AI-Based Knowledge Extraction from the Bioprinting Literature for Identifying Technology Trends

Area of Science:

• Biotechnology
• Materials Science
• Computational Biology

Background:

• The rapid growth of bioprinting literature necessitates advanced tools for comprehensive analysis.
• Existing methods struggle to keep pace with the increasing volume of scientific publications.
• Standardizing nomenclature and identifying trends in bioprinting research is challenging.

Purpose of the Study:

• To develop an automated keyword annotation model for bioprinting literature analysis.
• To leverage Natural Language Processing (NLP) techniques for extracting key information.
• To accelerate the development of novel bioprinting manufacturing techniques and materials.

Main Methods:

• A composite model combining FastText embeddings and Support Vector Machine (SVM) classification was developed.
• The model was trained using bioprinting abstracts and author keywords.
• A two-stage optimization procedure was employed to enhance classification performance.

Main Results:

• The model successfully annotated keywords into categories: manufacturing technique, material, or application.
• A comprehensive lexicon of the bioprinting field was generated.
• Insights into technology trends and manufacturing-material-application relationships were extracted.

Conclusions:

• The proposed NLP model offers an automated solution for analyzing bioprinting scientific literature.
• This approach facilitates literature analysis, nomenclature standardization, and trend identification.
• The model serves as a foundation for more sophisticated automated analyses in the bioprinting domain.