Bayesian Kernel Learning Methods for Parametric Accelerated Life Survival Analysis
Survival analysis is a branch of statistics concerned with the time elapsing before “failure”, with diverse applications in medical statistics and the analysis of the reliability of electrical or mechanical components. In this paper we introduce a parametric accelerated life survival analysis model based on kernel learning methods that, at least in principal, is able to learn arbitrary dependencies between a vector of explanatory variables and the scale of the distribution of survival times. The proposed kernel survival analysis method is then used to model the growth domain of Clostridium botulinum, that is the food processing and storage conditions permitting the growth of this foodborne microbial pathogen, leading to the production of the neurotoxin responsible for botulism. A Bayesian training procedure, based on the evidence framework, is used for model selection and to provide a credible interval on model predictions. The kernel survival analysis models are found to be more accurate than models based on more traditional survival analysis techniques, but also suggest a risk assessment of the foodborne botulism hazard would benefit from the collection of additional data.
Unable to display preview. Download preview PDF.
- 1.Cox, D.R., Oakes, D.: Analysis of Survival Data. Monographs on Statistics and Applied Probability, vol. 21. Chapman and Hall, Boca Raton (1984)Google Scholar
- 9.Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines (and other kernel-based learning methods). Cambridge University Press, Cambridge (2000)Google Scholar
- 10.Schölkopf, B., Smola, A.J.: Learning with kernels - support vector machines, regularization, optimization and beyond. MIT Press, Cambridge (2002)Google Scholar
- 12.Schölkopf, B., Herbrich, R., Smola, A.J.: A generalised representer theorem. In: Proceedings of the Fourteenth International Conference on Computational Learning Theory, Amsterdam, The Netherlands, pp. 416–426 (2001)Google Scholar
- 13.Fletcher, R.: Practical Methods of Optimization, 2nd edn. John Wiley and Sons, Chichester (2000)Google Scholar
- 17.Baudat, G., Anouar, F.: Kernel-based methods and function approximation. In: Proc. IJCNN, Washington, DC, pp. 1244–1249 (2001)Google Scholar
- 19.Luntz, A., Brailovsky, V.: On estimation of characters obtained in statistical procedure of recognition (in Russian). Techicheskaya Kibernetica 3 (1969)Google Scholar
- 22.Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
- 24.MacKay, D.J.C.: Hyperparameters: optimise or integrate out? In: Heidbreder, G. (ed.) Maximum Entropy and Bayesian Methods. Kluwer, Dordrecht (1994)Google Scholar
- 25.Lund, B.M., Peck, M.W.: Clostridium botulinum. In: Lund, B.M., Baird-Parker, A.C., Gould, G.W. (eds.) The Microbiological Safety and Quality of Food, Aspen, Gaithersburg, USA, pp. 1057–1109 (2000)Google Scholar
- 27.Fernández, P.S., Peck, M.W.: A predictive model that describes the effect of prolonged heating at 70 − 80° C and incubation at refrigeration temperatures on growth and toxigenesis by non-proteolytic Clostridium botulinum. Journal of Food Protection 60, 1064–1071 (1997)Google Scholar
- 28.Peck, M.W., Lund, B.M., Fairbairn, D.A., Kassperson, A.S., Undeland, P.C.: Effect of heat treatment on survival of, and growth from, spores of non-proteolytic Clostridium botulinum at refrigeration temperatures. Applied and Environmental Microbiology 61, 1780–1785 (1995)Google Scholar
- 29.Stringer, S.C., Haque, N., Peck, M.W.: Growth from spores of non-proteolytic Clostridium botulinum in heat treated vegetable juice. Applied and Environmental Microbiology 65, 2136–2142 (1999)Google Scholar