Exploring Anti-Aging Literature via ConvexTopics and Large Language Models

TL;DR

This paper introduces a convex optimization-based clustering method for biomedical literature that produces stable, interpretable, and fine-grained topics, improving reproducibility over traditional approaches.

Contribution

It reformulates clustering as a convex optimization problem, enabling stable, reproducible, and interpretable topic discovery in large biomedical datasets.

Findings

Uncovered medically validated topics on aging and longevity.

Outperformed K-means, LDA, and BERTopic in stability and interpretability.

Produced fine-grained, meaningful topics from 12,000 PubMed articles.

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.