PMCCPMCCPMCC

Search tips
Search criteria 

Advanced

 
Logo of bmcvetresBioMed Centralsearchsubmit a manuscriptregisterthis articleBMC Veterinary Research
 
BMC Vet Res. 2012; 8: 151.
Published online Aug 31, 2012. doi:  10.1186/1746-6148-8-151
PMCID: PMC3483212
Identifying associations between pig pathologies using a multi-dimensional machine learning methodology
Manuel J Sanchez-Vazquez,1 Mirjam Nielen,2 Sandra A Edwards,3 George J Gunn,1 and Fraser I Lewiscorresponding author#4
1Scottish Agricultural College, Kings Buildings, West Mains Road, Edinburgh, EH9 3JG, UK
2Department of Farm Animal Health, Faculty of Veterinary Medicine, Utrecht University, Utrecht, The Netherlands
3Newcastle University, Agriculture Building, Newcastle upon Tyne, NE1 7RU, Newcastle, UK
4Section of Epidemiology, Vetsuisse Faculty, University of Zurich, Zurich, Switzerland
corresponding authorCorresponding author.
#Contributed equally.
Manuel J Sanchez-Vazquez: manueljsanchezvazquez/at/gmail.com; Mirjam Nielen: M.Nielen/at/uu.nl; Sandra A Edwards: Sandra.Edwards/at/ncl.ac.uk; George J Gunn: george.gunn/at/sac.ac.uk; Fraser I Lewis: fraseriain.lewis/at/uzh.ch
Received February 11, 2011; Accepted August 22, 2012.
Abstract
Background
Abattoir 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.
Results
Multi-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.
Conclusions
The 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.
Articles from BMC Veterinary Research are provided here courtesy of
BioMed Central