The integration of machine learning in healthcare has transformed disease prognosis and diagnosis. Healthy livestock contributes to a better environment, sustainable resource use, and the prosperity and expansion of rural communities. Various machine-learning techniques have been used in tasks such as disease prediction, medical image analysis, and drug discovery. These techniques have the potential to improve diagnostics, treatment strategies, and patient outcomes. Machine learning algorithms, using diverse data sources, enable early detection and tailored interventions. Ongoing research aims to use machine learning algorithms in healthcare databases to identify effective patterns for future predictive modeling. This study investigates machine learning algorithms and descriptive analysis methodologies to determine an individual's diabetic status. Four machine learning classifiers, including K Nearest Neighbour, Support Vector Machine, Decision Tree, and Random Forest, are examined, and compared. These classifiers show potential in enhancing diabetes prediction and improving sustainable healthcare decision-making with respective accuracies of 81.16%, 84.84%, 77.16%, and 89.83%.