Inferring Relationship of Blood Metabolic Changes and Average Daily Gain With Feed Conversion Efficiency in Murrah Heifers: Machine Learning Approach.

Sikka P, Nath A, Paul SS, Andonissamy J, Mishra DC, Rao AR, Balhara AK, Chaturvedi KK, Yadav KK, Balhara S. (2020). Inferring Relationship of Blood Metabolic Changes and Average Daily Gain With Feed Conversion Efficiency in Murrah Heifers: Machine Learning Approach. Front. Vet. Sci., 7. https://doi.org/10.3389/fvets.2020.00518

This study utilized machine learning algorithms to predict feed conversion efficiency (FCE) in Murrah buffalo heifers, using blood parameters and average daily gain (ADG) as predictors. Isotonic regression was found to outperform other algorithms, and the combination of additive regression as the meta-learner and isotonic regression as the base learner produced the best results. Partial least square regression (PLSR) models were developed, with the model using higher FCE values (negative residual feed intake) performing the best. Insulin-like growth factor 1 (IGF1) and its interaction with other blood parameters were identified as key factors influencing higher FCE.