Study of obesity research using machine learning methods: A bibliometric and visualization analysis from 2004 to 2023

Area of Science:

• Bibliometrics and Health Informatics
• Obesity Research
• Machine Learning Applications

Background:

• Obesity is a major global health challenge requiring advanced analytical approaches.
• Machine learning (ML) offers significant potential for obesity screening, diagnosis, and analysis.
• A systematic evaluation of ML applications in obesity research is lacking.

Purpose of the Study:

• To quantitatively examine, visualize, and analyze publications on machine learning in obesity research.
• To identify trends, influential works, and emerging topics in this interdisciplinary field.
• To provide a bibliometric overview for researchers and clinicians.

Main Methods:

• Bibliometric analysis of publications from 2004-2023.
• Data sourced from the Web of Science core collection (English articles and reviews).
• Analysis tools included VOSviewer, CiteSpace, and Excel.

Main Results:

• Exponential growth in publications on machine learning for obesity research.
• The United States dominates publication volume; Leo Breiman identified as an influential author.
• Key research areas include deep learning, support vector machines, gut microbiota, and genome analysis.

Conclusions:

• Bibliometric analysis reveals the developmental patterns and intrinsic relationships in ML-driven obesity research.
• Identifies current hotspots and future research directions, including links to diabetic retinopathy and COVID-19.
• Offers valuable academic references for early detection and personalized treatment of obesity.