Dataset Information

Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows.

ABSTRACT: Bovine mastitis is one of the most important economic and health issues in dairy farms. Data collection during routine recording procedures and access to large datasets have shed the light on the possibility to use trained machine learning algorithms to predict the udder health status of cows. In this study, we compared eight different machine learning methods (Linear Discriminant Analysis, Generalized Linear Model with logit link function, Naïve Bayes, Classification and Regression Trees, k-Nearest Neighbors, Support Vector Machines, Random Forest and Neural Network) to predict udder health status of cows based on somatic cell counts. Prediction accuracies of all methods were above 75%. According to different metrics, Neural Network, Random Forest and linear methods had the best performance in predicting udder health classes at a given test-day (healthy or mastitic according to somatic cell count below or above a predefined threshold of 200,000 cells/mL) based on the cow's milk traits recorded at previous test-day. Our findings suggest machine learning algorithms as a promising tool to improve decision making for farmers. Machine learning analysis would improve the surveillance methods and help farmers to identify in advance those cows that would possibly have high somatic cell count in the subsequent test-day.

SUBMITTER: Bobbo T

PROVIDER: S-EPMC8249463 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundSomatic cell score (SCS) has been promoted as a selection criterion to improve mastitis resistance. However, SCS from healthy and infected animals may be considered as separate traits. Moreover, imperfect sensitivity and specificity could influence animals' classification and impact on estimated variance components. This study was aimed at: (1) estimating the heritability of bacteria negative SCS, bacteria positive SCS, and infection status, (2) estimating phenotypic and genetic correlations between bacteria negative and bacteria positive SCS, and the genetic correlation between bacteria negative SCS and infection status, and (3) evaluating the impact of imperfect diagnosis of infection on variance component estimates.MethodsData on SCS and udder infection status for 1,120 ewes were collected from four Valle del Belice flocks. The pedigree file included 1,603 animals. The SCS dataset was split according to whether animals were infected or not at the time of sampling. A repeatability test-day animal model was used to estimate genetic parameters for SCS traits and the heritability of infection status. The genetic correlation between bacteria negative SCS and infection status was estimated using an MCMC threshold model, implemented by Gibbs Sampling.ResultsThe heritability was 0.10 for bacteria negative SCS, 0.03 for bacteria positive SCS, and 0.09 for infection status, on the liability scale. The genetic correlation between bacteria negative and bacteria positive SCS was 0.62, suggesting that they may be genetically different traits. The genetic correlation between bacteria negative SCS and infection status was 0.51. We demonstrate that imperfect diagnosis of infection leads to underestimation of differences between bacteria negative and bacteria positive SCS, and we derive formulae to predict impacts on estimated genetic parameters.ConclusionsThe results suggest that bacteria negative and bacteria positive SCS are genetically different traits. A positive genetic correlation between bacteria negative SCS and liability to infection was found, suggesting that the approach of selecting animals for decreased SCS should help to reduce mastitis prevalence. However, the results show that imperfect diagnosis of infection has an impact on estimated genetic parameters, which may reduce the efficiency of selection strategies aiming at distinguishing between bacteria negative and bacteria positive SCS.

Project description:Mastitis is one of the most important infectious diseases and one of the diseases that causes the greatest use of antibiotics in dairy cows. Therefore, updated information on the bacteria that cause mastitis and their antibiotic susceptibility properties is important. Here, for the first time in over 10 years, we updated the bacterial findings in clinical mastitis in Swedish dairy cows together with their antibiotic resistance patterns and risk factors for each bacterial species. During the period 2013-2018, samples from clinical mastitis were collected, together with information on the cows and herds of origin. The samples were cultured, and a total of 664 recovered bacterial isolates were subjected to susceptibility testing. Staphylococcus aureus (S. aureus) was the most common pathogen and accounted for 27.8% of diagnoses, followed by Streptococcus dysgalactiae (S. dysgalactiae) (15.8%), Escherichia coli (E. coli) (15.1%), Streptococcus uberis (S. uberis) (11.4%), Trueperella pyogenes (T. pyogenes) (7.7%), non-aureus staphylococci (NAS) (2.8%), Klebsiella spp. (2.7%), Enterococcus spp. (1.3%), and Streptococcus agalactiae (S. agalactiae) (1.2%). Various other bacteria accounted for 2.6%. Staphylococci were, in general, susceptible to most antibiotics, but 2.6% of S. aureus and 30.4% of NAS were resistant to penicillin. No methicillin-resistant staphylococci were found. All S. agalactiae were susceptible to penicillin. Bimodal and trimodal MIC distributions for penicillin in S. dysgalactiae and S. uberis, respectively, indicate acquired reduced susceptibility in some isolates. The mostly unimodal MIC distributions of T. pyogenes indicate that acquired resistance does usually not occur in this species. Among E. coli, 14.7% were resistant to at least one antibiotic, most often ampicillin (8.7%), streptomycin (7.8%), or sulphamethoxazole (6.9%). Klebsiella spp. had low resistance to tetracycline (9.1%) but is considered intrinsically resistant to ampicillin. Pathogen-specific risk factors were investigated using multivariable models. Staphylococcus aureus, S. dysgalactiae, and T. pyogenes were more common, while E. coli was less common in quarters with more than one pathogen. S. aureus and T. pyogenes were mostly seen in early lactation, while E. coli was more common in peak to mid lactation and S. dysgalactiae in early to peak lactation. Trueperella pyogenes and Klebsiella spp. were associated with a previous case of clinical mastitis in the current lactation. Staphylococcus aureus was associated with tie stalls and T. pyogenes with loose housing. All pathogens except E. coli and S. dysgalactiae had a seasonal distribution. In conclusion, the aetiological agents for clinical bovine mastitis have remained relatively stable over the last 10-15 years, S. aureus, S. dysgalactiae, E. coli and S. uberis being the most important. Resistance to penicillin among Gram-positive agents was low, and in general, antibiotic resistance to other compounds was low among both Gram-positive and Gram-negative agents.

Dataset Information

Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets