<p>Chronic diseases are among the primary causes of mortality and healthcare burden worldwide. Early detection and accurate prediction of these diseases play a vital role in improving patient outcomes and reducing the burden on healthcare environment. In recent years, machine learning (ML) techniques have attracted considerable attention in the healthcare area because of their ability to assist in disease diagnosis, prediction, and clinical decision-making. This study presents a Systematic Literature Review (SLR) of ML-based approaches for chronic disease classification and prediction. The review examines existing studies by analyzing widely used algorithms, datasets, feature selection methods, and performance evaluation metrics. The findings show that traditional ML algorithms, such as Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF), and Decision Tree (DT) are applied techniques in chronic disease prediction research due to their effectiveness and interpretability. Although hybrid and ensemble models have been explored to a lesser extent, several studies report improved predictive accuracy and robustness using these approaches. The review also identifies several key challenges in this field, such as data imbalance, heterogeneity in healthcare datasets, limitations in feature selection, and the absence of standardized validation frameworks. Furthermore, the study emphasizes the need for benchmark datasets and reliable evaluation protocols to improve the generalizability and practical applicability of ML models in real-world healthcare environments. This SLR provides a comprehensive overview of current research on ML-based chronic disease prediction, highlights existing research gaps, and outlines future directions for developing more accurate, scalable, and clinically reliable healthcare prediction systems.</p>