Partial logistic artificial neural network for competing risks regularized with automatic relevance determination

IEEE Transactions on Neural Networks

Volumn 20, Issue 9, 2009, Pages 1403-1416

  Lisboa, Paulo J G ^a   Etchells, Terence A ^a   Jarman, Ian H ^a   Arsene, Corneliu T C ^a,b   Aung, M S Hane ^c   Eleuteri, Antonio ^d   Taktak, Azzam F G ^d   Ambrogi, Federico ^e   Boracchi, Patrizia ^e   Biganzoli, Elia ^e,f  

^a LIVERPOOL JOHN MOORES UNIVERSITY   (United Kingdom)

^b UNIVERSITY OF SOUTHAMPTON   (United Kingdom)

^c UNIVERSITY OF LIVERPOOL   (United Kingdom)

^d ROYAL LIVERPOOL UNIVERSITY HOSPITAL   (United Kingdom)

^e UNIVERSITY OF MILAN   (Italy)

^f NATIONAL CANCER INSTITUTE   (Italy)

Author keywords

Censorship; Prognostic modeling; Risk analysis; Survival modeling; Time to event data

Indexed keywords

ARTIFICIAL NEURAL NETWORK; AUTOMATIC RELEVANCE DETERMINATION; BAYESIAN REGULARIZATION; BREAST CANCER; CENSORSHIP; CLINICAL PROGNOSIS; COMPETING RISKS; CREDIT SCORING; DATA SETS; EVENT ANALYSIS; NEURAL NETWORK MODEL; PROGNOSTIC MODELING; RISK MODELING; SURVIVAL MODELING; THEORETICAL FRAMEWORK; TIME-TO-EVENT DATA;

NEURAL NETWORKS; RISK ANALYSIS; SAFETY FACTOR;

RISK ASSESSMENT;

ADOLESCENT; ADULT; AGED; ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATION; BAYES THEOREM; BREAST TUMOR; COMPUTER SIMULATION; FACTUAL DATABASE; FEMALE; FOLLOW UP; HUMAN; METHODOLOGY; MIDDLE AGED; NONLINEAR SYSTEM; PROBABILITY; PROPORTIONAL HAZARDS MODEL; RISK; STATISTICAL MODEL; SURVIVAL; TIME; TUMOR RECURRENCE;

ADOLESCENT; ADULT; AGED; ALGORITHMS; AUTOMATION; BAYES THEOREM; BREAST NEOPLASMS; COMPUTER SIMULATION; DATABASES, FACTUAL; FEMALE; FOLLOW-UP STUDIES; HUMANS; LOGISTIC MODELS; MIDDLE AGED; NEOPLASM RECURRENCE, LOCAL; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS; PROBABILITY; PROPORTIONAL HAZARDS MODELS; RISK; SURVIVAL ANALYSIS; TIME FACTORS; YOUNG ADULT;

EID: 70349260138     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2009.2023654     Document Type: Article

References (37)

1. O. O. Aalen, "Non parametric inference in connection with multiple decrement models," Scandinavian J. Statist., vol. 3, pp. 15-27, 1976.
2. B. Bakker, T. Heskes, J. Neijt, and B. Kappen, "Improving Cox survival analysis with a neural-Bayesian approach," Statist. Med., vol. 23, pp. 2989-3012, 2004.
3. E. Biganzoli, P. Boracchi, L. Mariani, and E. Marubini, "Feed forward neural networks for the analysis of censored survival data: A partial logistic regression approach," Statist. Med., vol. 17, pp. 1169-1186, 1998.
4. E. Biganzoli, P. Borachhi, and E. Marubini, "A general framework for neural network models on censored survival data," Neural Netw., vol. 15, pp. 209-218, 2002.
5. E. Biganzoli, P. Boracchi, D. Coradini, M. G. Daidone, and E. Marubini, "Time-dependent relevance of steroid receptors in breast cancer: A neural network analysis of risk profiles," Ann. Oncology, vol. 14, no. 10, pp. 1484-93, 2003.
6. E. Biganzoli, P. Boracchi, F. Ambrogi, and E. Marubini, "Artificial neural network models for the joint modeling of discrete cause specific hazards," Artif. Intell. Med., vol. 37, pp. 119-30, 2006.
7. C. M. Bishop, Neural Networks for Pattern Recognition. Oxford, U.K.: Clarendon Press, 1995.
8. P. Boracchi, E. Biganzoli, and E. Marubini, "Modelling cause-specific hazards with radial basis function artificial neural networks: Applications to 2233 breast cancer patients," Statist. Med., vol. 30, pp. 3677-3394, 2001.
9. P. Boracchi, E. Biganzoli, and E. Marubini, "Joint modelling of cause-specific hazard functions with cubic splines: An application to a large series of breast cancer patients," Comput. Statist. Data Anal. vol. 42, pp. 243-262, 2003.
10. D. R. Cox and D. Oakes, Analysis of Survival Data. New York: Chapman & Hall, 1984.
11. D. R. Cox, "Regression models and life-tables (with discussion)," J. Roy. Statist. Soc. B, vol. 34, pp. 187-220, 1972.
12. A. Eleuteri, R. Tagliaferri, L. Milano, S. De Placido, and M. De Laurentiis, "A novel neural network-based survival analysis model," Neural Netw., vol. 16, pp. 855-864, 2003.
13. B. Efron, "Logistic regression, survival analysis and the Kaplan-Meier curve," J. Amer. Statist. Assoc., vol. 83, pp. 414-425, 1988.
14. D. Faraggi and R. Simon, "A neural network model for survival data," Statist. Med., vol. 14, pp. 73-82, 1995.
15. D. Faraggi, R. Simon, E. Yaskil, and A. Kramar, "Bayesian neural network models for censored data," Biometrica J., vol. 5, pp. 519-532, 1997.
16. M. H. Galea, R. W. Blamey, C. E. Elston, and I. O. Ellis, "The Nottingham prognostic index in primary breast cancer," Breast Cancer Res. Treat., vol. 22, pp. 207-219, 1992.
17. E. L. Kaplan and P. Meier, "Nonparametric estimation from incomplete observations," J. Amer. Statist. Assoc., vol. 53, pp. 457-481, 1958.
18. K. Liestol, P. K. Andersen, and U. Andersen, "Survival analysis and neural nets," Statist. Med., vol. 13, no. 12, pp. 1189-200, Jun. 1994.
19. P. J. G. Lisboa, H. Wong, P. Harris, and R. Swindell, "A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer," Artif. Intell. Med. vol. 28, no. 1, pp. 1-25, 2003.
20. P. J. G. Lisboa, "A review of evidence of health benefit from artificial neural networks in medical intervention," Neural Netw. vol. 15, no. 1, pp. 9-37, 2002.
21. P. J. G. Lisboa, A. Vellido, and H.Wong, "Bias reduction in skewed binary classification with Bayesian neural networks," Neural Netw. vol. 13, pp. 407-410, 2000.
22. M. Lunn and D. McNeil, "Applying Cox regression to competing risks," Biometrics, vol. 51, no. 2, pp. 524-32, Jun. 1995.
23. D. J. C. MacKay, "Bayesian interpolation," Neural Comput., vol. 4, pp. 415-447, 1992.
24. D. J. C. MacKay, "The evidence framework applied to classification networks," Neural Comput., vol. 4, no. 5, pp. 720-736, 1992.
25. D. J. C. MacKay, "Probable networks and plausible predictions - A review of practical Bayesian methods for supervised neural networks," Network: Comput. Neural Syst., vol. 6, pp. 469-505, 1995.
26. E. Marubini and M. G. Valsecchi, Analysing Survival Data From Clinical Trials and Observational Studies, ser. Statistics in Practice. London, U.K.: Wiley-VCH, 2004.
27. I. Nabney, "NETLAB: Algorithms for pattern recognition," in Advances in Pattern Recognition. New York: Springer-Verlag, 2002.
28. W. B. Nelson, "Theory and applications of hazard plotting for censored failure data," Technometrics, vol. 945, p. 965, 1972.
29. A. Papoulis, Probability, Random Variables, and Stochastic Processes New York: McGraw-Hill, 1991.
30. P. M. Ravdin and G. M. Clark, "A practical application of neural network analysis for predicting outcome of individual breast cancer patients," Breast Cancer Res. Treatment, vol. 22, no. 3, pp. 285-293, Oct. 1992.
31. B. D. Ripley and R. M. Ripley, "Neural networks as statistical methods in survival analysis," in Artificial Neural Networks: Prospects for Medicine, R. Dybowski and V. Gant, Eds. Austin, TX: Landes Biosciences, 1998.
32. G. Schwartzer, W. Vach, and M. Schumacher, "On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology," Statist. Med., vol. 19, pp. 541-551, 2000.
33. P. L. Smith, "Splines as a useful and convenient statistical tool," Amer. Statist., vol. 33, pp. 57-62, 1979.
34. A. Taktak, L. Antolini, M. H. Aung, P. Boracchi, I. Campbell, B. Damato, E. Ifeachor, N. Lama, P. J. G. Lisboa, C. Setzkorn, V. Stalbovskaya, and E. M. Biganzoli, "Double-blind evaluation and benchmarking of survival models in a multi-centre study," Comput. Biol. Med., vol. 37, no. 8, pp. 1108-1120, 2007.
35. U. Veronesi, E. Marubini, M. Del Vecchio, A. Manzari, S. Andreola, M. Greco, A. Luini, M. Merson, R. Saccozzi, F. Rilke, and B. Salvadori, "Local recurrences and distant metastases after conservative breast cancer treatments: Partly independent events," J. Nat. Cancer Inst. vol. 87, pp. 19-27, 1995.
36. J. P. Klein and N. L. Moeschberger, Survival Analysis, Techniques for Censored and Truncated Data. New York: Springer-Verlag, 1997.
37. M. Aitkin, D. Anderson, B. Francis, and J. Hinde, Statistical Modelling in GLIM. Oxford, U.K.: Clarendon.