Identification of Predictive Subnetwork for Brain Network-Based Psychiatric Diagnosis: An Information-Theoretic Perspective DOI
Kaizhong Zheng, Shujian Yu, Badong Chen

и другие.

Опубликована: Июнь 4, 2023

Graph neural networks (GNNs) have recently been applied to develop useful diagnostic tools for psychiatric disorders. However, due the lack of interpretability, clinicians are hard identify quantifiable and personalizable biomarkers which provide biologically clinically relevance. We introduce three proposed GNN-based disorders models, namely BrainIB, Graph-PRI CI-GNN, from an information-theoretic perspective. These models able discriminate patients healthy controls predictive subgraph, a.k.a. biomarkers, solely observations. demonstrate their improved classification accuracy interpretability on ABIDE database. also put forward proposals future research.

Язык: Английский

A Systematic Review of Graph Neural Network in Healthcare-Based Applications: Recent Advances, Trends, and Future Directions DOI Creative Commons
Showmick Guha Paul, Arpa Saha, Md. Zahid Hasan

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 15145 - 15170

Опубликована: Янв. 1, 2024

Graph neural network (GNN) is a formidable deep learning framework that enables the analysis and modeling of intricate relationships present in data structured as graphs. In recent years, burgeoning interest has arisen exploiting latent capabilities GNN for healthcare-based applications, capitalizing on their aptitude complex unearthing profound insights from graph-structured data. However, to best our knowledge, no study systemically reviewed studies conducted healthcare domain. This furnished an all-encompassing erudite overview prevailing cutting-edge research healthcare. Through assimilation studies, current trends, recurrent challenges, promising future opportunities applications have been identified. China emerged leading country conduct GNN-based domain, followed by USA, UK, Turkey. Among various aspects healthcare, disease prediction drug discovery emerge most prominent areas focus application, indicating potential advancing diagnostic therapeutic approaches. proposed questions regarding diverse domain addressed them through in-depth analysis. can provide practitioners researchers with into landscape guide institutes, researchers, governments demonstrating ways which contribute development effective efficient systems.

Язык: Английский

Процитировано

17
Self-supervised learning for graph-structured data in healthcare applications: A comprehensive review DOI
Safa Ben Atitallah, Chaima Ben Rabah, Maha Driss

и другие.

Computers in Biology and Medicine, Год журнала: 2025, Номер 188, С. 109874 - 109874

Опубликована: Фев. 24, 2025

Язык: Английский

Процитировано

1
Information Geometry and Manifold Learning: A Novel Framework for Analyzing Alzheimer’s Disease MRI Data DOI Creative Commons
Ömer Akgüller, Mehmet Ali Balcı, Gabriela Cioca

и другие.

Diagnostics, Год журнала: 2025, Номер 15(2), С. 153 - 153

Опубликована: Янв. 10, 2025

Background: Alzheimer’s disease is a progressive neurological condition marked by decline in cognitive abilities. Early diagnosis crucial but challenging due to overlapping symptoms among impairment stages, necessitating non-invasive, reliable diagnostic tools. Methods: We applied information geometry and manifold learning analyze grayscale MRI scans classified into No Impairment, Very Mild, Moderate Impairment. Preprocessed images were reduced via Principal Component Analysis (retaining 95% variance) converted statistical manifolds using estimated mean vectors covariance matrices. Geodesic distances, computed with the Fisher Information metric, quantified class differences. Graph Neural Networks, including Convolutional Networks (GCN), Attention (GAT), GraphSAGE, utilized categorize levels graph-based representations of data. Results: Significant differences structures observed, increased variability stronger feature correlations at higher levels. distances between Impairment Mild (58.68, p<0.001) (58.28, are statistically significant. GCN GraphSAGE achieve perfect classification accuracy (precision, recall, F1-Score: 1.0), correctly identifying all instances across classes. GAT attains an overall 59.61%, variable performance Conclusions: Integrating geometry, learning, GNNs effectively differentiates AD stages from The strong indicates their potential assist clinicians early identification tracking progression.

Язык: Английский

Процитировано

0
MHNet: Multi-view High-Order Network for Diagnosing Neurodevelopmental Disorders Using Resting-State fMRI DOI Creative Commons
Yueyang Li, Weiming Zeng,

Wenhao Dong

и другие.

Deleted Journal, Год журнала: 2025, Номер unknown

Опубликована: Янв. 28, 2025

Abstract Deep learning models have shown promise in diagnosing neurodevelopmental disorders (NDD) like ASD and ADHD. However, many either use graph neural networks (GNN) to construct single-level brain functional (BFNs) or employ spatial convolution filtering for local information extraction from rs-fMRI data, often neglecting high-order features crucial NDD classification. We introduce a Multi-view High-order Network (MHNet) capture hierarchical multi-view BFNs derived data prediction. MHNet has two branches: the Euclidean Space Features Extraction (ESFE) module Non-Euclidean (Non-ESFE) module, followed by Feature Fusion-based Classification (FFC) identification. ESFE includes Functional Connectivity Generation (FCG) Convolutional Neural (HCNN) extract space. Non-ESFE comprises Generic Internet-like Brain Hierarchical (G-IBHN-G) Graph (HGNN) topological non-Euclidean Experiments on three public datasets show that outperforms state-of-the-art methods using both AAL1 Brainnetome Atlas templates. Extensive ablation studies confirm superiority of effectiveness fMRI features. Our study also offers atlas options constructing more sophisticated explains association between key regions NDD. leverages feature spaces, incorporating enhance classification performance.

Язык: Английский

Процитировано

0
Interpretable data-driven urban building energy modeling considering inter-building effect. DOI

Deqing Lin,

Xiaodong Xu, Ke Liu

и другие.

Building and Environment, Год журнала: 2025, Номер unknown, С. 112688 - 112688

Опубликована: Фев. 1, 2025

Процитировано

0
A comprehensive ATM security framework for detecting abnormal human activity via granger causality-inspired graph neural network optimized with eagle-strategy supply-demand optimization DOI

Aniruddha Prakash Kshirsagar,

H. Azath

Expert Systems with Applications, Год журнала: 2025, Номер 272, С. 126731 - 126731

Опубликована: Фев. 9, 2025

Язык: Английский

Процитировано

0
Multi-view united transformer block of graph attention network based autism spectrum disorder recognition DOI Creative Commons

D. Darling Jemima,

A. Grace Selvarani,

J. Daphy Louis Lovenia

и другие.

Frontiers in Psychiatry, Год журнала: 2025, Номер 16

Опубликована: Фев. 20, 2025

Introduction Autism Spectrum Disorder (ASD) identification poses significant challenges due to its multifaceted and diverse nature, necessitating early discovery for operative involvement. In a recent study, there has been lot of talk about how deep learning algorithms might improve the diagnosis ASD by analyzing neuroimaging data. Method To overrule negatives current techniques, this research proposed revolutionary strategic model called Unified Transformer Block Multi-View Graph Attention Networks (MVUT_GAT). For purpose extracting delicate outlines from physical efficient functional MRI data, MVUT_GAT combines advantages multi-view with attention processes. Result With use ABIDE dataset, thorough analysis shows that performs better than Mutli-view Site Convolution Network (MVS_GCN), outperforming it in accuracy +3.40%. This enhancement reinforces our suggested model’s effectiveness identifying ASD. The result implications over higher metrics. Through improving consistency diagnosis, will help interference assistance patients. Discussion Moreover, MVUT_GAT’s which patches distance between models medical visions helping identify biomarkers linked end, effort advances knowledge recognizing autism spectrum disorder along powerful ability enhance results value people who are undergone.

Язык: Английский

Процитировано

0
Dynamic Network Security Leveraging Efficient CoviNet with Granger Causality-Inspired Graph Neural Networks for Data Compression in Cloud IoT Devices DOI
M. Baritha Begum,

Yogeshwaran A,

Meena Nagarajan

и другие.

Knowledge-Based Systems, Год журнала: 2024, Номер unknown, С. 112859 - 112859

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

3
A generic causality‐informed neural network (CINN) methodology for quantitative risk analytics and decision support DOI
Xiaoge Zhang, Xiangyun Long, Yu Liu

и другие.

Risk Analysis, Год журнала: 2024, Номер unknown

Опубликована: Июнь 8, 2024

Abstract In this paper, we develop a generic framework for systemically encoding causal knowledge manifested in the form of hierarchical causality structure and qualitative (or quantitative) relationships into neural networks to facilitate sound risk analytics decision support via causally‐aware intervention reasoning. The proposed methodology establishing causality‐informed network (CINN) follows four‐step procedure. first step, explicate how directed acyclic graph (DAG) can be discovered from observation data or elicited domain experts. Next, categorize nodes constructed DAG representing among observed variables several groups (e.g., root nodes, intermediate leaf nodes), align architecture CINN with specified while preserving orientation each existing relationship. addition dedicated design, also gets embodied design loss function, where both are treated as target outputs predicted by CINN. third propose incorporate on stable CINN, injected constraints act guardrails prevent unexpected behaviors Finally, trained is exploited perform reasoning emphasis estimating effect that policies actions have system behavior, thus facilitating risk‐informed making through comprehensive “what‐if” analysis. Two case studies used demonstrate substantial benefits enabled support.

Язык: Английский

Процитировано

1
An objective quantitative diagnosis of depression using a local-to-global multimodal fusion graph neural network DOI Creative Commons
Shuyu Liu, Jingjing Zhou, Xuequan Zhu

и другие.

Patterns, Год журнала: 2024, Номер 5(12), С. 101081 - 101081

Опубликована: Ноя. 4, 2024

This study developed an artificial intelligence (AI) system using a local-global multimodal fusion graph neural network (LGMF-GNN) to address the challenge of diagnosing major depressive disorder (MDD), complex disease influenced by social, psychological, and biological factors. Utilizing functional MRI, structural electronic health records, offers objective diagnostic method integrating individual brain regions population data. Tested across cohorts from China, Japan, Russia with 1,182 healthy controls 1,260 MDD patients 24 institutions, it achieved classification accuracy 78.75%, area under receiver operating characteristic curve (AUROC) 80.64%, correctly identified subtypes. The further discovered distinct connectivity patterns in MDD, including reduced between left gyrus rectus right cerebellar lobule VIIB, increased Rolandic operculum hippocampus. Anatomically, is associated thickness changes gray white matter interface, indicating potential neuropathological conditions or injuries.

Язык: Английский

Процитировано

1