Predicting the likelihood of conception to first insemination of dairy cows using milk mid-infrared spectroscopy

Abstract

The objective of this study was to examine the ability of milk mid-infrared (MIR) spectroscopy and other onfarm data, such as milk yield, milk composition, stage of lactation, calving age, days in milk at insemination, and somatic cell count, to identify cows that were most or least likely to conceive to first insemination. A total of 16,628 spectral and milk production records of 7,040 cows from 29 commercial dairy herds across 3 Australian states were used. Three models, comprising different explanatory variables, were tested. Model 1 included features that are readily available on farms participating in milk recording, such as milk yield, milk composition, somatic cell count, days from calving to insemination, and calving season. Days in milk and age at calving were incorporated into model 1 to form model 2. In model 3, MIR was added to model 2, but to avoid double counting, milk composition traits of model 2 were removed. The models were first trained on extreme data [i.e., including cows that (1) conceived to first insemination and (2) cows with no conception event recorded and with only 1 insemination]. Then, the models were validated in a fresh data set with all cows regardless of conception outcomes present to test for their ability to identify cows that conceived or did not conceive to first insemination. To do this, we ranked the predicted probability of all cows in the validation set and then selected the top and bottom records in varying proportions from 5 to 40% (i.e., where the model predicted the highest versus lowest likelihood of conception to first insemination, respectively) and compared with the actual values. The model's performance was evaluated through herd-year by herd-year external validation and measured as the proportion of selected records being correct. The results show that when more cows are selected (i.e., descending confidence), the accuracy of the models was reduced, and selecting the 10% of cows with the highest confidence of predictions produces optimal accuracy. Irrespective of the proportions, none of the models could predict cows that conceived to first insemination, with an accuracy around 0.48. When attempting to predict the bottom 10% of cows, which had the least likelihood of conception to first insemination, model 1 had prediction accuracy around 0.64. Compared with model 1, the addition of days in milk and calving age (model 2) resulted in a negligible improvement in prediction accuracy (0.01 to 0.03). Model 3 had the highest prediction accuracy (0.76), which implies that in the models tested, MIR is of primary importance in the prediction of fertility of dairy cows. In conclusion, this study indicates that MIR and other milk recording data could be used to identify cows with potential difficulty in getting pregnant to first insemination with promising accuracy.

Genetic parameters for mid-infrared spectroscopy–predicted fertility

“…Because the strongest correlation was detected between MFERT and TFERT, adapting MFERT to predict CFS rather than PREG may further increase the genetic correlation between MFERT and CFS. Furthermore, MFERT is better at predicting high and low fertile cows than moderately fertile cows (Ho et al, 2019;Ho and Pryce, 2020). If we assume a normal distribution for fertility, moderately fertile cows would make up a substantial proportion of our data.…”

“…MFERT was able to phenotypically classify cows into high or low fertile groups. The inference here is that by training the MFERT model that contrasts the most fertile cows (i.e., cows that conceived at first insemination) with the least fertile (i.e., cows with only one insemination within the mating season without conception), clearer biological signals might be observed and thus higher modeling accuracy could be obtained (Ho et al, 2019;Ho and Pryce, 2020).…”

“…The MFERT trait is the probability of conception to first insemination predicted using milk MIR, age at calving, DIM, and MY, derived using the model described in detail by Ho et al (2019) and Ho and Pryce (2020). Data used for our study were collected between 2016 and 2018 (inclusive) from 29 commercial Australian dairy herds.…”

“…Therefore, the benefit of using MFERT for genetic selection is limited at the moment. However, MFERT is a promising tool for phenotypic prediction and management (Ho et al, 2019;Ho and Pryce, 2020), and MIR samples are being collected and used for prediction of a wide range of other traits (e.g., Ho et al, 2021). Consequently, the number of records for MFERT van den Berg et al | Predicting fertility using mid-infrared spectroscopy Table 2.…”

Assessing the relationship between somatic cell count and the milk mid‐infrared spectrum in Chinese Holstein cows

“…6 However, variations in physiological status have been shown to cause changes in milk composition. Consequently, milk MIR spectroscopy also has the potential to predict characteristics such as a cow's fertility, 7,8 lameness score, 9 pregnancy status 10 and tuberculosis status. 11 However, to date, no study has been conducted to determine milk SCC by MIR spectroscopy.…”