Related Experiment Video
Updated: May 16, 2025
Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
Published on: September 20, 2024
Machine Learning-Based Identification of Children With Intermittent Exotropia Using Multiple Resting-State Functional
Mengdi Zhou1, Huixin Li2, Xiaoxia Qu1
1Department of Radiology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
Insights
Machine learning models using resting-state fMRI data effectively distinguish children with intermittent exotropia (IXT) from healthy controls. The slow-5 fractional amplitude of low-frequency fluctuations (fALFF) parameter shows promise as a biomarker for IXT.
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.
Objective:
To investigate the performance of machine learning (ML) methods based on resting-state functional magnetic resonance imaging (rs-fMRI) parameters in distinguishing children with intermittent exotropia (IXT) from healthy controls (HCs).
Method:
Forty-one IXT children and 36 HCs were recruited. The amplitude of low-frequency fluctuations (ALFF), fractional ALFF (fALFF) in the slow-4 and slow-5 bands, and regional homogeneity (ReHo) were calculated. The 360 cortical areas of the Human Connectome Project multimodal parcellation atlas (HCP-MMP 1.0 atlas) were chosen as 360 regions of interest (ROIs). Each rs-fMRI parameter value of one ROI was taken as a feature. The Pearson correlation coefficient (PCC) was performed to reduce dimensions. We used four feature selection methods and nine classifiers. The ten-fold cross-validation was applied to evaluate the results.
Results:
The ML methods combined with rs-fMRI parameters had good classification performance in distinguishing IXT children from HCs, with the slow-5 fALFF parameter showing the best classification performance. The linear regression (LR) classifier with analysis of variance (ANOVA) feature selection achieved the highest area under the receiver operator characteristic curve values (0.957, 0.804, and 0.818 for the training, validation, and test datasets, respectively) using five features, including the slow-5 fALFF values of the right inferior parietal gyrus (IPG), right supplementary motor area (SMA), left primary somatosensory complex, right frontal opercula, and left dorsolateral prefrontal cortex (DLPFC), and the accuracy, sensitivity, and specificity values were 0.759, 0.759, and 0.760, respectively. The brain regions showing the greatest discriminative power included right IPG, right SMA, left primary somatosensory complex, right frontal opercula, left DLPFC, right posterior orbitofrontal cortex (pOFC), left medial superior temporal (MST), left parieto-occipital sulcus (POS), and right anterior ventral insula.
Conclusion:
Based on the slow-5 fALFF values of the five cortices as the features, LR with ANOVA was the best ML model for distinguishing between IXT children and HCs. The result indicates the slow-5 fALFF parameter has the potential to serve as a biomarker for distinguishing IXT children from HCs. In addition, brain regions related to stereopsis, eye movement, and higher-order cognitive functions play an important role in the neuropathologic mechanisms underlying IXT.
