Machine Learning to Predict Pregnancy in Dairy Cows: An Approach Integrating Automated Activity Monitoring and On-Farm Data.

Automated activity monitoring (AAM) systems are critical in the dairy industry for detecting estrus and optimizing the timing of artificial insemination (AI), thus enhancing pregnancy success rates in cows. This study developed a predictive model to improve pregnancy success by integrating AAM data with cow-specific and environmental factors. Utilizing data from 1,054 cows, this study compared the pregnancy outcomes between two AI timings-8 or 10 h post-AAM alarm. Variables such as age, parity, body condition, locomotion, and vaginal discharge scores, peripartum diseases, the breeding program, the bull used for AI, milk production at the time of AI, and environmental conditions (season, relative humidity, and temperature-humidity index) were considered alongside the AAM data on rumination, activity, and estrus intensity. Six predictive models were assessed to determine their efficacy in predicting pregnancy success: logistic regression, Bagged AdaBoost algorithm, linear discriminant, random forest, support vector machine, and Bagged Classification Tree. Integrating the on-farm data with AAM significantly enhanced the pregnancy prediction accuracy at AI compared to using AAM data alone. The random forest models showed a superior performance, with the highest Kappa statistic and lowest false positive rates. The linear discriminant and logistic regression models demonstrated the best accuracy, minimal false negatives, and the highest area under the curve. These findings suggest that combining on-farm and AAM data can significantly improve reproductive management in the dairy industry.

Identification of genomic regions related to age at first calving and first calving interval in water buffalo using single-step GBLUP.

In Brazil, water buffaloes have been used to produce milk for mozzarella cheese production. Consequently, the main selection criterion applied for the buffalo genetic improvement is the estimated mozzarella yield as a function of milk, fat and protein production. However, given the importance of reproductive traits in production systems, this study aimed to use techniques for identifying genomic regions that affect the age at first calving (AFC) and first calving interval (FCI) in buffalo cows and to select candidate genes for the identification of QTL and gene expression studies. The single-step GBLUP method was used for the identification of genomic regions. Windows of 1 Mb containing single-nucleotide polymorphisms were constructed and the 10 windows that explained the greatest proportion of genetic variance were considered candidate regions for each trait. Genes present into the selected windows were identified using the UOA_WB_1 assembly as the reference, and their ontology was defined with the Panther tool. Candidate regions for both traits were identified on BBU 3, 12, 21 and 22; for AFC, candidates were detected on BBU 6, 7, 8, 9 and 15 and for first calving interval on BBU 4, 14 and 19. This study identified regions with great contribution to the additive genetic variance of age at first calving and first calving interval in the population of buffalo cows studied. The ROCK2, PMVK, ADCY2, MAP2K6, BMP10 and GFPT1 genes are main candidates for reproductive traits in water dairy buffaloes, and these results may have future applications in animal breeding programs or in gene expression studies of the species.

Taxa de concepção de vacas leiteiras submetidas à inseminação artificial em tempo fixo em diferentes épocas do ano / Conception rate of dairy cows submitted to fixed time artificial insemination at different seasons of the year

Objetivou-se avaliar a influência da época do ano sobre a taxa de concepção de diferentes categorias de vacas lactantes submetidas à inseminação artificial em tempo fixo (IATF). As vacas foram divididas nas categorias: multíparas de alta produção (MA), multíparas de baixa produção (MB) e primíparas de alta produção (PA). Foi comparada a taxa de concepção entre as vacas inseminadas no período de temperaturas mais amenas (TA) e no período de temperaturas mais elevadas do ano (TE), dentro de cada categoria animal. Foi utilizado o seguinte protocolo de IATF para todos os animais: D0 ­ implante de progesterona e 2 mg de benzoato de estradiol; D8 ­ retirada do implante de progesterona, 0,15 mg de cloprostenol sódico, 300 UI de gonadotrofina coriônica equina, 1 mg de cipionato de estradiol; D10 ­ 0,004 mg de acetato de buserelina e inseminação artificial após 48 horas da retirada do implante. O diagnostico de gestação foi realizado aos 30 e 60 dias após a IATF. Os dados foram analisados estatisticamente pelo Teste Exato de Fisher a 5% de significância (SAS, 2000). Não houve diferença estatística entre os grupos analisados. A época do ano não interferiu na taxa de concepção de vacas multíparas de alta produção, multíparas de baixa produção e primíparas de alta produção, nos diferentes períodos do ano.

The objective of the present study was to assess the influence of season of the year on conception rate of different categories of milking cows submitted to fixed time artificial insemination (FTAI). The cows were divided into the following categories: high production multiparous (MA), low production multiparous (MB) and high production primiparous cows (PA). The conception rate was compared between the cows inseminated in the period with mild temperatures (TA) and in the period with higher temperatures (TE), within each animal category. The following FTAI protocol was used for all the animals: D0 ­ progesterone implant, 2 mg of estradiol benzoate, D8 ­ progesterone implant removal, 0.15 mg of cloprostenol sodium, 300 UI of equine chorionic gonadotropin, 1 mg of estradiol cypionate; D10 ­ 0.004 mg of buserelin acetate and artificial insemination 48 hours after removing the implant. Pregnancy was diagnosed at 30 and 60 days after FTAI and the data was analyzed by the Exact Fisher test. There was no statistical difference in the conception rate of the cows inseminated at different seasons of the year in any categories analyzed. The season of the year did not interfere in the conception rate of high production multiparous cows, low production multiparous cows and high production primiparous cows.

The effects of progesterone treatment following artificial insemination on the reproductive performance of dairy cows.

The objective of this study was to examine the effects of increasing circulating progesterone in multiparous Holstein cows, using an intravaginal progesterone implant between days 3 and 7 following fixed-time artificial insemination (FTAI). The animals were randomly assigned into two groups: (1) treatment group and (2) control (no treatment). The experiment took place during periods of high and mild temperatures. Pregnancy rates were evaluated by ultrasound at 30 and 60 days after FTAI; embryonic and fetal mortality rates were also evaluated on these dates. The temperature and humidity index on the day of FTAI were different (P < 0.05) during the times of interest, but it did not affect conception rates. Neither the conception rates at days 30 and 60 nor the embryonic and fetal mortality rates differed between the groups during either the high- or mild-temperature periods (P > 0.05). Throughout the experimental period, the serum progesterone concentration was higher in the treatment group than in the control (P < 0.05). We conclude that the intravaginal progesterone implant inserted from days 3 to 7 following FTAI had no effect on conception rates at days 30 and 60 or on embryonic or fetal mortality rates but enhances the serum progesterone concentrations following treatment in multiparous Holstein cows during high- and mild-temperature periods.

Variação da qualidade do leite cru refrigerado em função do período do ano e do tipo de ordenha / Change in the quality of cooled raw milk due to the year period and type of milking

O objetivo desta investigação foi de avaliar a qualidade do leite cru refrigerado estocado em propriedades rurais nos períodos de tempo chuvoso e seco. As amostras foram avaliadas quanto a CCS, CBT, composição centesimal, contagem de microrganismos psicrotróficos e acidez titulável; os dados foram submetidos à análise de variância. Os fatores analisados foram: período do ano (chuvoso ou seco) e tipo de ordenha (manual ou mecânica), em delineamento inteiramente randômico e em arranjo fatorial 2 x 2. A comparação dos resultados em função do período de ano e tipo de ordenha foi realizada por meio do teste F da análise de variância; utilizando-se o programa software SISVAR. A taxa de CBT do leite cru refrigerado estava acima do limite estabelecido pela legislação, o que serve de alerta aos produtores e indústrias na obtenção e processamento de leite com qualidade higiênico-sanitária adequada.

The present investigation aims at evaluating the quality of cooled raw milk stored in dairy farms duringrainy and dry weathers. The collected samples were analyzed on SCC, TBC, centesimal composition, psychrotrophics count and titratable acidity; the variance analysis was employed for evaluating the observeddata. The analyzed factors were weather period (rainy or dry) and milking procedure (manual or mechanical), in a random delineation and in factorial arrangement 2 x 2. The data comparison as per year period and milking technique was performed by means of variance analysis (F-test), using the SISVAR software. The TBC rate of cooled raw milk was over the limit established by the legislation in effect, which indicated the inadequate hygienic-sanitary quality of the cooled raw milk samples analyzed.

Qualidade do leite na indústria de laticínios / The quality of the milk stored in dairy industries silos

Com o objetivo de avaliar a qualidade das amostras de leite conservadas nos silos de estocagem de duas indústrias de laticínios, foram coletadas sete amostras da indústria A e seis da indústria B. As amostras foram analisadas quanto aos parâmetros CCS, CBT, composição centesimal, contagem de microrganismos psicrotróficos e acidez titulável. A comparação de resultados entre os tipos de amostra foi realizada por meio do teste F da análise de variância. As análises estatísticas foram feitas por meio do programa de software SISVAR. Foram encontradas más condições de higiene dos utensílios e equipamentos usados nos silos; a temperatura e o tempo de estocagem estavam acima dos respectivos limites máximos permitidos pela legislação. Os resultados obtidos indicaram que as autoridades pertinentes não tem monitorado a qualidade do leite cru refrigerado recebido pelas indústrias de laticínios.

The present study analyzes the milk samples collected from the storing silos of two dairy industries,being seven samples from industry A and six from industry B. The SCC, TBC, centesimal composition,psychrotrophic microorganism counting and the titratable acidity were investigated. The results on typesof milk samples were statistically compared by means of test F of the variance analysis, employing theSISVAR software. Unsuitable hygienic conditions in appliances and equipments were found, and the milkstorage time-period and temperature were found to be over the respective maximum limits established by the legislation in force. Inadequate procedures in storing raw milk samples produce hazards that must bemitigated by monitoring the quality of products.