Lumpy Skin Disease (LSD) is a highly contagious viral infection that affects cattle and poses a significant threat to the livestock industry worldwide. Rapid and accurate diagnosis of LSD is crucial for controlling its spread and preventing economic losses. Traditional diagnostic methods, such as clinical observation and laboratory testing, are time-consuming and may lack sensitivity. In recent years, machine learning (ML) has emerged as a powerful tool for medical diagnosis, offering the potential for faster and more reliable detection of diseases. This paper presents a novel approach for the diagnosis of Lumpy Skin Disease using machine learning techniques. We collected a comprehensive dataset of clinical and histopathological s of cattle affected by LSD, along with data from healthy cattle for comparison. The dataset was preprocessed to remove noise and standardized for analysis.The advantages of our ML-based diagnosis system are twofold. Firstly, it offers a rapid and non-invasive method for detecting LSD, significantly reducing the time required for diagnosis compared to traditional methods. This speed is crucial for implementing timely control measures and preventing the spread of the disease. Secondly, the system's high accuracy ensures reliable results, reducing the risk of misdiagnosis and associated economic losses. The system has the potential to revolutionize the way LSD is detected and managed, contributing to the health and productivity of cattle populations worldwide while safeguarding the livestock industry against this devastating disease.

Keywords: MLP, Extra tree, Naïve baye’s, evaluation, ml techniques.