Journal of Ophthalmic and Optometric Sciences
Volume:5 Issue: 2, Spring 2021

The present study aims to investigate the visual evoked potentials in patients with exotropia, a type of ocular deviation in which one or both eyes are deflected outwards.

Twenty-five patients with exotropia aged 6-8 years participated in this study as a case group, and twenty-five age- and sex-matched controls were selected as control. VEP was recorded using the Pattern Reversal checkerboard technique for all participants. Latency (msec) and amplitude (μV) of VEP, P100 peak were measured in both groups.

The mean amplitude of VEP, P100 peak was 2.92 and 7.84 μV in case and control groups, respectively, showing a statistically significant difference (P = 0.001). The difference in mean latency of the VEP, P100 peak was not statistically significant between the two groups (P = 0.45).

Exotropia is a visual disturbance that affects visual evoked potential P100 peak amplitude, whereas the latency of P100 remains intact.

Age-related macular degeneration (AMD) is the progressive degenerative disease of the macula and the main cause of blindness in older adults. Various risk factors have been associated with disease progression among different individuals.AMD is affected by different risk factors such as aging, genetic susceptibility, environmental risk factors and lifestyle. Since the etiology of AMD is not fully known, it would be essential to identify disease risk factors and novel predictive risk factors to detect AMD at an early stage.

The expression data were obtained from the Gene Expression Omnibus database. Samples were quantile normalized, and log2 transformed. Furthermore, outlier samples were removed by hierarchical clustering. R limma was used to run a linear model and identify differentially expressed genes (DEGs). As a result, 33 genes were discovered with a q-value less than 0.05 and a |log (FC)|≥0.7. With a machine learning (ML) approach, DEGs were applied to discriminate between the case and control samples. Furthermore, FeatureSelect is used to extract the most effective separator genes. Nine genes were identified as the best disease discriminator genes through 11 feature selection algorithms.

The gene set found in the study distinguishes healthy samples from patient samples with an accuracy of 87.5 %. We found DEF119B, UBD, and GRP to be three novel potential AMD candidate biomarkers using ML models and feature selection.

Machine learning can be beneficial in diagnosing, preventing and treating diseases, especially in diseases such as AMD that do not have a clear etiology.

Hypertensive Retinopathy (HR) is amongst the abnormalities occurred with high blood pressure. This high blood pressure level makes retinal arterial narrower, retinal hemorrhages and cotton wool spots more harmful. Based on what was mentioned, early detection of hypertensive retinopathy is pivotal to prevent its following disabilities and boost its treatment with more accurate methods.

The main objective of this study is to investigate an appropriate deep learning method for improving the automatic diagnosis of hypertensive retinopathy in its early stages. The complete data used in this study have been obtained from integration of Structured Analysis of the Retina (STARE) and The Digital Retinal Images for Vessel Extraction (DRIVE) datasets.

Interestingly, we reached an accuracy of 87.5 % after using the well-suited preprocessing method to integrate different images for further analysis by our designed convolutional neural network (CNN).

This model performs well with integration of two mentioned datasets.

Association of T2DM and OS disorders addresses a human eye metagenome drift. Despite the clarity of diabetic retinopathy, process of involvement of conjunctival sac microbiota is still ambiguous. We seek predictive value of OS microbiota using ML-based methods.

16S rRNA characterization of human eye metagenome for samples of 192 patients (with mean age of 66 years and 56 % females) with different onsets of T2DM is analyzed using various metrics including abundance and diversity indices and LDA at phyla, families, and genera levels. We took advantage of variance threshold, Chi-squared significance, and LDA Effect Size (LEfSe) feature selection strategies for inclusion of predictive families and genera in the T2DM prediction model. ML models with different algorithms including RF, GB, SVM, and ANN are implemented. Generalizability and robust performance of the models are also ensured using a 5-fold cross-validation process. DeLong’s test is also used to investigate different performance of the methods.

Microbiome analyses revealed that eye metagenome profiles of the patients with <15 years of T2DM history show significantly higher richness and diversity. ML model performance shows ROC-AUC of ~0.8. ML model with the superior performance exhibit sensitivity and accuracy of 0.86 and 0.68, respectively, in the prediction of T2DM occurrence.

significant correlation and co-occurrence of T2DM and eye microbiome dysbiosis is trackable and well-optimized ML-strategies can predict T2DM onsets based on the microbiome of conjunctival sac.

A traumatic cataract is a known consequence of both closed and open-eye injuries and can present as an early or a late sequel of the traumatic event. A variety of etiologies, including penetrating injuries, eye contusion, chemical burns, electric sparks, radiation, infrared, and or ultraviolet (UV) beam exposure, may lead to traumatic cataracts in different settings such as occupations, sports, entertainment ,and iatrogenic causes. The reduced transparency of the injured crystalline lens manifest with various patterns in the examination. Diagnosis of the traumatic cataract is often made by slit lamp biomicroscopy but would be more challenging in the presence of coexisting corneal haziness, hyphema, posterior synechia, anterior segment inflammation or fibrin reaction, in comparison with a routine cataract. In terms of management, the timing and the process of the surgical intervention should be tailored for each patient.

In the field of computer science, Artificial Intelligence can be considered one of the branches that study the development of algorithms that mimic certain aspects of human intelligence. Over the past few years, there has been a rapid advancement in the technology of computer-aided diagnosis (CAD). This in turn has led to an increase in the use of deep learning methods in a variety of applications. For us to be able to understand how AI can be used in order to recognize eye diseases, it is crucial that we have a deep understanding of how AI works in its core concepts. This paper aims to describe the most recent and applicable uses of artificial intelligence in the various fields of ophthalmology disease.

The visual evoked potential is one of the suitable techniques for the diagnosis of multiple sclerosis. There are two stimulation techniques, i.e., pattern reversal checkerboard and flash, to record visually evoked potential. Flash type of stimulation is used in patients with poor visual acuity. Here we report the VEP recording of a multiple sclerosis patients with two types of stimulation and an extraordinarily significant P100 peak latency difference observed between the two types of stimulation.