<p>As data visualizations become increasingly central to communication, analysis, and decision-making across a variety of fields, the need to ensure their accessibility becomes critical. Visual representations, such as charts, graphs, and infographics, are effective tools for conveying complex information; however, they often present significant barriers for individuals with various types of impairments. This paper explores the potential of Machine Learning (ML) to enhance the accessibility of data visualizations. Specifically, we present a Systematic Literature Review (SLR) that investigates how ML techniques have been applied to make visual data more inclusive. The review considers both visualization-related aspects (such as visualization types and source, target user, and evaluation) and ML-related factors (including data formats, preprocessing, and model types and evaluation). Our findings reveal that only a limited number of studies directly address the use of ML for improving visualization accessibility, and there is a lack of standardized solutions or frameworks in this area. Our contribution focused on the identification of a conceptual framework based on nine key open challenges that highlight the lack of consideration for infographics, particular types of charts, printed chart, different kind of impairments, involvement of users, accurate interpretation of complex visual data, real-time support, standard benchmarking, the potential bias and, hence, the need for continued research and development at the intersection of data visualization and machine learning, with a strong focus on accessibility and inclusivity.</p>