Prediction of the likelihood of conception after the first or second insemination in Chinese Holstein cows using milk Fourier-transform infrared spectroscopy.

Accurate identification of cows' likelihood of conception during the period from recent calving to the first artificial insemination (AI) will provide assistance in managing the fertility of dairy cows and contribute to the economic prosperity and sustainability of farms. The purpose of this study was to use Fourier-transform infrared (FTIR) spectroscopy data collected between recent calving and the first AI to predict the likelihood of a cow conceiving after the first AI and the first or second AI. This study specifically focused on the role of FTIR spectral and farm data collected during different time windows in improving the accuracy of models for predicting a cow's likelihood of conceiving after the first AI and the first or second AI. From 2019 to 2023, fertility information of 10,873 Holstein dairy cows in China were collected, coupled with 21,928 spectral data. First, cows were classified as having a good or poor likelihood of conception. In strategy 1, cows conceiving after the first AI were classified as having a good likelihood of conception and as others as having a poor likelihood of conception. In strategy 2, cows conceiving after the first or second AI were classified as having a good likelihood of conception and others as having a poor likelihood of conception. Second, partial least squares discriminant analysis was used to develop models for predicting the likelihood of conception after the first AI and the first or second AI. The model was assessed using a cross-validation set and herd-independent external validation set. The study also focused on examining the potential correlation between the accuracy of prediction and the period of spectral and farm data collection by analyzing the diagnostic performance of the model in 8 different time windows: from 0 to 7 d postpartum (dpp), 8 to 14 dpp, 15 to 21 dpp, 22 to 30 dpp, 31 to 45 dpp, 46 to 60 dpp, ≥61 dpp, and 0 to 7 d before the first AI. The results showed that the model based on strategy 1 performed better when in proximity to the first AI, with AUC for the cross-validation and herd-independent external validation sets of 0.621 and 0.633, respectively. The model based on strategy 2 exhibited superior performance throughout the late phase of uterine involution. The optimal model was developed by using spectral data collected from 22 to 30 dpp. The AUC for the cross-validation and herd-independent external validation sets were 0.644 and 0.660, respectively, which were higher than those of strategy 1. This study demonstrates the potential of using FTIR spectral data to predict a cow's ability to conceive. The model developed from data collected within a certain time window exhibited better prediction accuracy, particularly from 22 to 30 dpp and 0 to 7 d before the first AI. This study offers novel perspectives on alternate approaches for assessing the fertility of cows, which will contribute to the regularization and sustainability of farms, as well as to the precision management of agriculture.