Related Experiment Video
Updated: Jan 22, 2026

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
Hybrid Functional Brain Network With First-Order and Second-Order Information for Computer-Aided Diagnosis of
Qi Zhu1,2, Huijie Li1, Jiashuang Huang1
1College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China.
This study introduces a novel second-order brain network analysis to detect subtle changes in brain functional connectivity networks for schizophrenia diagnosis. The hybrid approach improves diagnostic accuracy by incorporating high-order information.
Area of Science:
- Neuroscience
- Medical Imaging
- Computational Psychiatry
Background:
- Brain functional connectivity network (BFCN) analysis is crucial for diagnosing mental disorders like schizophrenia.
- Current BFCN methods often overlook high-order information, potentially missing subtle network changes in early-stage schizophrenia.
Purpose of the Study:
- To develop a novel BFCN construction method that incorporates high-order information for improved schizophrenia diagnosis.
- To identify sensitive biomarkers for schizophrenia by analyzing multi-region correlations.
Main Methods:
- Defined triplet correlation to capture high-order information among three brain regions.
- Derived a second-order brain network using connectivity differences and ordinal information within triplets.
- Proposed a hybrid approach fusing first- and second-order brain networks.
Main Results:
- The proposed hybrid method demonstrated superior performance in schizophrenia diagnosis compared to existing BFCN methods.
- Experimental results on six datasets (439 patients, 426 controls) validated the method's effectiveness.
- Identified potential biomarkers for schizophrenia through enhanced network analysis.
Conclusions:
- The novel second-order and hybrid BFCN approach effectively captures subtle brain network alterations in schizophrenia.
- This method offers improved diagnostic accuracy and biomarker identification for schizophrenia.
- Exploiting high-order brain network information is vital for detecting complex neurological disorders.
Related Concept Videos
Schizophrenia
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Network Function of a Circuit
Biological Causes of Schizophrenia
Genetic Factors in Schizophrenia
The genetic basis of schizophrenia is strongly supported by family and twin...
Network Covalent Solids
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
Psychological and Sociocultural Causes of Schizophrenia

