Exploring Anti-Aging Literature via ConvexTopics and Large Language Models

2026-02-23

AI Summary

This study addresses the challenge of organizing the rapidly expanding body of biomedical literature on aging, where conventional clustering and topic modeling approaches suffer from limited reproducibility and interpretability. To overcome these limitations, the authors propose ConvexTopics—a convex optimization–based clustering algorithm that generates fine-grained, interpretable topics by selecting representative samples. Applied to approximately 12,000 PubMed articles on anti-aging research and integrated with a large language model, ConvexTopics guarantees a global optimum, significantly enhancing the stability, reproducibility, and interpretability of topic modeling compared to mainstream methods such as K-means, LDA, and BERTopic. Expert validation confirmed the method’s ability to identify key themes spanning molecular mechanisms, dietary supplements, physical activity, and gut microbiota, laying the groundwork for scalable knowledge discovery tools in aging research.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Non-convex Optimization
• Machine Learning: Clustering

Application Category

• Web Mining and Content Analysis: Topic discovery and tracking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The rapid expansion of biomedical publications creates challenges for organizing knowledge and detecting emerging trends, underscoring the need for scalable and interpretable methods. Common clustering and topic modeling approaches such as K-means or LDA remain sensitive to initialization and prone to local optima, limiting reproducibility and evaluation. We propose a reformulation of a convex optimization based clustering algorithm that produces stable, fine-grained topics by selecting exemplars from the data and guaranteeing a global optimum. Applied to about 12,000 PubMed articles on aging and longevity, our method uncovers topics validated by medical experts. It yields interpretable topics spanning from molecular mechanisms to dietary supplements, physical activity, and gut microbiota. The method performs favorably, and most importantly, its reproducibility and interpretability distinguish it from common clustering approaches, including K-means, LDA, and BERTopic. This work provides a basis for developing scalable, web-accessible tools for knowledge discovery.

Problem

• topic modeling
• biomedical literature
• clustering
• interpretability
• reproducibility

Innovation

• convex optimization
• topic modeling
• interpretable clustering
• biomedical literature
• global optimum