An object-oriented Bayesian network modeling the causes of leg disorders in finisher herds.

The implementation of an effective control strategy against disease in a finisher herd requires knowledge regarding the disease level in the herd. A Bayesian network was constructed that can estimate risk indexes for three cause-categories of leg disorders in a finisher herd. The cause-categories of leg disorders were divided into infectious causes (arthritis caused by infectious pathogens), physical causes (e.g. fracture and claw lesions), and inherited causes (osteochondrosis). Information about the herd (e.g. the herd size, floor type and number of suppliers) and information about individual pigs (e.g. results from diagnostic tests) were used to estimate the most likely cause of leg disorders at herd level. As information to the model originated from two different levels, we used an object-oriented structure in order to ease the specification of the Bayesian network. Hence, a Herd class and a Pig class comprised the basic components of the object-oriented structure. The causal structure of the model was based on evidence from published literature. The conditional probabilities used in the model were elicited from experts within the field and from the published literature. To illustrate the behaviour of the model, we investigated the value of different levels of evidence in two fictitious herds with different herd characteristics related to the risk of leg disorders (e.g. purchase policy, production type and the stocking density in pens). The model enabled us to demonstrate the value of performing systematic collection of additional information (i.e. clinical, pathological and bacteriological examination) when identifying causes of leg disorders at herd level.

[1]  S. Stern,et al.  Osteochondrosis and leg weakness in pigs selected for lean tissue growth rate , 1995 .

[2]  O. Peltoniemi,et al.  Case-control study of factors associated with arthritis detected at slaughter in pigs from 49 farms , 2007, Veterinary Record.

[3]  T Grondalen,et al.  Osteochondrosis and arthrosis in pigs. I. Incidence in animals up to 120 kg live weight. , 1974, Acta veterinaria Scandinavica.

[4]  Elizabeth S Burnside,et al.  Bayesian networks: computer-assisted diagnosis support in radiology. , 2005, Academic radiology.

[5]  Sandra A. Edwards,et al.  Limb injuries, immune response and growth performance of early-weaned pigs in different housing systems. , 2000 .

[6]  J. Arnbjerg Effect of a low-growth rate on the frequency of osteochondrosis in Danish Landrace pigs (short communication) , 2007 .

[7]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[8]  H. B. Simonsen,et al.  Tail biting in pigs. , 2001, Veterinary journal.

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

[10]  L. C. van der Gaag,et al.  Probabilities for a Probabilistic Network : A Case-study in Oesophageal Carcinoma , 2001 .

[11]  L. Green,et al.  Prevalence and distribution of foot lesions in finishing pigs in south-west England , 1997, Veterinary Record.

[12]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[13]  S. H. Andersen,et al.  Genetic parameters for osteochondrosis in Danish Landrace and Yorkshire boars and correlations with leg weakness and production traits , 2000 .

[14]  O. P. Miniats,et al.  Glasser's disease and prevalence of subclinical infection with Haemophilus parasuis in swine in southern Ontario. , 1989, The Canadian veterinary journal = La revue veterinaire canadienne.

[15]  Hans Houe,et al.  Mycoplasma hyopneumoniae i infection. A review of pathogenesis, diagnosis, risk factors and biological effects as input for economical modelling , 2000 .

[16]  H Gjein,et al.  The Effect of Claw Lesions and Claw Infections on Lameness in Loose Housing of Pregnant Sows , 1995, Acta Veterinaria Scandinavica.

[17]  K. S. Howe,et al.  A framework for the economic analysis of disease in farm livestock , 1992 .

[18]  Jan Tind Sørensen Validation of livestock herd simulation models: a review , 1990 .

[19]  Niels Peter Baadsgaard,et al.  A Bayesian approach to the accuracy of clinical observations. , 2003, Preventive veterinary medicine.

[20]  Silja Renooij,et al.  Probabilities for a probabilistic network: a case study in oesophageal cancer , 2002, Artif. Intell. Medicine.

[21]  L. Green,et al.  Foot lesions in finishing pigs and their associations with the type of floor , 1999, Veterinary Record.

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

[23]  B Svensmark,et al.  Non-purulent arthritis in Danish slaughter pigs. I. A study of field cases. , 1995, Zentralblatt fur Veterinarmedizin. Reihe A.

[24]  N. Nielsen,et al.  Mycoplasma hyosynoviae arthritis in grower-finisher pigs. , 2001, Journal of veterinary medicine. A, Physiology, pathology, clinical medicine.

[25]  M.W.A. Verstegen,et al.  Performance and carcass traits of individual pigs housed in groups as affected by ad libitum and restricted feeding , 1996 .

[26]  P Haddawy,et al.  Construction of a Bayesian network for mammographic diagnosis of breast cancer , 1997, Comput. Biol. Medicine.

[27]  Ine H J Van der Fels-Klerx,et al.  Elicitation of Quantitative Data from a Heterogeneous Expert Panel: Formal Process and Application in Animal Health , 2002, Risk analysis : an official publication of the Society for Risk Analysis.

[28]  Trygue Grøndalen,et al.  Osteochondrosis and Arthrosis in Pigs , 1974, Acta Veterinaria Scandinavica.

[29]  学 尾形,et al.  Mycoplasma hyosynoviae , 1982, CABI Compendium.

[30]  Nils Toft,et al.  The effect of lameness treatments and treatments for other health disorders on the weight gain and feed conversion in boars at a Danish test station , 2007 .

[31]  S. Edwards,et al.  The welfare of finishing pigs in two contrasting housing systems: Fully-slatted versus straw-bedded accommodation , 2006 .

[32]  H Hariharan,et al.  An Investigation of Bacterial Causes of Arthritis in Slaughter Hogs , 1992, Journal of veterinary diagnostic investigation : official publication of the American Association of Veterinary Laboratory Diagnosticians, Inc.

[33]  N. Lundeheim,et al.  Genetic Analysis of Osteochondrosis and Leg Weakness in the Swedish Pig Progeny Testing Scheme , 1987 .

[34]  Avi Pfeffer,et al.  Object-Oriented Bayesian Networks , 1997, UAI.

[35]  L. Green,et al.  Prevalence and risk factors associated with adventitious bursitis in live growing and finishing pigs in south-west England. , 1999, Preventive veterinary medicine.

[36]  B. Jørgensen,et al.  Influence of floor type and stocking density on leg weakness, osteochondrosis and claw disorders in slaughter pigs , 2003 .