论文信息 - Developing a Bayesian Network for Clinical Diagnosis in Veterinary Medicine : from the Individual to the Herd

Developing a Bayesian Network for Clinical Diagnosis in Veterinary Medicine : from the Individual to the Herd

In close collaboration with two experts, we are building a Bayesian network for the early detection of classical swine fever in pigs. Although our network will ultimately be tailored to detecting the disease in pig herds, we decided to begin with modelling the pathogenesis of the disease in the individual animal. Having modelled the patterns of classical swine fever observed in individuals, we now are in the process of rendering our network applicable to herds. Upon doing so, we are confronted with various intriguing modelling issues. As an example, we focus in this paper on the issue of modelling diverging knowledge that pertains to the different types of pig in a herd.

Linda C. van der Gaag | Petra L. Geenen

[1] Erik Jørgensen,et al. A Bayesian network based monitoring system for sow management , 1999 .

[2] Lise Getoor,et al. Learning Probabilistic Relational Models , 1999, IJCAI.

[3] C. S. Kristensen,et al. A biological network describing infection with Mycoplasma hyopneumoniae in swine herds. , 2004, Preventive veterinary medicine.

[4] Silja Renooij,et al. How to Elicit Many Probabilities , 1999, UAI.

[5] M. D. de Jong,et al. Quantification of the transmission of classical swine fever virus between herds during the 1997-1998 epidemic in The Netherlands. , 1999, Preventive veterinary medicine.

[6] Weng-Keen Wong,et al. Bayesian Biosurveillance of Disease Outbreaks , 2004, UAI.

[7] I J McKendrick,et al. Using a Bayesian belief network to aid differential diagnosis of tropical bovine diseases. , 2000, Preventive veterinary medicine.