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

2025-10-23

AI Summary

Existing depression detection research prioritizes predictive accuracy while neglecting dynamic knowledge evolution. Method: This paper proposes the first closed-loop framework integrating large language models (LLMs) with a dynamic medical knowledge graph, establishing a co-evolutionary “learning-in-prediction and prediction-in-learning” mechanism. It leverages user-generated content (UGC) for symptom identification, comorbidity inference, and social risk factor discovery, and incorporates entity extraction, relation recognition, and expert-supervised incremental graph updating. Contribution/Results: The framework achieves bidirectional closed-loop optimization—simultaneously improving depression detection performance and enabling continuous clinical knowledge discovery. It is both interpretable and evolvable, supporting automated identification of novel symptoms and social risk factors. Evaluated on large-scale social media data, it achieves significantly higher detection accuracy; clinically validated findings demonstrate clear supplementary value to existing biomedical literature.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Simultaneously detecting depression and expanding medical knowledge from social media
• Integrating prediction and knowledge expansion in an iterative closed-loop framework
• Enhancing both predictive accuracy and clinical understanding through continuous learning

Innovation

• Closed-loop LLM-Knowledge Graph framework for iterative learning
• LLM performs depression detection and entity extraction simultaneously
• Knowledge graph expands with new entities under expert supervision