August 15, 2025Nature CommunicationsOpen Access

Large language model powered knowledge graph construction for mental health exploration

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Innovative knowledge graph enhances predictive modeling for mental disorders, suggesting new avenues for clinical validation.

MDKG significantly improves predictive accuracy in mental disorders, reducing evaluation time by up to 70%.
The knowledge graph encompasses over 10 million relations, including nearly 1 million new associations from previous studies.
Built using large language models, the graph unifies data from biomedical literature and curated databases.
MDKG serves as a scalable resource for psychiatric research, aiding in the discovery of reliable biomarkers and disease pathways.

Gao et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark