Machine Learning-Based Identification of Children With Intermittent Exotropia Using Multiple Resting-State Functional...

Area of Science:

• Neuroimaging
• Machine Learning
• Ophthalmology

Background:

• Intermittent exotropia (IXT) is a common childhood eye misalignment.
• Understanding the neurobiological underpinnings of IXT is crucial for diagnosis and treatment.
• Resting-state functional magnetic resonance imaging (rs-fMRI) offers insights into brain function.

Purpose of the Study:

• To evaluate the efficacy of machine learning (ML) models utilizing rs-fMRI parameters for differentiating children with IXT from healthy controls (HCs).
• To identify specific rs-fMRI parameters and brain regions that serve as potential biomarkers for IXT.

Main Methods:

• rs-fMRI data from 41 IXT children and 36 HCs were analyzed.
• Key parameters calculated include amplitude of low-frequency fluctuations (ALFF), fractional ALFF (fALFF) in slow-4/slow-5 bands, and regional homogeneity (ReHo).
• Machine learning classifiers and feature selection methods were employed, with ten-fold cross-validation for performance evaluation.

Main Results:

• ML models demonstrated good performance in distinguishing IXT from HCs.
• The slow-5 fALFF parameter yielded the best classification results.
• A linear regression classifier with ANOVA feature selection achieved high accuracy (0.957 training, 0.804 validation, 0.818 test AUC) using five key brain regions, including the right inferior parietal gyrus and left dorsolateral prefrontal cortex.

Conclusions:

• The linear regression model using slow-5 fALFF values from specific cortical regions is effective for distinguishing IXT children from HCs.
• Slow-5 fALFF shows potential as a neuroimaging biomarker for IXT.
• Brain regions involved in stereopsis, eye movement, and cognitive functions are implicated in the pathophysiology of IXT.