Epidemiology of eye diseases among children with disability in rural Bangladesh: a population-based cohort study

Anterior segment indices in mentally retarded children

To compare the anterior segment indices between mentally retarded and normal children. The current study was conducted as a cohort. In this study, 73 mentally retarded and 76 normal children were selected from normal school and special schools for mentally retarded children using random cluster sampling method. Mental retardation in children was confirmed by a psychologist. Optometry examinations including visual acuity and refraction were performed for all participants, and ultimately, corneal imaging measurements were taken by Pentacam. The mean age of mentally retarded and normal children was of 13.30 ± 1.83 and 13.05 ± 1.82 years, respectively (P = 0.180). A multiple generalized estimating equations model demonstrated that there is a significant association between central corneal thickness (CCT) (coef = 1.011, P < 0.001), corneal diameter (CD) (coef = 0.444, P = 0.046), anterior chamber depth (ACD) (coef = 0.23), P < 0.001) and index of vertical asymmetry (IVA) (coef = 0.12, P < 0.001) and mental retardation. Cerebral palsy children had higher keratoconus index (KI), central keratoconus index (CKI), index of height asymmetry(IHA), and index of height decentration (IHD) compared to those without cerebral palsy (P < 0.05). Children with moderate mental retardation had higher index of surface variance (ISV), IVA, IHA, and IHD than those with mild mental retardation (P < 0.05). The mean and standard deviation of CCT, CD, ACD and IVA index in mentally retarded children were 535.3 ± 46.68 micron, 11.87 ± 0.42 mm, 3.29 ± 0.24 mm and 0.25 ± 0.18 mm, respectively. These indices in the normal group were 525.53 ± 47.52 micron, 11.84 ± 0.38 mm, 3.15 ± 0.28 mm and 0.17 ± 0.05 mm, respectively. The findings of this study showed that some anterior segment indices were different in mentally retarded compared to normal children. Moreover, some keratoconus indicators were worse in cerebral palsy children and children with higher grade mental retardation. So, it is important to consider keratoconus screening in these children.

An Efficient Approach to Predict Eye Diseases from Symptoms Using Machine Learning and Ranker-Based Feature Selection Methods

The eye is generally considered to be the most important sensory organ of humans. Diseases and other degenerative conditions of the eye are therefore of great concern as they affect the function of this vital organ. With proper early diagnosis by experts and with optimal use of medicines and surgical techniques, these diseases or conditions can in many cases be either cured or greatly mitigated. Experts that perform the diagnosis are in high demand and their services are expensive, hence the appropriate identification of the cause of vision problems is either postponed or not done at all such that corrective measures are either not done or done too late. An efficient model to predict eye diseases using machine learning (ML) and ranker-based feature selection (r-FS) methods is therefore proposed which will aid in obtaining a correct diagnosis. The aim of this model is to automatically predict one or more of five common eye diseases namely, Cataracts (CT), Acute Angle-Closure Glaucoma (AACG), Primary Congenital Glaucoma (PCG), Exophthalmos or Bulging Eyes (BE) and Ocular Hypertension (OH). We have used efficient data collection methods, data annotations by professional ophthalmologists, applied five different feature selection methods, two types of data splitting techniques (train-test and stratified k-fold cross validation), and applied nine ML methods for the overall prediction approach. While applying ML methods, we have chosen suitable classic ML methods, such as Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), AdaBoost (AB), Logistic Regression (LR), k-Nearest Neighbour (k-NN), Bagging (Bg), Boosting (BS) and Support Vector Machine (SVM). We have performed a symptomatic analysis of the prominent symptoms of each of the five eye diseases. The results of the analysis and comparison between methods are shown separately. While comparing the methods, we have adopted traditional performance indices, such as accuracy, precision, sensitivity, F1-Score, etc. Finally, SVM outperformed other models obtaining the highest accuracy of 99.11% for 10-fold cross-validation and LR obtained 98.58% for the split ratio of 80:20.