Rubber (Hevea brasiliensis) is an important agricultural product that makes significant contributions to the world economy, especially in tropical areas like Malaysia, Thailand, and India. However, rubber plantations face high susceptibility to a range of leaf diseases, including Abnormal Leaf Fall, Powdery Mildew, and Corynespora Leaf Fall, which can cause large production decreases. Traditional methods for identifying diseases can be difficult and mostly depend on expert visual inspection. Machine learning (ML) and deep learning (DL) techniques have shown good results in the automated process of plant disease detection and prediction in the past few years. This research paper presents a comprehensive review of ML-based techniques for disease prediction and detection in rubber plantations. This research paper discussed various image processing techniques, machine learning algorithms, datasets, and performance.