Milk lipidome alterations in first-lactation dairy cows with lameness: A biomarker identification approach using untargeted lipidomics and machine learning

Lameness, defined as an impaired gait, impacts cow welfare and performance, compromising future health and production, and increasing culling risk. Untargeted milk lipidomics, together with the use of machine learning methods, have shown promise in identifying potential biomarkers for the early detection of lameness, before the development of visible clinical lameness. Prediction of early lameness would allow for the earlier implementation of management and treatment strategies, ultimately reducing the negative consequences. This study aimed to evaluate the predictive accuracy of differences in the milk metabolome and identify milk lipid biomarkers for early lameness detection in first-lactation dairy cows. Untargeted lipidomics and machine learning approaches were used to evaluate the differences in the milk metabolomic profiles in samples collected from heifers during the transition period (before lameness) and at the time of first lameness onset. A total of 56 milk samples from 32 cows (16 lame, 16 control) were analyzed by liquid chromatography-high-resolution mass spectrometry after calving (before lameness) and at lameness onset. Elastic net regression achieved 83% accuracy in predicting lameness from samples collected after calving and 100% accuracy at the time of lameness. A total of 10 mass ions selected by different statistical methods showed potential to be considered predictors of lameness. Pathway analysis revealed significant dysregulation of retinol metabolism after calving in cows that go on to develop lameness in that lactation. This study demonstrated potential for using milk lipidomics for early lameness detection. This, in turn, provides insights into lameness pathogenesis, furthering our understanding of lameness, with the ultimate goal of developing interventions to improve dairy cow welfare and farm productivity.