<![CDATA[The integration of Case-Based Reasoning (CBR) with Machine Learning (ML) has emerged as a promising approach to improve decision-making processes in various domains. This systematic review synthesizes the current state of research on hybrid models combining CBR and ML, identifying methodologies, applications, and key challenges. Through a comprehensive search of academic databases, we identified and analyzed 46 relevant studies published from 2019 to 2024. The study found that integrating CBR and ML is highly effective in domains that require historical context, improving accuracy and predictive performance. Key findings include the successful application of hybrid models in improving accuracy. However, the review also highlighted several challenges, including the complexity of model integration, the need for large and diverse data sets, and difficulties in interpreting hybrid model results. Systematic research on Case-Based Reasoning solutions remains limited. Therefore, this study analyzes the integration methods used in the CBR approach for decision-making across various fields, aiming to identify the characteristics of internal similarity. It is concluded that CBR has two significant impact factors, namely the type of similarity attribute and the way of similarity calculation, which determine the assessment process. Future research should focus on developing standardized methodologies for integrating CBR and ML, exploring the potential of hybrid models in emerging fields. This systematic review provides a basic understanding of the synergistic potential of CBR and ML and offers valuable insights for researchers and practitioners.]]>
