Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis

ObjectiveAccurate diagnosis of neurodevelopmental disorders relies on understanding the complex interactions and high-order relationships between brain regions. This work aims to model the subtle, disease-specific high-order relationships among brain regions that have been overlooked in existing wor...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangmin Han, Junchang Li
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1654199/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849303905952858112
author Xiangmin Han
Junchang Li
author_facet Xiangmin Han
Junchang Li
author_sort Xiangmin Han
collection DOAJ
description ObjectiveAccurate diagnosis of neurodevelopmental disorders relies on understanding the complex interactions and high-order relationships between brain regions. This work aims to model the subtle, disease-specific high-order relationships among brain regions that have been overlooked in existing works.MethodThis paper proposes a Unified Multi-View Hypergraph Learning framework that combines knowledge-driven and data-driven strategies for a more precise and comprehensive representation of the adolescent brain network. The knowledge-driven branch leverages prior knowledge of functional brain subnetworks to guide feature learning and uncover structured, high-order functional associations. Meanwhile, the data-driven branch consists of two complementary modules: at the global level, a nearest-neighbor-based strategy captures large-scale associations involving overlapping brain regions; at the local level, a granularity-adaptive approach identifies finer, region-specific high-order relationships, allowing for a more nuanced understanding of brain network interactions.ResultsExperimental results on the ABIDE and ADHD datasets demonstrate that our method outperforms existing methods in diagnostic accuracy and robustness. Additionally, visualizing the high-order associations learned from both branches reveals new insights into the pathogenic mechanisms of these disorders.ConclusionThe proposed method combines knowledge-driven and data-driven strategies for high-order brain network modeling, advancing the understanding of brain networks in neurodevelopmental diseases.
format Article
id doaj-art-37fe8cf3efbc453083e85be59de08eb8
institution Kabale University
issn 2296-858X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-37fe8cf3efbc453083e85be59de08eb82025-08-20T03:55:54ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-07-011210.3389/fmed.2025.16541991654199Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosisXiangmin Han0Junchang Li1School of Software, Tsinghua University, Beijing, ChinaShenzhen Clinical Research Center for Mental Disorders, Shenzhen Kangning Hospital and Shenzhen Mental Health Center, Shenzhen, ChinaObjectiveAccurate diagnosis of neurodevelopmental disorders relies on understanding the complex interactions and high-order relationships between brain regions. This work aims to model the subtle, disease-specific high-order relationships among brain regions that have been overlooked in existing works.MethodThis paper proposes a Unified Multi-View Hypergraph Learning framework that combines knowledge-driven and data-driven strategies for a more precise and comprehensive representation of the adolescent brain network. The knowledge-driven branch leverages prior knowledge of functional brain subnetworks to guide feature learning and uncover structured, high-order functional associations. Meanwhile, the data-driven branch consists of two complementary modules: at the global level, a nearest-neighbor-based strategy captures large-scale associations involving overlapping brain regions; at the local level, a granularity-adaptive approach identifies finer, region-specific high-order relationships, allowing for a more nuanced understanding of brain network interactions.ResultsExperimental results on the ABIDE and ADHD datasets demonstrate that our method outperforms existing methods in diagnostic accuracy and robustness. Additionally, visualizing the high-order associations learned from both branches reveals new insights into the pathogenic mechanisms of these disorders.ConclusionThe proposed method combines knowledge-driven and data-driven strategies for high-order brain network modeling, advancing the understanding of brain networks in neurodevelopmental diseases.https://www.frontiersin.org/articles/10.3389/fmed.2025.1654199/fullneurodevelopmental disordershypergraph learninghigh-order correlationbrain diseaseknowledge and data dual-driven
spellingShingle Xiangmin Han
Junchang Li
Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis
Frontiers in Medicine
neurodevelopmental disorders
hypergraph learning
high-order correlation
brain disease
knowledge and data dual-driven
title Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis
title_full Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis
title_fullStr Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis
title_full_unstemmed Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis
title_short Leveraging unified multi-view hypergraph learning for neurodevelopmental disorders diagnosis
title_sort leveraging unified multi view hypergraph learning for neurodevelopmental disorders diagnosis
topic neurodevelopmental disorders
hypergraph learning
high-order correlation
brain disease
knowledge and data dual-driven
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1654199/full
work_keys_str_mv AT xiangminhan leveragingunifiedmultiviewhypergraphlearningforneurodevelopmentaldisordersdiagnosis
AT junchangli leveragingunifiedmultiviewhypergraphlearningforneurodevelopmentaldisordersdiagnosis