According to the results of the current study, which compared obese children to a healthy control group, obesity had an effect on choroidal thickness at distinct measurement points, but not at all measurement points. Obesity-related metabolic alterations have an effect on the choriocapillaries, particularly in the subfoveal region and the outer semi-circle at 1500 µm from optic disc head. This research is noteworthy because it is not only evaluating MCT and PPCT in obese children, but it also utilizes machine learning algorithms in their analysis.
There are only a few studies in the literature that assess the impact of childhood obesity on ocular structures. Baran et al. [26] found that obese children had higher IOP and lower RNFLT than healthy children. They reported that childhood obesity may contribute to the development of glaucoma. They assessed choroidal thickness in the central subfoveal region alone and discovered no statistically significant differences. However, they did not conduct a comprehensive evaluation of MCT and PPCT. Bulus et al. [27] discovered that obese children have thicker MCT than healthy children, but did not evaluate PPCT. Additionally, they also used the BMI standard deviation score, which is equal to the BMIZ for childhood nutrition and growth classification reported by the World Health Organization in 2006. Buluş et al. reported that there was a strong positive correlation between BMI standard deviation score and subfoveal MCT. Consistent with this study, we found that subfoveal MCT is affected by obesity and is a distinguishing feature between the obese and control groups.
While there are several literature studies assessing the MCT in various diseases, there are few studies evaluating the PPCT. Read et al. [28] identified normal PPCT values and variations in healthy children and confirmed that myopic refractive errors cause thinning in PPCT. Ozcimen et al. [29] documented thinning in both PPCT and MCT in chronic obstructive pulmonary diseases. He claimed that choroidal thinning is caused by vascular resistance due to hypoxia. Koma et al. [30] evaluated PPCT and subfoveal choroidal thickness in healthy and glaucoma subjects using spectral domain OCT and swept source OCT. She discovered that choroidal thickness was significantly thicker in glaucoma subjects than in controls in the peripapillary region, but not in the macular region, using swept source OCT.
This is the first research that we are aware of that evaluates PPCT in childhood obesity. Furthermore, conventional statistical methods have been employed in previous studies, including the choroidal evaluation of various disorders. There is no prior study in the current literature that evaluates both MCT and PPCT by using machine learning algorithms.
In machine learning, feature selection helps boost classification efficiency by avoiding over-fitting, creating a time-saving model, and making the designed model more human-friendly. There are several feature selection approaches in the literature to minimize the number of features for classification purposes. Different subsets can be created with each feature selection method. We ran all of the data through a feature selection process using three different algorithms: VR, CFS, and PCA. None of the parameters associated with MCT and PPCT were excluded in any of the three analyses, and they were found to be distinctive in all of them. According to the results, obese and healthy children have significantly different choroidal thicknesses at specific measurement points. These measurement points were PPCT temporal 500 µm, PPCT temporal 1500 µm, PPCT nasal 1500 µm, PPCT inferior 1500 µm, and subfovealregions. The spherical equivalent value was chosen in the PCA algorithm in addition to the distinguishing features chosen in the CFS algorithm. There was no statistically significant difference between the two groups' spherical equivalent values (p > 0.05). The CFS algorithm outperforms PCA in classification because of the spherical equivalent value is not a distinguishing feature for these groups. While machine learning algorithms identify distinct features in classification for the two groups, they do not show the relative value of these features in each group. Due to the fact that machine learning algorithms reveal the importance of features, classification is performed on all of the selected features.
In this study, the results of three different classification algorithms, which included RF, SVM, and MLP were compared. Because it is difficult to predict which machine learning algorithm will perform better in classification. We selected RF because it is a good comparison and classification technique and can very well detect outliers. SVM is a very robust technique for solving high-dimensional problems and creating accurate classifications. MLP is an attainable technique with the ability to create a simple architecture, easily build it and quickly calculate the model. The risk of being introduced into the local extremum, weak overfitting skills, a lack of theoretically-based rigid design programs, and difficulty managing the training program are disadvantages of the MLP algorithm. SVM may be more determinant in some cases, even though the RF algorithm is generally more successful in classification. Due to the limited and unbalanced datasets used in this study, we encountered some difficulties when implementing SVM and MLP algorithms. To overcome this challenging situation, we focused on kernel selection, which had an effect on the kernel's success in implementing the SVM algorithm. We used polynomial and radial base kernels to improve classification efficiency by reducing our margin of error. Additionally, the MLP algorithm's success was influenced by the network structure. The more complicated the network's structure, the more successful it will be. However, we did not increase the number of layers in order to reduce the margin of error.
While RF produces better results against outliers and noise than SVM, it is not as successful in handling the dataset imbalance problem. Although our dataset was slightly unbalanced, the results with RF were quite successful. MLP was found to be less successful than SVM and RF in the classification according to the choroidal thickness.
The MLP algorithm had the highest rate of misclassification of all of the other classification techniques. The MLP algorithm misclassified the ten samples. At the same time, three of them were also misclassified by the SVM algorithm. We found no similarities in terms of features such as height or weight in cases misclassified by the MLP algorithm. In terms of group classification, we discovered that the SVM algorithm outperforms the MLP algorithm. The main reason for misclassification based on the SVM algorithm is that they were at the limit of obesity according to the BMIZ value (respectively 2,01 and 2,02). As a result, classification success of SVM algorithm is higher in obese cases with a high BMIZ value.
The performance of machine learning algorithms, as well as the complexity of the models used, are influenced by the quality and quantity of data. To the best of our knowledge, there is no open dataset in the literature that is comparable to our dataset. The drawback of our analysis is the limited size of the dataset. However, the majority of medical research faces difficulty in achieving a sufficient number of cases. Obtaining large quantities of high-quality data for medical research is a time-consuming and difficult task. There are medical research in the literature that use machine learning algorithms with small number of datasets. Hidalgo et al. [31] used machine learning algorithms to classify keratoconus using 5 Pentacam-derived parameters of 131 eyes. An et al. [32] developed classification criteria that could aid in the clinical management of glaucoma by using machine learning algorithms to classify 163 glaucomatous optic discs. Cartes et al. [33] evaluated the variability of tear osmolarity in 20 patients with dry eye using machine learning techniques. It has been demonstrated that machine learning algorithms can conduct self-diagnosis and classification analyses of OCT images with high accuracy, speed, and consistency [34]. However, in the classification tests, we measured Kappa values to ensure that the small dataset did not affect the reliability of our results and to maximize success. The Kappa value is a measure that contrasts the observed precision with the predicted precision (random chance). This is a far more reflective indicator of model efficiency. Kappa values were measured as 97.71%, 93.05%, and 76% for the RF, SVM, and MLP analyses, respectively. According to the Kappa statistics, RF is the most accurate test, but the reliability of SVM is also very similar to RF. Despite the limited number of datasets, Kappa analyses showed that both RF and SVM were very successful and reliable in the classification of obese and healthy children.