Identifying associations between pig pathologies using a multi-dimensional machine learning methodology

BackgroundAbattoir detected pathologies are of crucial importance to both pig production and food safety. Usually, more than one pathology coexist in a pig herd although it often remains unknown how these different pathologies interrelate to each other. Identification of the associations between different pathologies may facilitate an improved understanding of their underlying biological linkage, and support the veterinarians in encouraging control strategies aimed at reducing the prevalence of not just one, but two or more conditions simultaneously.ResultsMulti-dimensional machine learning methodology was used to identify associations between ten typical pathologies in 6485 batches of slaughtered finishing pigs, assisting the comprehension of their biological association. Pathologies potentially associated with septicaemia (e.g. pericarditis, peritonitis) appear interrelated, suggesting on-going bacterial challenges by pathogens such as Haemophilus parasuis and Streptococcus suis. Furthermore, hepatic scarring appears interrelated with both milk spot livers (Ascaris suum) and bacteria-related pathologies, suggesting a potential multi-pathogen nature for this pathology.ConclusionsThe application of novel multi-dimensional machine learning methodology provided new insights into how typical pig pathologies are potentially interrelated at batch level. The methodology presented is a powerful exploratory tool to generate hypotheses, applicable to a wide range of studies in veterinary research.

[1]  S. Abutarbush,et al.  Diseases of the Respiratory System , 2016 .

[2]  J. B. Andersen,et al.  The Danish pig health scheme: Nation-wide computer-based abattoir surveillance and follow-up at the herd level , 1984 .

[3]  R J Huey,et al.  Incidence, location and interrelationships between the sites of abscesses recorded in pigs at a bacon factory in Northern Ireland , 1996, Veterinary Record.

[4]  Preben Willeberg,et al.  The need for built-in validation of surveillance data so that changes in diagnostic performance of post-mortem meat inspection can be detected. , 2003, Preventive veterinary medicine.

[5]  Andrew J. Bulpitt,et al.  A Primer on Learning in Bayesian Networks for Computational Biology , 2007, PLoS Comput. Biol..

[6]  S. Martin,et al.  Veterinary Epidemiologic Research , 2009 .

[7]  C. Venkatesan,et al.  The Liver and Biliary System , 1983 .

[8]  Robert E. Schapire,et al.  Predicting Nearly As Well As the Best Pruning of a Decision Tree , 1995, COLT '95.

[9]  Sergei L. Kosakovsky Pond,et al.  An Evolutionary-Network Model Reveals Stratified Interactions in the V3 Loop of the HIV-1 Envelope , 2007, PLoS Comput. Biol..

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

[11]  A. Ersbøll,et al.  Chronic pleuritis in Danish slaughter pig herds. , 2002, Preventive veterinary medicine.

[12]  Gertraud Regula,et al.  Concepts for risk-based surveillance in the field of veterinary medicine and veterinary public health: Review of current approaches , 2006, BMC Health Services Research.

[13]  M. Nielen,et al.  Relationships between dairy cow mastitis and fertility management and farm performance. , 1999, Preventive veterinary medicine.

[14]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[15]  Anders Ringgaard Kristensen,et al.  An object-oriented Bayesian network modeling the causes of leg disorders in finisher herds. , 2009, Preventive veterinary medicine.

[16]  I. Dohoo,et al.  Factor analysis of swine farm management practices on Prince Edward Island , 1994 .

[17]  Nir Friedman,et al.  Being Bayesian About Network Structure. A Bayesian Approach to Structure Discovery in Bayesian Networks , 2004, Machine Learning.

[18]  J. Franckel,et al.  5. De la couleur des prépositions dans leurs emplois fonctionnels , 2006 .

[19]  N. Simionescu,et al.  The Cardiovascular System , 1983 .

[20]  J. Segalés,et al.  Risk factors associated with pleuritis and cranio-ventral pulmonary consolidation in slaughter-aged pigs. , 2010, Veterinary journal.

[21]  J. Dewulf,et al.  A cross-sectional study of risk factors associated with pulmonary lesions in pigs at slaughter. , 2011, Veterinary journal.

[22]  Lene Juul Pedersen,et al.  Early piglet mortality in loose-housed sows related to sow and piglet behaviour and to the progress of parturition , 2006 .

[23]  Sergei L. Kosakovsky Pond,et al.  Evolutionary Interactions between N-Linked Glycosylation Sites in the HIV-1 Envelope , 2006, PLoS Comput. Biol..

[24]  O. M. Hale,et al.  Losses to internal parasites in swine production. , 1988, Journal of animal science.

[25]  David C J Main,et al.  Tail-biting: a new perspective. , 2010, Veterinary journal.

[26]  M. Nielen,et al.  Identification of factors influencing the occurrence of milk spot livers in slaughtered pigs: A novel approach to understanding Ascaris suum epidemiology in British farmed pigs. , 2010, Veterinary parasitology.

[27]  G. Pinchbeck,et al.  Hierarchical and spatial analyses of pneumonia-lesion prevalence at slaughter in New Zealand lambs. , 2008, Preventive veterinary medicine.

[28]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[29]  John P. Huelsenbeck,et al.  MRBAYES: Bayesian inference of phylogenetic trees , 2001, Bioinform..

[30]  Marianne Bonde,et al.  Evaluation of sensitivity and specificity of routine meat inspection of Danish slaughter pigs using Latent Class Analysis. , 2010, Preventive veterinary medicine.

[31]  C. Gusmara,et al.  Pneumonia disease assessment using a slaughterhouse lung-scoring method. , 2007, Journal of veterinary medicine. A, Physiology, pathology, clinical medicine.

[32]  Nir Friedman,et al.  Being Bayesian about Network Structure , 2000, UAI.

[33]  C. Enøe,et al.  Infectious and rearing-system related risk factors for chronic pleuritis in slaughter pigs. , 2002, Preventive veterinary medicine.

[34]  M. Stenbeck,et al.  Respiratory system. , 1995, Acta oncologica.

[35]  P. Davies,et al.  Using slaughter inspections to evaluate sarcoptic mange infestation of finishing swine. , 1997, Veterinary parasitology.

[36]  M. Nielen,et al.  The British pig health schemes: integrated systems for large-scale pig abattoir lesion monitoring , 2011, Veterinary Record.

[37]  W Steeneveld,et al.  Providing probability distributions for the causal pathogen of clinical mastitis using naive Bayesian networks. , 2009, Journal of dairy science.

[38]  George M. Maxwell,et al.  The Alimentary System , 1984 .

[39]  Nicola Fox,et al.  Cardiovascular system. , 2007, Nursing Standard.

[40]  F I Lewis,et al.  Structure discovery in Bayesian networks: an analytical tool for analysing complex animal health data. , 2011, Preventive veterinary medicine.

[41]  R. Morrison,et al.  Relationships between tail biting in pigs and disease lesions and condemnations at slaughter , 2007, Veterinary Record.

[42]  M. Tielen,et al.  Epidemiological studies on lesions in finishing pigs in the Netherlands. I. Prevalence, seasonality and interrelationship , 1992 .

[43]  H. L. Thacker,et al.  Streptococclcs Suis Infection in Swine: A Retrospective Study of 256 Cases. Part II. Clinical Signs, Gross and Microscopic Lesions, and Coexisting Microorganisms , 1994 .