Agriculture is of utmost importance for global sustenance making it crucial to optimize crop yields and minimize losses. Therefore, plant disease detection and classification has proven to be a critical task, especially in the field of precision agriculture. Through this article, we provide a comprehensive overview of the existing machine learning and deep learning methods for the classification and health analysis of potato leaf diseases in precision agriculture. Given the need for effective disease management strategies and the potential of data-driven approaches, our goal is to bring together insights from methods such as artificial neural networks (ANNs), convolutional neural networks (CNNs), and deep learning approaches. The survey aims to highlight innovations and advances in disease classification techniques, identify optimal model parameters, and evaluate the performances of various datasets. Furthermore, the article also explores the integration of metaheuristic optimization algorithms with machine learning and deep learning models to improve accuracy and efficiency in disease classification. Effectively, the results of this survey can serve as a guide for precision agriculture researchers and practitioners, facilitating informed decisions and driving further advances in data-driven agricultural practices.