Modeling new trends in bone regeneration, using the BERTopic approach

Area of Science:

• Biomedical Engineering
• Regenerative Medicine
• Materials Science

Background:

• Bibliometric surveys are essential for tracking research progress but are time-consuming and difficult to scale.
• The field of bone regeneration is rapidly expanding, necessitating more efficient methods for literature analysis.
• Artificial intelligence offers potential solutions for automating the screening of vast scientific literature.

Purpose of the Study:

• To evaluate the utility of artificial intelligence, specifically the BERTopic algorithm, for automatically identifying research topics in bone regeneration.
• To assess the scalability and efficiency of AI-driven bibliometric analysis compared to traditional methods.
• To map research similarities and identify emerging hotspots within the bone regeneration field.

Main Methods:

• A corpus of MEDLINE manuscripts related to bone regeneration was analyzed using the BERTopic algorithm.
• BERTopic was employed to detect latent topics, map their interrelationships, and visualize research trends.
• The algorithm was used to automatically screen and categorize a large volume of scientific literature.

Main Results:

• The BERTopic algorithm successfully identified 372 distinct topics within the bone regeneration literature.
• Analysis revealed the increasing significance of novel research areas, including 3D printing and extracellular vesicles.
• The study demonstrated the capability of AI to highlight current and emerging research hotspots.

Conclusions:

• The BERTopic algorithm is a suitable tool for establishing automated screening routines in scientific research.
• AI-powered bibliometric analysis can efficiently track the progress and identify key trends in rapidly evolving fields like bone regeneration.
• This approach facilitates a more dynamic and scalable understanding of scientific advancements.