Disrupted dynamic amplitude of low-frequency fluctuations in patients with active thyroid-associated ophthalmopathy

Abstract

Purpose: Thyroid-associated ophthalmopathy (TAO) is an autoimmune disease that affects the orbit and is the most prevalent extra-thyroidal complication of Graves’ disease. Previous neuroimaging studies have focused on abnormal static regional activity and functional connectivity in patients with TAO. However, the characteristics of local brain activity over time are poorly understood. This study aimed to investigate alterations in the dynamic amplitude of low-frequency fluctuation (dALFF) in patients with active TAO and to distinguish patients with TAO from healthy controls (HCs) using a support vector machine (SVM) classifier.Methods: A total of 21 patients with TAO and 21 HCs underwent resting-state functional magnetic resonance imaging scans. dALFFs were calculated in conjunction with sliding window approaches to assess dynamic regional brain activity and to compare the groups. Then, we used SVM, a machine learning algorithm, to determine whether dALFF maps may be used as diagnostic indicators for TAO.Results: Compared with HCs, patients with active TAO showed decreased dALFF in the right calcarine, lingual gyrus, superior parietal lobule, and precuneus. The SVM model showed an accuracy of 45.24%–47.62% and area under the curve of 0.35–0.44 in distinguishing TAO from HCs. No correlation was found between clinical variables and regional dALFF.Conclusion: Patients with active TAO showed altered dALFF in the visual cortex and the ventral and dorsal visual pathways, providing further details on the pathogenesis of TAO.

Aberrant dynamic functional and effective connectivity changes of the primary visual cortex in patients with retinal detachment via machine learning

“…Conversely, a signi cant decrease in dEC values was found from L-PoCG to L-V1. In a study by Wen et al 33 , an increase in dALFF value was reported in the SPG of patients with active thyroid-associated ophthalmopathy. This nding was postulated to be associated with delayed visuospatial information processing.Wu et al 34 discovered a decrease in FC values of the IPL among patients with asthma, potentially in uencing attention and executive function.…”

Machine learning analysis reveals aberrant dynamic changes in amplitude of low-frequency fluctuations among patients with retinal detachment

“…Finally, the support-vector machine (SVM) is a supervised machine learning technique that seeks to maximize the margin to sort input points into classes in a high-dimensional space (Pereira et al, 2009). The method of combining SVM and dALFF to analyze changes in brain activity in various diseases has been a research hotspot in recent years, such as comitant exotropia (Chen et al, 2022) and active thyroidassociated ophthalmopathy (Wen et al, 2023) and SVM has high accuracy in distinguishing patients from healthy populations. In the present study, we tested two hypotheses: (1) RD patients exhibit greater temporal variability compared with healthy controls (HCs); and (2) dALFF values are sensitive biomarkers that can distinguish RD patients from HCs.…”