A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks
Bayesian networks are attractive for developing prognostic models in medicine, due to the possibility for modelling the multivariate relationships between variables that come into play in the care process. In practice, the development of these models is hindered due to the fact that medical data is often censored, in particular the survival time. In this paper, we propose to directly integrate Cox proportional hazards models as part of a Bayesian network. Furthermore, we show how such Bayesian network models can be learned from data, after which these models can be used for probabilistic reasoning about survival. Finally, this method is applied to develop a prognostic model for Glioblastoma Multiforme, a common malignant brain tumour.
KeywordsBayesian Network Glioblastoma Multiforme Prognostic Model Karnofsky Performance Score Survival Node
- 1.Hilbe, J.: Survival analysis for epidemiologic and medical research. J. Stat. Softw. Book Rev. 30(4), 1–4 (2009)Google Scholar
- 4.Kraisangka, J., Druzdzel, M.J.: Making large Cox’s proportional hazard models tractable in Bayesian networks. In: Probabilistic Graphical Models (2016)Google Scholar
- 5.Ostrom, Q.T., Gittleman, H., Farah, P., Ondracek, A., Chen, Y., Wolinsky, Y., Stroup, N.E., Kruchko, C., Barnholtz-Sloan, J.S.: CBTRUS statistical report: primary brain and central nervous system tumors diagnosed in the united states in 2006–2010. Neuro-oncology 15(Suppl. 2), ii1–ii56 (2013)Google Scholar
- 8.Weeks, J., Cook, E.F., O’Day, S., Peterson, L., Wenger, N., Reding, D., Harrel, F., Kussin, P., Dawson, N., Connors, A., Lynn, J., Phillips, R.: Relationship between cancer patients’ predictions of prognosis and their treatment preferences. J. Am. Med. Assoc. 279(21), 1709–1714 (1998)CrossRefGoogle Scholar