Clinical Relevance of Choroidal Thickness in Obese and Healthy Children: A Machine Learning Study
Erkan Bulut1, Sümeyra Köprübaşı2, Özlem Dayi3
1Gelişim University, Vocational School of Health Services, Department of Opticianry, İstanbul, Türkiye.
Insights
Obesity impacts children's choroidal thickness, particularly in the subfoveal and outer peripapillary regions. Machine learning algorithms like Random Forest and Support Vector Machine accurately classify obese children based on these measurements.
Area of Science:
- Ophthalmology
- Pediatrics
- Biomedical Engineering
Background:
- Childhood obesity is a growing public health concern.
- Obesity is associated with various systemic health issues, potentially affecting ocular structures.
- Understanding ocular changes in obese children is crucial for early detection and management.
Purpose of the Study:
- To investigate the effect of macular choroidal thickness (MCT) and peripapillary choroidal thickness (PPCT) on classifying obese versus healthy children.
- To compare the performance of Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) algorithms in this classification task.
Main Methods:
- Prospective comparative study involving 59 obese and 35 healthy children (aged 6-15 years).
- Optical coherence tomography (OCT) used to measure MCT and PPCT at various distances (500, 1000, 1500 μm) from the fovea and optic disc.
- Feature selection algorithms identified key differentiating features, followed by classification using RF, SVM, and MLP.
Main Results:
- The correlation feature selection algorithm yielded the best results.
- Key features for distinguishing groups included PPCT at temporal 500 μm and 1500 μm, nasal 1500 μm, inferior 1500 μm, and subfoveal MCT.
- Classification accuracies were: RF 98.6%, SVM 96.8%, and MLP 89%.
Conclusions:
- Obesity significantly affects choroidal thickness in children, especially in the subfoveal and outer peripapillary areas.
- RF and SVM algorithms demonstrate high accuracy and effectiveness in classifying obese children based on choroidal thickness measurements.
Objectives:
To analyze the effect of macular choroidal thickness (MCT) and peripapillary choroidal thickness (PPCT) on the classification of obese and healthy children by comparing the performance of the random forest (RF), support vector machine (SVM), and multilayer perceptrons (MLP) algorithms.
Materials And Methods:
Fifty-nine obese children and 35 healthy children aged 6 to 15 years were studied in this prospective comparative study using optical coherence tomography. MCT and PPCT were measured at distances of 500 μm, 1,000 μm, and 1,500 μm from the fovea and optic disc. Three different feature selection algorithms were used to determine the most prominent features of all extracted features. The classification efficiency of the extracted features was analyzed using the RF, SVM, and MLP algorithms, demonstrating their efficacy for distinguishing obese from healthy children. The precision and reliability of measurements were assessed using kappa analysis.
Results:
The correlation feature selection algorithm produced the most successful classification results among the different feature selection methods. The most prominent features for distinguishing the obese and healthy groups from each other were PPCT temporal 500 μm, PPCT temporal 1,500 μm, PPCT nasal 1,500 μm, PPCT inferior 1,500 μm, and subfoveal MCT. The classification rates for the RF, SVM, and MLP algorithms were 98.6%, 96.8%, and 89%, respectively.
Conclusion:
Obesity has an effect on the choroidal thicknesses of children, particularly in the subfoveal region and the outer semi-circle at 1,500 μm from the optic disc head. Both the RF and SVM algorithms are effective and accurate at classifying obese and healthy children.
More Related Videos
03:47Retinal and Choroidal Thickness Changes in Populations with Helicobacter pylori Infection by Swept-Source Optical Coherence Tomography
Published on: November 1, 2024
06:48Author Spotlight: Advancements in 3D Optical Imaging for Comprehensive Body Composition Assessment in Modern Research
Published on: June 7, 2024
