Large language model powered knowledge graph construction for mental health exploration

Abstract Mental health is a major global concern, yet findings remain fragmented across studies and databases, hindering integrative understanding and clinical translation. To address this gap, we present the Mental Disorders Knowledge Graph (MDKG)—a large-scale, contextualized knowledge graph built...

Full description

Saved in:
Bibliographic Details
Main Authors: Shan Gao, Kaixian Yu, Yue Yang, Sheng Yu, Chenglong Shi, Xueqin Wang, Niansheng Tang, Hongtu Zhu
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-62781-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332570915864576
author Shan Gao
Kaixian Yu
Yue Yang
Sheng Yu
Chenglong Shi
Xueqin Wang
Niansheng Tang
Hongtu Zhu
author_facet Shan Gao
Kaixian Yu
Yue Yang
Sheng Yu
Chenglong Shi
Xueqin Wang
Niansheng Tang
Hongtu Zhu
author_sort Shan Gao
collection DOAJ
description Abstract Mental health is a major global concern, yet findings remain fragmented across studies and databases, hindering integrative understanding and clinical translation. To address this gap, we present the Mental Disorders Knowledge Graph (MDKG)—a large-scale, contextualized knowledge graph built using large language models to unify evidence from biomedical literature and curated databases. MDKG comprises over 10 million relations, including nearly 1 million novel associations absent from existing resources. By structurally encoding contextual features such as conditionality, demographic factors, and co-occurring clinical attributes, the graph enables more nuanced interpretation and rapid expert validation, reducing evaluation time by up to 70%. Applied to predictive modeling in the UK Biobank, MDKG-enhanced representations yielded significant gains in predictive performance across multiple mental disorders. As a scalable and semantically enriched resource, MDKG offers a powerful foundation for accelerating psychiatric research and enabling interpretable, data-driven clinical insights.
format Article
id doaj-art-d4a6970b64b245b0b6df08111ffd820c
institution Kabale University
issn 2041-1723
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-d4a6970b64b245b0b6df08111ffd820c2025-08-20T03:46:09ZengNature PortfolioNature Communications2041-17232025-08-0116111610.1038/s41467-025-62781-zLarge language model powered knowledge graph construction for mental health explorationShan Gao0Kaixian Yu1Yue Yang2Sheng Yu3Chenglong Shi4Xueqin Wang5Niansheng Tang6Hongtu Zhu7Yunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan UniversityInsilicom LLCDepartment of Biostatistics, University of North Carolina at Chapel HillDepartment of Statistics and Data Science, Tsinghua UniversityThe Second Affiliated Hospital of Kunming Medical University, Kunming Medical UniversitySchool of Management, University of Science and Technology of ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan UniversityDepartment of Biostatistics, University of North Carolina at Chapel HillAbstract Mental health is a major global concern, yet findings remain fragmented across studies and databases, hindering integrative understanding and clinical translation. To address this gap, we present the Mental Disorders Knowledge Graph (MDKG)—a large-scale, contextualized knowledge graph built using large language models to unify evidence from biomedical literature and curated databases. MDKG comprises over 10 million relations, including nearly 1 million novel associations absent from existing resources. By structurally encoding contextual features such as conditionality, demographic factors, and co-occurring clinical attributes, the graph enables more nuanced interpretation and rapid expert validation, reducing evaluation time by up to 70%. Applied to predictive modeling in the UK Biobank, MDKG-enhanced representations yielded significant gains in predictive performance across multiple mental disorders. As a scalable and semantically enriched resource, MDKG offers a powerful foundation for accelerating psychiatric research and enabling interpretable, data-driven clinical insights.https://doi.org/10.1038/s41467-025-62781-z
spellingShingle Shan Gao
Kaixian Yu
Yue Yang
Sheng Yu
Chenglong Shi
Xueqin Wang
Niansheng Tang
Hongtu Zhu
Large language model powered knowledge graph construction for mental health exploration
Nature Communications
title Large language model powered knowledge graph construction for mental health exploration
title_full Large language model powered knowledge graph construction for mental health exploration
title_fullStr Large language model powered knowledge graph construction for mental health exploration
title_full_unstemmed Large language model powered knowledge graph construction for mental health exploration
title_short Large language model powered knowledge graph construction for mental health exploration
title_sort large language model powered knowledge graph construction for mental health exploration
url https://doi.org/10.1038/s41467-025-62781-z
work_keys_str_mv AT shangao largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT kaixianyu largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT yueyang largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT shengyu largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT chenglongshi largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT xueqinwang largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT nianshengtang largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration
AT hongtuzhu largelanguagemodelpoweredknowledgegraphconstructionformentalhealthexploration