Utilização de inteligência artificial (redes neurais artificiais) para a classificação do comportamento bioquímico de amostras de Escherichia coli isoladas de frangos de corte

Salle, Felipe de Oliveira; Fortes, Flávia Bonarcini Borges; Rocha, Ângela Sanches; Rocha, Sílvio Luis da Silveira; Souza, Guilherme Fonseca de; Moraes, Hamilton Luiz de Souza; Moraes, Lucas Brunelli de; Salle, Carlos Tadeu Pippi

doi:10.22456/1679-9216.16542

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thus, the monitoring of pathogenic E. coli in the poultry farms is important and becomes unavoidable. The difficulty in distinguishing pathogenic and no pathogenic strains of E. coli after bacterial isolation is possibly related to the complexity of the interactions that exist among the virulence factors of E. coli, beyond the subjectivity of conventional parameters used to determine the pathogenicity [18].…”

Section: Discussionmentioning

confidence: 99%

Classification of Avian Pathogenic Escherichia coli by a Novel Pathogenicity Index Based on an Animal Model

Souza

Rocha

Furian

et al. 2016

Acta Scientiae. Vet.

Self Cite

View full text Add to dashboard Cite

Background: Avian Pathogenic Escherichia coli is the main agent of colibacillosis, a systemic disease that causes considerable economic losses to the poultry industry. In vivo experiments are used to measure the ability of E. coli to be pathogenic. Generally, these experiments have proposed different criteria for results interpretation and did not take into account the death time. The aim of this study was to propose a new methodology for the classification of E. coli pathogenicity by the establishment of a pathogenicity index based in the lethality, death time and the ability of the strain to cause colibacillosis lesions in challenged animals.Materials, Methods & Results: A total of 293 isolates of E. coli were randomly selected to this study. The strains were isolated from cellulitis lesions, broiler bedding material or respiratory diseases and were previously confirmed through biochemical profile. The bacterial isolates were kept frozen at -20°C. The strains were retrieved from stocks and cultured in brain-heart infusion broth overnight at 37°C to obtain a final concentration of 109 UFC/mL. A total of 2940 one-dayold chicks from commercial breeding hens were randomly assigned to groups containing 10 animals and each group was subcutaneously inoculated in the abdominal region with 0.1 mL of the standard inoculum solution containing each of the strains. A control group of 10 broilers were inoculated with 0.1 mL of brain-heart infusion broth by the same route. The chicks were kept for seven days. They were observed at intervals of 6, 12 and 24 h post-inoculation during the first days. From the second day on, the chicks were observed at intervals of 12 h. According to the death time and to the scores of each lesion (aerosaculitis, pericarditis, perihepatitis, peritonitis and cellulitis), a formula to determine the Individual Pathogenicity Index was established. A value of 10 was established as the maximum pathogenicity rate for an inoculated bird. From this rate, 5 points corresponded to scores for gross lesions present at necropsy. For each lesion present, it represents 1 point. The remaining 5 points corresponded to the death time. To obtain the death time value, an index of 1, corresponding to the maximum value assigned to a death on the first day, was divided by the number of days that the birds were evaluated, resulting in a value of 0.1428, which corresponded to a survival bonus factor. It was possible to classify E. coli strains into four pathogenicity groups according to the pathogenicity index: high pathogenicity (pathogenicity index ranging from 7 to 10), intermediate pathogenicity (pathogenicity index ranging from 4 to 6.99), low pathogenicity (pathogenicity index ranging from 1 to 3.99) and apathogenic (pathogenicity index ranging from 0 to 0.99). The analysis of the strains according to their origin revealed that isolates from broiler bedding material presented a lower pathogenicity index.Discussion: It is possible that the source of isolation implies in different results, depending on the criteria adopted. This data reinforces the importance of use a more accurate mathematical model to represents the biological phenomenon. In the study, all avian pathogenic Escherichia coli strains were classified based on a pathogenicity index and the concept of the death time represents an interesting parameter to measure the ability of the strain to promote acute and septicemic manifestation. The use of a support method for poultry veterinary diagnostic accompanying the fluctuation of the bacteria pathogenicity inside the farms may indicate a rational use of antimicrobial in poultry industry.

show abstract

Section: Discussionmentioning

confidence: 99%

Classification of Avian Pathogenic Escherichia coli by a Novel Pathogenicity Index Based on an Animal Model

Souza

Rocha

Furian

et al. 2016

Acta Scientiae. Vet.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this context, the development of alternative and objective tools for the productive management of farms is essential to guarantee the productivity and health of the flocks. Among these alternative tools, the ANNs proved to be a viable and robust tool that can be used to laying hens management [20]. Such methods have been applied in animal sciences, and their popularity is increasing due to their superiority in predictive ability for complex systems [8].…”

Section: Discussionmentioning

confidence: 99%

Artificial Neural Networks on Eggs Production Data Management

Almeida

Oliveira

Furian

et al. 2020

Acta Scientiae. Vet.

Self Cite

View full text Add to dashboard Cite

Background: Eggs have acquired a greater importance as an inexpensive and high-quality protein. The Brazilian egg industry has been characterized by a constant production expansion in the last decade, increasing the number of housed animals and facilitating the spread of many diseases. In order to reduce the sanitary and financial risks, decisions regarding the production and the health status of the flock must be made based on objective criteria. The use of Artificial Neural Networks (ANN) is a valuable tool to reduce the subjectivity of the analysis. In this context, the aim of this study was at validating the ANNs as viable tool to be employed in the prediction and management of commercial egg production flocks.Materials, Methods & Results: Data from 42 flocks of commercial layer hens from a poultry company were selected. The data refer to the period between 2010 and 2018 and it represents a total of 600,000 layers. Six parameters were selected as “output” data (number of dead birds per week, feed consumption, number of eggs, weekly weight, weekly egg production and flock uniformity) and a total of 13 parameters were selected as “input” data (flock age, flock identification, total hens in the flock, weekly weight, flock uniformity, lineage, weekly mortality, absolute number of dead birds, eggs/hen, weekly egg production, feed consumption, flock location, creation phase). ANNs were elaborated by software programs NeuroShell Predictor and NeuroShell Classifier. The programs identified input variables for the assembly of the networks seeking the prediction of the variables called outgoing that are subsequently validated. This validation goes through the comparison between the predictions and the real data present in the database that was the basis for the work. Validation of each ANN is expressed by the specific statistical parameters multiple determination (R2) and Mean Squared Error (MSE). For instance, R2 above 0.70 expresses a good validation. ANN developed for the output variable “number of dead birds per week” presented R2= 0.9533 and MSE= 256.88. For “feed consumption”, the results were R2= 0.7382 and MSE= 274.56. For “number of eggs (eggs/hen)”, the results were R2= 0.9901 and MSE= 172.26. For “weekly weight”, R2= 0.9712 and MSE= 11154.41. For “weekly egg production”, R2= 0.8015 and MSE= 72.60. For “flock uniformity”, R2= -2.9955 and MSE= 431.82.Discussion: From the six ANN designed in this study, in five it was possible to validate the predictions by comparing predictions with the real data. In one output parameter (“flock uniformity”), it was not possible to have adequate validation due to insufficient data in our database. For “number of dead birds per week”, “feed consumption”, “weekly weight” and “uniformity”, the most important variable was “flock age” (27.5%, 52.5%, 55.2% and 37.9%, respectively). For “number of eggs (eggs/hen)”, “uniformity” (52.1%) was the most relevant variable for prediction. For “weekly egg production”, “flock age” and “number of eggs (eggs/hen)” were the most important zootechnical parameters, both with a relative contribution of 38.2%. The results showed that even with the use of a robust tool such as ANNs, it is necessary to have well-noted and clear information that expresses the reality of the flocks. In any case, the results presented allow us to state that ANNs are capable for the management of data generated in a commercial egg production facility. The process of evaluation of these data would be improved if ANNs were routinely used by the professionals linked to this activity.

show abstract

“…Em Salle et al (2010), as RNAs foram utilizadas para a classificação do comportamento bioquímico de amostras de Escherichia coli isoladas de frangos de corte.…”

Section: No Trabalho Deunclassified

Estudo Da Influência De Fatores Ambientais Em Variáveis Fisiológicas De Frangos De Corte Com Redes Neurais Artificiais

Sevegnani

Silva

Fernandes³

et al. 2017

EnergAgric

View full text Add to dashboard Cite

RESUMO: Este trabalho investiga o uso de Redes Neurais Artificiais (RNAs) na análise da influência de fatores ambientais em diversos parâmetros fisiológicos em frangos de corte. Os dados deste trabalho foram obtidos em câmara climática do Núcleo de Pesquisa em Ambiência -NUPEA/ESALQ/USP. Machos e fêmeas de frangos de corte da linhagem Ross com 21, 28, 35, 42 e 49 dias de idade foram submetidos a quatro combinações de temperatura e umidade relativas. As RNAs foram utilizadas para avaliação da influência e relação de variáveis tais como temperatura, umidade relativa, frequência respiratória, temperatura retal, idade, ganho de peso, tempo de permanência no comedouro e tempo de permanência no bebedouro. Os resultados mostraram que é difícil predizer a condição ambiental a qual o animal foi submetido pelo conjunto de dados. O menor erro foi obtido com a variável ganho de peso como saída, sugerindo que esta seja a mais fortemente correlacionada com as outras variáveis.ABSTRACT: This work investigates the use of Artificial Neural Networks to analyse the influence of ambiental variables in broilers. Data was obtained in the climatic chamber of Nucleous of Bioclimatology Research (NUPEA/ESALQ/USP). Broilers (males and females) of Ross genetic with 21, 28, 35, 42 e 49 day-old were submited to four combinations of temperature and relative humidity. Artificial Neural Networks were applied to evaluation of the influence and correlation of variables such as temperature, relative humidity, respiratory frequency, retal temperature and age in the weight gain of broilers. The results showed that it is difficult to predict the environmental conditions that the animal was subjected by the data set. The smallest error was obtained with the variable weight gain as output, suggesting that this one is the most strongly correlated with the other variables.

show abstract

Utilização de inteligência artificial (redes neurais artificiais) para a classificação do comportamento bioquímico de amostras de Escherichia coli isoladas de frangos de corte

Cited by 3 publications

References 0 publications

Classification of Avian Pathogenic Escherichia coli by a Novel Pathogenicity Index Based on an Animal Model

Classification of Avian Pathogenic Escherichia coli by a Novel Pathogenicity Index Based on an Animal Model

Artificial Neural Networks on Eggs Production Data Management

Estudo Da Influência De Fatores Ambientais Em Variáveis Fisiológicas De Frangos De Corte Com Redes Neurais Artificiais

Contact Info

Product

Resources

About