Artificial Intelligence in Medicine
Volume 37, Issue 2 , Pages 119-130 , June 2006

Artificial neural network for the joint modelling of discrete cause-specific hazards

  • Elia M. Biganzoli

      Affiliations

    • Unità di Statistica Medica e Biometria, Istituto Nazionale Tumori, Milano, Via Venezian 1, 20133 Milano, Italy
    • ,
  • Patrizia Boracchi

      Affiliations

    • Istituto di Statistica Medica e Biometria, Università degli Studi di Milano, Italy
    • ,
  • Federico Ambrogi

      Affiliations

    • Unità di Statistica Medica e Biometria, Istituto Nazionale Tumori, Milano, Via Venezian 1, 20133 Milano, Italy
    • Corresponding Author InformationCorresponding author. Tel.: +39 02 23902065; fax: +39 02 50320866.
    • ,
  • Ettore Marubini

      Affiliations

    • Istituto di Statistica Medica e Biometria, Università degli Studi di Milano, Italy

Received 9 May 2005 ,Revised 30 December 2005 ,Accepted 11 January 2006.

References 

  1. Marubini E, Valsecchi MG. Analyzing survival data from clinical trial and observational studies. Chichester: John Wiley and Sons; 1995;
  2. Klein JP, Keiding N, Kamby C. Semiparametric Marshall-Olkin models applied to the occurrence of metastases at multiple sites after breast cancer. Biometrics. 1989;45:1073–1086
  3. Lunn M, McNeil D. Applying Cox regression to competing risks. Biometrics. 1995;51:524–532
  4. Herndon JE, Harrell FE. The restricted cubic spline as baseline hazard in the proportional hazards model with step function time dependent covariables. Stat Med. 1995;14:2119–2129
  5. Aitkin M, Anderson D, Francis B, Hinde J. Statistical modeling in Glim. Oxford: Oxford University Press; 1989;
  6. Larson MG. Covariate analysis of competing-risks data with log-linear models. Biometrics. 1984;40:459–468
  7. Kramar A, Pejovic MH, Chassagne D. A method of analysis taking into account competing events: application to the study of digestive complications following irradiation for cervical cancer. Stat Med. 1987;6:785–794
  8. Boracchi P, Biganzoli E, Marubini E. Joint modelling of cause-specific hazard functions with cubic splines: an application to a large series of breast cancer patients. Comput Stat Data Anal. 2003;42:243–262
  9. Boracchi P, Biganzoli E, Marubini E. Modelling cause-specific hazards with radial basis function artificial neural networks: application to 2233 breast cancer patients. Stat Med. 2001;30:3677–3694
  10. Biganzoli E, Boracchi P, Mariani L, Marubini E. Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med. 1998;17:1169–1186
  11. Biganzoli E, Boracchi P, Marubini E. A general framework for neural network models on censored survival data. Neural Netw. 2002;15:209–218
  12. Lisboa PJG, Wong H, Harris P, Swindell R. A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer. Artif Intell Medi. 2003;28:1–25
  13. Liestol K, Andersen PK, Andersen U. Survival analysis and neural nets. Stat Med. 1994;13:1189–1200
  14. Coradini D, Daidone MG, Boracchi P, Biganzoli E, Oriana S, Bresciani G,, et al. Time-dependent relevance of steroid receptors in breast cancer. J Clin Oncol. 2000;18:2702–2709
  15. Biganzoli E, Boracchi P, Coradini D, Daidone MG, Marubini E. Prognosis in node-negative primary breast cancer: a neural network analysis of risk profiles using routinely assessed factors. Ann Oncol. 2003;14:1484–1493
  16. McCullagh P, Nelder JA. Generalized linear models. London: Chapman and Hall; 1989;
  17. Efron B. Logistic regression, survival analysis, and the Kaplan–Meyer curve. J Am Stat Assoc. 1988;83:414–425
  18. Bishop CM. Neural networks for pattern recognition. New York: Oxford University Press Inc; 1995;
  19. Venables WN, Ripley BD. Modern applied statistics with S-PLUS. fourth ed.. New York: Springer; 2003;
  20. Ripley BD. Pattern recognition and neural networks. Cambridge: Cambridge University Press; 1996;
  21. Sarle WS. Neural network faq, 2002. Official FAQ of the Usenet newsgroup comp.ai. neural-nets (http://www.sas.com/pub/neural/FAQ.html). Accessed: 1 April 2005.
  22. Ripley BD. Neural networks and flexible regression and discrimination. In:  Mardia KV editors. Statistics and images advances in applied statistics. Abingdon: Carfax; 1994;p. 39–57
  23. Moody J. Prediction risk and architecture selection for neural networks. In: Cherkassky V, Friedman JH, Wechsler H, editors. From statistics to neural networks. NATO ASI Series F. Springer-Verlag; 1994.
  24. Murata N, Yoshizawa S, Amari S. Network information criterion—determining the number of hidden units for artificial neural network models. IEEE Trans. Neural Networks. 1994;5:865–872
  25. Moody JE. The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems. In:  Moody JE,  Hanson SJ,  Lippmann RP editor. Advances in neural information processing systems. vol. 4:San Mateo: Morgan Kaufmann; 1992;p. 847–854
  26. Biganzoli E, Ambrogi F, Boracchi P. Selection of artificial neural network models for survival data. 23rd Meeting of the International Society for Clinical Biostatistics, Dijon, France, September 9–13, 2002.
  27. Mariani L, Coradini D, Biganzoli E, Boracchi P, Marubini E, Pilotti S,, et al. Prognostic factors for metachronous contralateral breast cancer: a comparison of the linear Cox regression model and its artificial neural network extension. Breast Cancer Res Treat. 1997;44:167–178
  28. Fahrmeir L, Wagenpfeil S. Smoothing hazard functions and time-varying effects in discrete duration and competing risks models. J Am Stat Assoc. 1996;91:1584–1594

PII: S0933-3657(06)00057-1

doi: 10.1016/j.artmed.2006.01.004

Artificial Intelligence in Medicine
Volume 37, Issue 2 , Pages 119-130 , June 2006

Article Tools

* Image Usage & Resolution