Research Hotspots and Cutting-edge Trends in Machine Learning for Chronic Disease Management: A Bibliometric and Visual Analysis

Objective: This study aims to provide an overview of the current status and emerging trends in machine learning (ML) applications for chronic disease managementˈ analyze the research hotspots and frontiers in this field, and provide a reference for further development and in-depth research of ML in chronic disease management in the future. Methods: The methodology involved searching the Web of Science core database for relevant literature on ML and chronic disease management up to June 23, 2024. Visualization and analysis were performed with the help of CiteSpaces (6.3.R1), VOSviewer (1.6.20), and R (4.4.1) software. Results: A total of 1070 papers were included, and the number of ML research publications in chronic disease management showed an exponential increase in general. Deep learning is the most popular machine learning algorithm, and prediction is the hottest machine learning method. Hotspot diseases are diabetes and its complications, cardiovascular diseases, and popular applications are risk prediction, diagnosis, and individualized treatment. Conclusion: The growth of ML in the area of chronic diseases is penetrating deeper into all aspects of management. Future research can enhance ML’s role in chronic disease management by continuously optimizing algorithms and integrating multi-source data.