A model for reasoning about persistence and causation
Computational Intelligence
A computational scheme for reasoning in dynamic probabilistic networks
UAI '92 Proceedings of the eighth conference on Uncertainty in Artificial Intelligence
The EM algorithm for graphical association models with missing data
Computational Statistics & Data Analysis - Special issue dedicated to Toma´sˇ Havra´nek
A Guide to the Literature on Learning Probabilistic Networks from Data
IEEE Transactions on Knowledge and Data Engineering
Challenge: what is the impact of Bayesian networks on learning?
IJCAI'97 Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1
Local learning in probabilistic networks with hidden variables
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Probabilistic temporal networks: A unified framework for reasoning with time and uncertainty
International Journal of Approximate Reasoning
Probabilistic temporal reasoning with endogenous change
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence
A new look at causal independence
UAI'94 Proceedings of the Tenth international conference on Uncertainty in artificial intelligence
Impact of censoring on learning Bayesian networks in survival modelling
Artificial Intelligence in Medicine
Learning Bayesian networks from survival data using weighting censored instances
Journal of Biomedical Informatics
Hi-index | 0.00 |
In this paper, we introduce the Dynamic Bayesian Belief Network (DBBN) and show how it can be used in data mining. DBBNs generalise the concept of Bayesian Belief Networks (BBNs) to include a time dimension. We may thus represent a stochastic (or probabilistic) process along with causal information. The approach combines BBNs for modelling causal information with a latent Markov model for dealing with temporal (survival) events. It is assumed that the model includes both qualitative (causal) and quantitative (survival) variables. We introduce the idea of conditional phase-type (C-Ph) distributions to model such data. These models describe duration until an event occurs in terms of a process consisting of a sequence of phases - the states of a latent Markov model. Our approach is illustrated using data on hospital spells (the process) of geriatric patients along with personal details, admissions reasons, dependency levels and destination (the causal network).