Abstract
The hazard function plays an important role in the study of disease dynamics in survival analysis. Longer follow-up for various kinds of cancer, particularly breast cancer, has made it possible the observation of complex shapes of the hazard function of occurrence of metastasis and death. The identification of the correct hazard shape is important both for formulation and support of biological hypotheses on the mechanism underlying the disease.
In this paper we propose the use of a neural network to model the shape of the hazard function in time in dependence of covariates extending the piecewise exponential model. The use of neural networks accommodates a greater flexibility in the study of the hazard shape.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Aitkin, M., Francis, B., Hinde, J., Darnell, R.: Statistical Modelling in R. Oxford University Press, Oxford (2009)
Biganzoli, E., Boracchi, P., Marubini, E.: A general framework for neural network models on censored survival data. Neural Netw. 37, 119–130 (2002)
Bishop, C.M.: Neural Networks for Pattern Recognition. Springer, New York (1995)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)
Boracchi, P., Biganzoli, E., Marubini, E.: Modelling cause-specific hazards with radial basis function artificial neural networks: application to 2233 breast cancer patients. Statist. Med. 20, 3677–3694 (2001)
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 An. 42, 243–262 (2003)
Demicheli, R., Retsky, M.W., Baum, M.: Tumor dormancy and surgery-driven interruption of dormancy in breast cancer: learning from failures. Nat. Clin. Pract. Oncol. 4, 699–710 (2007)
Fallah, N., Gu, H., Mohammad, K., Seyyedsalehi, S.A., Nourijelyani, K., Eshraghian, M.R.: Nonlinear Poisson regression using neural networks: a simulation study. Neural Comput. Appl. 18, 939–943 (2009)
Fu, K.K., Phillips, T.L., Silverberg, I.J., Jacobs, C., Goffinet, D.R., Chun, C., Friedman, M.A., Kohler, M., McWhirter, K., Carter, S.K.: Combined radiotherapy and chemotherapy with bleomycin and methotrexate for advanced inoperable head and neck cancer: update of a Northern California Oncology Group randomized trial. J. Clin. Oncol. 5, 1410–1418 (1987)
Herndon, J.E., Harrell, F.E.: The restricted cubic spline hazard model. Comm. Statist. Theory Meth. 19, 639–663 (1990)
Marubini, E., Valsecchi, M.G.: Analysing Survival Data from Clinical Trials and Observational Studies. Wiley, Chichester (2004)
Nabney, I.T.: NETLAB, Algorithms for Pattern Recognition. Springer, New York (2002)
R Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2013). http://www.R-project.org/
Rajaram, S., Graepel, T., Herbrich, R.: Poisson-networks: a model for structured point processes. In: Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics (2005)
Ramlau-Hansen, H.: Smoothing counting process intensities by means of kernel functions. Ann. Stat. 11, 453–466 (1983)
Ripley, B.D.: Statistical ideas for selecting network architectures. In: Kappen, B., Gielen, S. (eds.) Neural Networks: Artificial Intelligence and Industrial Applications, pp. 183–190. Springer, London (1995)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (1996)
Rosenberg, P.S.: Hazard function estimation using B-splines. Biometrics 51, 874–887 (1995)
Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S. Springer, New York (2002)
Veronesi, U., Marubini, E., DelVecchio, M., Manzari, A., Andreola, S., Greco, M., Luini, A., Merson, M., Saccozzi, R., Rilke, F., Salvadori, B.: Local recurrences and distant metastases after conservative breast cancer treatments: partly independent events. J. Natl Cancer Inst. 87, 19–27 (1995)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Fornili, M., Ambrogi, F., Boracchi, P., Biganzoli, E. (2014). Piecewise Exponential Artificial Neural Networks (PEANN) for Modeling Hazard Function with Right Censored Data. In: Formenti, E., Tagliaferri, R., Wit, E. (eds) Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB 2013. Lecture Notes in Computer Science(), vol 8452. Springer, Cham. https://doi.org/10.1007/978-3-319-09042-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-09042-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09041-2
Online ISBN: 978-3-319-09042-9
eBook Packages: Computer ScienceComputer Science (R0)