Survey on Machine Learning and Deep Learning Applications in Livestock and Biomedical Research

Abstract

Machine learning (ML) and deep learning (DL) have emerged as transformative technologies across livestock and biomedical research, enabling advances in disease detection, animal health monitoring, genetic selection, and reproductive evaluation. In dairy production, ML/DL techniques have enhanced the early diagnosis of subclinical mastitis [9]; [19]; [48], lameness [2]; [29]), and infectious diseases in calves ([12]), offering non-invasive and cost-effective alternatives to traditional methods. These technologies have also improved genomic prediction strategies, combining deep learning with genomic BLUP frameworks ([21]; [33]) and providing explainable classifiers based on whole-genome sequencing ([19]). Furthermore, DL has been successfully applied to cattle identification [3]; [28]; [41]), feeding behavior monitoring [4]; [49]), reproductive assessment of bovine oocytes ([34]; [5], and carcass quality grading ([20]; [17]; [23]). Beyond livestock, biomedical research has benefited from DL in medical imaging, genomics, and disease surveillance ([14]; [18]; [47]). Despite remarkable progress, challenges remain in terms of data quality, generalization across farms, interpretability, and ethical implications ([30]; [35]; [32]). By integrating AI with precision livestock farming and biomedical practices, interdisciplinary collaboration can foster more sustainable, accurate, and welfare-oriented systems.