From Detection to Discovery: A Closed-Loop Approach for Simultaneous and Continuous Medical Knowledge Expansion and Depression Detection on Social Media

TL;DR

This paper introduces a closed-loop LLM-knowledge graph framework that simultaneously improves depression detection from social media and expands medical knowledge through iterative learning and expert supervision.

Contribution

It presents a novel iterative framework combining depression prediction and knowledge expansion, advancing both predictive accuracy and medical understanding.

Findings

Enhanced depression detection accuracy on large-scale UGC.

Discovery of clinically meaningful symptoms and social triggers.

Framework demonstrates co-evolution of models and domain knowledge.

Abstract

Social media user-generated content (UGC) provides real-time, self-reported indicators of mental health conditions such as depression, offering a valuable source for predictive analytics. While prior studies integrate medical knowledge to improve prediction accuracy, they overlook the opportunity to simultaneously expand such knowledge through predictive processes. We develop a Closed-Loop Large Language Model (LLM)-Knowledge Graph framework that integrates prediction and knowledge expansion in an iterative learning cycle. In the knowledge-aware depression detection phase, the LLM jointly performs depression detection and entity extraction, while the knowledge graph represents and weights these entities to refine prediction performance. In the knowledge refinement and expansion phase, new entities, relationships, and entity types extracted by the LLM are incorporated into the knowledge graph under expert supervision, enabling continual knowledge evolution. Using large-scale UGC, the framework enhances both predictive accuracy and medical understanding. Expert evaluations confirmed the discovery of clinically meaningful symptoms, comorbidities, and social triggers complementary to existing literature. We conceptualize and operationalize prediction-through-learning and learning-through-prediction as mutually reinforcing processes, advancing both methodological and theoretical understanding in predictive analytics. The framework demonstrates the co-evolution of computational models and domain knowledge, offering a foundation for adaptive, data-driven knowledge systems applicable to other dynamic risk monitoring contexts.