)挖掘技術(shù)在臨床中應(yīng)用進(jìn)展. 圖書與情報(bào), 2010 (3):95-98.
  22. 22.  范炤, 呂吉元, 陳澤華, 等. 基于BP人工神經(jīng)網(wǎng)絡(luò)的急性前壁心肌梗塞冠脈內(nèi)支架術(shù)一年預(yù)后模型研究. 中國衛(wèi)生統(tǒng)計(jì), 2010, 27 (1):71-73, 82.
  23. 23.  張鳴. 初步構(gòu)建基于我國肝移植受體的生存評(píng)估模型及其與MELD的比較研究. 成都:四川大學(xué), 2006. 1-87.
  24. 24.  蔡煜東, 官家文, 甘駿人, 等. 人工神經(jīng)網(wǎng)絡(luò)方法在乳腺癌死亡率研究中的應(yīng)用. 中國生物醫(yī)學(xué)工程學(xué)報(bào), 1994, 13 (4):364-366.
  25. 25.  黃德生, 周寶森, 劉延齡, 等. BP人工神經(jīng)網(wǎng)絡(luò)用于肺鱗癌預(yù)后預(yù)測(cè). 中國衛(wèi)生統(tǒng)計(jì), 2000, 17 (6):337-340.
  26. 26.  姜成華, 王正國, 朱佩芳, 等. 基于神經(jīng)網(wǎng)絡(luò)的創(chuàng)傷預(yù)后仿真模型. 中華創(chuàng)傷雜志, 1997, 13 (3):42-44.
  27. 27.  De Laurentiis M, De Placido S, Bianco AR, et al. A prognostic model that makes quantitative estimates of probability of relapse for breast cancer patients. Clin Cancer Res, 1999, 5 (12):4133-4139.
  28. 28.  Piaggi P, Lippi C, Fierabracci P, et al. Artificial neural networks in the outcome prediction of adjustable gastric banding in obese women. PLoS One, 2010, 5 (10):e13624.
  29. 29.  Tu JV, Guerriere MJ. Use of a neural network as a predictive instrument for length of stay in the intensive care unit following cardiac surgery. Comput Biomed Res, 1993, 26 (3):220-229.
  30. 30.  Lin E, Hwang Y, Wang SC, et al. An artificial neural network approach to the drug efficacy of interferon treatments. Pharmacogenomics, 2006, 7 (7):1017-1024.
  31. 31.  Chang HH, Chen PS, Giacomini KM. A neural network model for predicting treatment response of antidepressant in patients with major depressive disorder. Biol Psychiatry, 2012, 71 (8):286S.
  32. 32.  Solomon I, Maharshak N, Chechik G, et al. Applying an artificial neural network to warfarin maintenance dose prediction. Isr Med Assoc J, 2004, 6 (12):732-735.
  33. 33.  Dipti I, Peter BS, Almassy RJ, et al. Artificial neural networks:Current status in cardiovascular medicine. J Am Coll Cardiol, 1996, 28 (2):515-521.