The Predictive Values of Changes in Local and Remote Brain Functional Connectivity in Primary Angle-Closure Glaucoma Patients According to Support Vector Machine Analysis

Fu, Qiang; Liu, Hui; Zhong, Yu Lin

doi:10.3389/fnhum.2022.910669

Cited by 7 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous studies, SVM have been integrated with rs-fMRI to achieve optimal predictive results for lesion classification by identifying patients and HCs based on abnormal signal values. 44–48 Therefore, we applied the SVM approach to test whether abnormal WM function can effectively differentiate PACG patients from HCs.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Analysis Classifies Patients with Primary Angle-Closure Glaucoma Using Abnormal Brain White Matter Function

Tang,

Zhong,

Wang

et al. 2024

OPTH

View full text Add to dashboard Cite

Objective Primary angle-closure glaucoma (PACG) is a globally prevalent, irreversible eye disease leading to blindness. Previous neuroimaging studies demonstrated that PACG patients were associated with gray matter function changes. However, whether the white matter(WM) function changes in PACG patients remains unknown. The purpose of the study is to investigate WM function changes in the PACG patients. Methods In total, 40 PACG patients and 40 well-matched HCs participated in our study and underwent resting-state functional magnetic resonance imaging (rs-fMRI) scans. We compared between-group differences between PACG patients and HC in the WM function using amplitude of low-frequency fluctuations (ALFF). In addition, the SVM method was applied to the construction of the PACG classification model. Results Compared with the HC group, ALFF was attenuated in right posterior thalamic radiation (include optic radiation), splenium of corpus callosum, and left tapetum in the PACG group, the results are statistically significant (GRF correction, voxel-level P < 0.001, cluster-level P < 0.05). Furthermore, the SVM classification had an accuracy of 80.0% and an area under the curve (AUC) of 0.86 for distinguishing patients with PACG from HC. Conclusion The findings of our study uncover abnormal WM functional alterations in PACG patients and mainly involves vision-related regions. These findings provide new insights into widespread brain damage in PACG from an alternative WM functional perspective.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Analysis Classifies Patients with Primary Angle-Closure Glaucoma Using Abnormal Brain White Matter Function

Tang,

Zhong,

Wang

et al. 2024

OPTH

View full text Add to dashboard Cite

show abstract

“…Recently, resting-state functional MRI (rs-fMRI) has been increasingly used to explore intrinsic brain activity in glaucoma patients and has provided critical information in the search for pathological mechanisms ( 14 , 15 ). Several recent studies have shown that PACG patients exhibit abnormalities in regional homogeneity (ReHo) ( 16 , 17 ) and amplitude of low-frequency fluctuation (ALFF) ( 18 , 19 ) in multiple brain regions. And Tong et al ( 20 ) found that there is disturbed interhemispheric resting-state functional connectivity in the vision-related brain areas of individuals with PACG.…”

Section: Introductionmentioning

confidence: 99%

Altered functional connectivity of the thalamus in primary angle-closure glaucoma patients: A resting-state fMRI study

Wang

Chen²,

Cai³

et al. 2022

Front. Neurol.

View full text Add to dashboard Cite

Background and objectivesGlaucoma is one of the leading irreversible causes of blindness worldwide, and previous studies have shown that there is abnormal functional connectivity (FC) in the visual cortex of glaucoma patients. The thalamus is a relay nucleus for visual signals; however, it is not yet clear how the FC of the thalamus is altered in glaucoma. This study investigated the alterations in thalamic FC in patients with primary angle-closure glaucoma (PACG) by using resting-state functional MRI (rs-fMRI). We hypothesized that PACG patients have abnormal FC between the thalamus and visual as well as extravisual brain regions.MethodsClinically confirmed PACG patients and age- and gender-matched healthy controls (HCs) were evaluated by T1 anatomical and functional MRI on a 3 T scanner. Thirty-four PACG patients and 33 HCs were included in the rs-fMRI analysis. All PACG patients underwent complete ophthalmological examinations; included retinal nerve fiber layer thickness (RNFLT), intraocular pressure (IOP), average cup-to-disc ratio (A-C/D), and vertical cup-to-disc ratio (V-C/D). After the MRI data were preprocessed, the bilateral thalamus was chosen as the seed point; and the differences in resting-state FC between groups were evaluated. The brain regions that significantly differed between PACG patients and HCs were identified, and the correlations were then evaluated between the FC coefficients of these regions and clinical variables.ResultsCompared with the HCs, the PACG patients showed decreased FC between the bilateral thalamus and right transverse temporal gyrus, between the bilateral thalamus and left anterior cingulate cortex, and between the left thalamus and left insula. Concurrently, increased FC was found between the bilateral thalamus and left superior frontal gyrus in PACG patients. The FC between the bilateral thalamus and left superior frontal gyrus was positively correlated with RNFLT and negatively correlated with the A-C/D and V-C/D. The FC between the left thalamus and left insula was negatively correlated with IOP.ConclusionExtensive abnormal resting-state functional connections between the thalamus and visual and extravisual brain areas were found in PACG patients, and there were certain correlations with clinical variables, suggesting that abnormal thalamic FC plays an important role in the progression of PACG.

show abstract

Topological Organization of the Brain Network in Patients with Primary Angle-closure Glaucoma Through Graph Theory Analysis

Chen,

Li,

Huang

2024

Brain Topogr

View full text Add to dashboard Cite

Primary angle-closure glaucoma (PACG) is an irreversible blinding eye disease. Previous neuroimaging studies have reported abnormal brain function changes in PACG patients, but the potential association of PACG with changes in brain functional networks remains unknown. This study aims to investigate the impact of PACG on brain networks, with the goal of enhancing understanding of its neurobiological mechanisms for improved diagnosis and treatment through the application of graph theory analysis. MethodA cohort comprising 44 PACG patients and 44 healthy controls was recruited for the study. Functional brain networks were constructed based on fMRI data utilizing the Automated Anatomical Labeling 90 template. Subsequently, graph theory analysis was conducted to assess global metrics, nodal metrics, modular organization, and network-based statistics(NBS), facilitating a comparative analysis between PACG patients and the control group. ResultThe global metrics( including small world and network e ciency) did not reveal signi cant differences between the two groups. However, PACG patients showed increased nodal metrics (including centrality and e ciency) in the left frontal superior medial, right frontal superior medial, and right posterior central brain regions, alongside decreased values in the right temporal superior gyrus region compared with health controls. Moreover, Module 5 demonstrated signi cant differences in intra-module connectivity, while signi cant variations in inter-module connectivity were observed between Module 1 and Module 7, as well as Module 1 and Module 8. Notably, the NBS analysis revealed a signi cantly modi ed network when comparing the PACG and HC groups. Conclusionthe study suggests that PACG patients exhibit differences in nodal metrics and modularity of functional brain networks, with changes observed mainly in prefrontal, occipital, and temporal lobes, as well as cerebellar regions. However, global metrics analysis indicates that the global connectivity patterns of the entire brain network remain unchanged in PACG patients. These ndings may serve as potential biomarkers for early diagnosis and differential diagnosis of PACG, and interventions targeting brain regions with high degree centrality and nodal e ciency may help to optimize therapeutic strategies.With the advancement of neuroimaging techniques, functional magnetic resonance imaging (fMRI) has emerged as a non-invasive method for measuring blood oxygen level-dependent (BOLD) signals in diverse brain regions, offering valuable insight into neural activity. ( 14). fMRI plays a pivotal role in investigating the neural mechanism alterations associated with glaucoma. Prior research has revealed varying degrees of changes in brain structure and function in glaucoma patients. For instance, a study by Jiang found differences in the whole brain grey matter volume of glaucoma patients, primarily concentrated in multiple brain regions relevant to visual motion function, the thalamocortical pathway, and emotional function. These regions incl...

show abstract

The Predictive Values of Changes in Local and Remote Brain Functional Connectivity in Primary Angle-Closure Glaucoma Patients According to Support Vector Machine Analysis

Cited by 7 publications

References 39 publications

Machine Learning Analysis Classifies Patients with Primary Angle-Closure Glaucoma Using Abnormal Brain White Matter Function

Machine Learning Analysis Classifies Patients with Primary Angle-Closure Glaucoma Using Abnormal Brain White Matter Function

Altered functional connectivity of the thalamus in primary angle-closure glaucoma patients: A resting-state fMRI study

Topological Organization of the Brain Network in Patients with Primary Angle-closure Glaucoma Through Graph Theory Analysis

Contact Info

Product

Resources

About