Impaired interhemispheric synchrony in patients with iridocyclitis and classification using machine learning: an fMRI...

Area of Science:

• Neuroscience
• Ophthalmology
• Medical Imaging

Background:

• Iridocyclitis is associated with vision loss and cognitive dysfunction.
• Understanding the underlying pathophysiological mechanisms is crucial for effective intervention.
• Interhemispheric integration patterns in iridocyclitis remain underexplored.

Purpose of the Study:

• To examine interhemispheric integration patterns in iridocyclitis patients using voxel-mirrored homotopic connectivity (VMHC).
• To assess the potential of VMHC to differentiate iridocyclitis patients from healthy controls (HCs).
• To explore the utility of VMHC as an objective biomarker for early diagnosis and intervention.

Main Methods:

• Resting-state functional magnetic resonance imaging (fMRI) was performed on 26 iridocyclitis patients and 26 matched HCs.
• Voxel-mirrored homotopic connectivity (VMHC) technique was employed to analyze interhemispheric functional connectivity.
• A support vector machine (SVM) classifier was used to evaluate the diagnostic efficacy of VMHC features.

Main Results:

• Iridocyclitis patients showed significantly reduced VMHC in bilateral inferior temporal gyrus, calcarine, middle temporal gyrus, and precuneus compared to HCs.
• VMHC features effectively classified iridocyclitis patients from HCs with an AUC of 0.74 and accuracy of 0.673.
• Correlation analyses investigated associations between VMHC values and clinical features.

Conclusions:

• Disrupted interhemispheric functional organization is evident in iridocyclitis.
• VMHC analysis shows potential as an objective biomarker for iridocyclitis diagnosis.
• Machine learning approaches can aid in addressing diagnostic heterogeneity in ophthalmology.