Interaction between diet and genetics in patients with inflammatory bowel disease

In this editorial,we comment on the article by Marangoni et al,published in the recent issue of the World Journal of Gastroenterology 2023;29:5618-5629,about“Diet as an epigenetic factor in inflammatory bowel disease”.The authors emphasized the role of diet,especially the interaction with genetics,in promoting the inflam-matory process in inflammatory bowel disease(IBD)patients,focusing on DNA methylation,histone modifications,and the influence of microRNAs.In this editorial,we explore the interaction between genetics,gut microbiota,and diet,in an only way.Furthermore,we provided dietary recommendations for patients with IBD.The Western diet,characterized by a low fiber content and deficiency the micronutrients,impacts short-chain fatty acids production and may be related to the pathogenesis of IBD.On the other hand,the consumption of the Mediter-ranean diet and dietary fibers are associated with reduced risk of IBD flares,particularly in Crohn’s disease(CD)patients.According to the dietary guidance from the International Organization for the Study of Inflammatory Bowel Diseases(IOIBD),the regular consumption of fruits and vegetables while reducing the consumption of saturated,trans,dairy fat,additives,processed foods rich in maltodextrins,and artificial sweeteners containing sucralose or saccharine is recommended to CD patients.For patients with ulcerative colitis,the IOIBD recommends the increased intake of natural sources of omega-3 fatty acids and follows the same restrictive recommendations aimed at CD patients,with the possible inclusion of red meats.In conclusion,IBD is a complex and hetero-geneous disease,and future studies are needed to elucidate the influence of epigenetics on diet and microbiota in IBD patients.

Artificial intelligence in individualized retinal disease management

Owing to the rapid development of modern computer technologies,artificial intelligence(AI)has emerged as an essential instrument for intelligent analysis across a range of fields.AI has been proven to be highly effective in ophthalmology,where it is frequently used for identifying,diagnosing,and typing retinal diseases.An increasing number of researchers have begun to comprehensively map patients’retinal diseases using AI,which has made individualized clinical prediction and treatment possible.These include prognostic improvement,risk prediction,progression assessment,and interventional therapies for retinal diseases.Researchers have used a range of input data methods to increase the accuracy and dependability of the results,including the use of tabular,textual,or image-based input data.They also combined the analyses of multiple types of input data.To give ophthalmologists access to precise,individualized,and high-quality treatment strategies that will further optimize treatment outcomes,this review summarizes the latest findings in AI research related to the prediction and guidance of clinical diagnosis and treatment of retinal diseases.

Retinal nerve fiber layer defects and chronic kidney disease:the Kailuan Eye Study

AIM:To investigate whether retinal nerve fiber layer defects(RNFLDs)is a potential risk factor for chronic kidney disease(CKD)in Chinese adults.METHODS:The Kailuan Eye Study was a populationbased study that included 14440 participants.All participants underwent detailed assessments,RNFLDs were diagnosed using color fundus photographs.RESULTS:Overall,12507 participants[8533 males(68.23%)]had complete systemic examination data and at least one evaluable fundus photograph.RNFLDs were found in 621 participants[5.0%;95%confidence interval(CI):4.6%-5.34%],and 70 cases of multiple RNFLDs were found(11.27%).After adjusting multiple factors,RNFLDs was significantly associated with CKD severity,the ORs of CKD stage 3,stage 4 and stage 5 were 1.698,4.167,and 9.512,respectively.Multiple RNFLDs were also associated with CKD severity after adjusting multiple factors,the ORs of CKD stage 3 and stage 5 were 4.465 and 11.833 respectively.Furthermore,2294 participants had CKD(18.34%,95%CI:17.68%-18.99%).After adjusting for other factors,CKD presence was significantly correlated with the presence of RNFLDs.CONCLUSION:The strongest risk factors for RNFLDs are CKD and hypertension.Conversely,RNFLDs can be an ocular feature in patients with CKD.Fundoscopy can help detect systemic diseases,and assessment for RNFLDs should be considered in CKD patients.

Retinal capillary plexus in Parkinson’s disease using optical coherence tomography angiography

AIM:To evaluate the alterations of the retinal microvasculature and foveal avascular zone in patients with Parkinson’s disease(PD)using optical coherence tomography angiography(OCT-A).METHODS:A retrospective study of PD patients examined in the Ophthalmology Department of the General Hospital of Athens,“Georgios Gennimatas”from March 2021 to March 2022 was conducted.Totally 44 patients with PD were included and 18 healthy controls were examined,hence a total of 124 eyes were enrolled in the study.The foveal and parafoveal superficial and deep capillary plexus vascular density(fSCP-VD,fDCP-VD,pSCP-VD,pDCP-CD)and foveal avascular zone(FAZ)were quantified with OCTA.Optical coherence tomography(OCT)was used to measure macular thickness.Our statistical analysis was conducted by using a mixed effect linear regression model.RESULTS:After adjustment for age and gender,the mean parafoveal superficial capillary plexus vascular density(pSCP-VD)and mean parafoveal deep capillary plexus vascular density(pDCP-VD)were significantly decreased in individuals with PD(P<0.001 in both)by-2.35(95%CI-3.3,-1.45)and-7.5(95%CI-10.4,-4.6)respectively.fSCP-VD and fDCP-VD didn’t approach statistical significance.The FAZ area and perimeter were significantly decreased(P<0.001 in both)by-0.1 mm^(2)(95%CI-0.13,-0.07)and-0.49 mm^(2)(95%CI-0.66,-0.32)respectively.Circularity didn’t approach statistical significance.Central retinal thickness(CRT)was significantly decreased in individuals with PD(P<0.001)by-23.1μm(95%CI-30.2,-16)and temporal retinal thickness(TRT)was decreased(P=0.025)by-11μm(95%CI-22,-1.5)while nasal retinal thickness(NRT)only approached statistical significance(P=0.066).CONCLUSION:The mean pSCP-VD,pDCP-VD,CRT and TRT are significantly decreased and FAZ is altered in individuals with PD.These findings can be potentially used as biomarkers for the diagnosis and evaluation of early PD.

Stem cell therapy in retinal diseases

Alteration of the outer retina leads to various diseases such as age-related macular degeneration or retinitis pigmentosa characterized by decreased visual acuity and ultimately blindness.Despite intensive research in the field of retinal disorders,there is currently no curative treatment.Several therapeutic approaches such as cell-based replacement and gene therapies are currently in development.In the context of cell-based therapies,different cell sources such as embryonic stem cells,induced pluripotent stem cells,or multipotent stem cells can be used for transplantation.In the vast majority of human clinical trials,retinal pigment epithelial cells and photoreceptors are the cell types considered for replacement cell therapies.In this review,we summarize the progress made in stem cell therapies ranging from the pre-clinical studies to clinical trials for retinal disease.

Automated Classification of Inherited Retinal Diseases in Optical Coherence Tomography Images Using Few-shot Learning

Objective To develop a few-shot learning(FSL) approach for classifying optical coherence tomography(OCT) images in patients with inherited retinal disorders(IRDs).Methods In this study, an FSL model based on a student–teacher learning framework was designed to classify images. 2,317 images from 189 participants were included. Of these, 1,126 images revealed IRDs, 533 were normal samples, and 658 were control samples.Results The FSL model achieved a total accuracy of 0.974–0.983, total sensitivity of 0.934–0.957, total specificity of 0.984–0.990, and total F1 score of 0.935–0.957, which were superior to the total accuracy of the baseline model of 0.943–0.954, total sensitivity of 0.866–0.886, total specificity of 0.962–0.971,and total F1 score of 0.859–0.885. The performance of most subclassifications also exhibited advantages. Moreover, the FSL model had a higher area under curves(AUC) of the receiver operating characteristic(ROC) curves in most subclassifications.Conclusion This study demonstrates the effective use of the FSL model for the classification of OCT images from patients with IRDs, normal, and control participants with a smaller volume of data. The general principle and similar network architectures can also be applied to other retinal diseases with a low prevalence.

Accuracy improvement for classifying retinal OCT images by diseases using deep learning-based selective denoising approach

In ophthalmology,retinal optical coherence tomography(OCT)images with noticeable structural features help identify human eyes as healthy or diseased.The recently hot arti ficial intelligence(AI)realized this recognition process automatically.However,speckle noise in the original retinal OCT image reduces the accuracy of disease classi fication.This study presents a timesaving approach based on deep learning to improve classi fication accuracy by removing the noise from the original dataset.Firstly,four pre-trained convolutional neural networks(CNNs)from the ImageNet Large Scale Visual Recognition Challenge(ILSVRC)were trained to classify the original images into two categories:The noise reduction required(NRR)and the noise-free(NF)images.Among the CNNs,VGG19 BN performed best with 98%accuracy and 99%recall.Then,we used the block-matching and 3D filtering(BM3D)algorithm to denoise the NRR images.Those noise-removed NRR and the NF images form the processed dataset.The quality of images in the dataset is prominently ameliorated after denoising,which is valid to improve the models'performance.The original and processed datasets were tested on the four pre-trained CNNs to evaluate the effectiveness of our proposed approach.We have compared the CNNs,and the results show the performance of the CNNs trained with the processed dataset is improved by an average of 2.04%,5.19%,and 5.10%under overall accuracy(OA),Macro F1-score,and Micro F1-score,respectively.Especially for DenseNet161,the OA is improved to 98.14%.Our proposed method demonstrates its effectiveness in improving classi fication accuracy and opens a new solution to reduce denoising time-consuming for large datasets.

Convolutional Neural Network-Based Classificationof Multiple Retinal Diseases Using Fundus Images

Use of deep learning algorithms for the investigation and analysis of medical images has emerged as a powerful technique.The increase in retinal dis-eases is alarming as it may lead to permanent blindness if left untreated.Automa-tion of the diagnosis process of retinal diseases not only assists ophthalmologists in correct decision-making but saves time also.Several researchers have worked on automated retinal disease classification but restricted either to hand-crafted fea-ture selection or binary classification.This paper presents a deep learning-based approach for the automated classification of multiple retinal diseases using fundus images.For this research,the data has been collected and combined from three distinct sources.The images are preprocessed for enhancing the details.Six layers of the convolutional neural network(CNN)are used for the automated feature extraction and classification of 20 retinal diseases.It is observed that the results are reliant on the number of classes.For binary classification(healthy vs.unhealthy),up to 100%accuracy has been achieved.When 16 classes are used(treating stages of a disease as a single class),93.3%accuracy,92%sensitivity and 93%specificity have been obtained respectively.For 20 classes(treating stages of the disease as separate classes),the accuracy,sensitivity and specificity have dropped to 92.4%,92%and 92%respectively.

Complications of Ziv-Aflibercept in Choroidal and Retinal Vascular Diseases

Introduction: The modern ophthalmology trends are changing rapidly every day with the introduction of much newer studies and research. Numerous anti-vascular endothelial growth factors (VEGF) are utilized as the mainstay in the treatment of intraocular vascular pathologies. The rationale of this study is to add to the literature regarding the safety and efficacy profile of the ziv-aflibercept as there is insubstantial data in patients with intraocular vascular pathologies being treated with this injection with prime focus on the complications of the injection. Materials and Methods: A prospective observational study was conducted at Opthalmology Department, Lahore General Hospital, Lahore between 14 August 2018 and 23 December 2019. Patients with choroidal and retinal vascular diseases like diabetic macular edema (DME), age-related macular degeneration (AMD) and retinal vein occlusion (RVO) who had no active infection of eye and had no history of myocardial infarction or cerebrovascular accident were added in this study. Results: Best-corrected visual acuity was significantly improved at 4, 8, and 12 weeks as compared to the baseline (p Conclusion: The use of ziv-aflibercept injection via intravitreal route under aseptic conditions for choroidal and retinal vascular diseases is effective as well as safe with mild and treatable ocular side effects.

Genome-edited rabbits:Unleashing the potential of a promising experimental animal model across diverse diseases

Animal models are extensively used in all aspects of biomedical research,with substantial contributions to our understanding of diseases,the development of pharmaceuticals,and the exploration of gene functions.The field of genome modification in rabbits has progressed slowly.However,recent advancements,particularly in CRISPR/Cas9-related technologies,have catalyzed the successful development of various genome-edited rabbit models to mimic diverse diseases,including cardiovascular disorders,immunodeficiencies,agingrelated ailments,neurological diseases,and ophthalmic pathologies.These models hold great promise in advancing biomedical research due to their closer physiological and biochemical resemblance to humans compared to mice.This review aims to summarize the novel gene-editing approaches currently available for rabbits and present the applications and prospects of such models in biomedicine,underscoring their impact and future potential in translational medicine.

Pyrroloquinoline quinone:a potential neuroprotective compound for neurodegenerative diseases targeting metabolism

Pyrroloquinoline quinone is a quinone described as a cofactor for many bacterial dehydrogenases and is reported to exert an effect on metabolism in mammalian cells/tissues.Pyrroloquinoline quinone is present in the diet being available in foodstuffs,conferring the potential of this compound to be supplemented by dietary administration.Pyrroloquinoline quinone’s nutritional role in mammalian health is supported by the extensive deficits in reproduction,growth,and immunity resulting from the dietary absence of pyrroloquinoline quinone,and as such,pyrroloquinoline quinone has been considered as a“new vitamin.”Although the classification of pyrroloquinoline quinone as a vitamin needs to be properly established,the wide range of benefits for health provided has been reported in many studies.In this respect,pyrroloquinoline quinone seems to be particularly involved in regulating cell signaling pathways that promote metabolic and mitochondrial processes in many experimental contexts,thus dictating the rationale to consider pyrroloquinoline quinone as a vital compound for mammalian life.Through the regulation of different metabolic mechanisms,pyrroloquinoline quinone may improve clinical deficits where dysfunctional metabolism and mitochondrial activity contribute to induce cell damage and death.Pyrroloquinoline quinone has been demonstrated to have neuroprotective properties in different experimental models of neurodegeneration,although the link between pyrroloquinoline quinone-promoted metabolism and improved neuronal viability in some of such contexts is still to be fully elucidated.Here,we review the general properties of pyrroloquinoline quinone and its capacity to modulate metabolic and mitochondrial mechanisms in physiological contexts.In addition,we analyze the neuroprotective properties of pyrroloquinoline quinone in different neurodegenerative conditions and consider future perspectives for pyrroloquinoline quinone’s potential in health and disease.

Genetic Variations and Nonalcoholic Fatty Liver Disease:Field Synopsis,Systematic Meta-Analysis,and Epidemiological Evidence

Objective To systematically summarize the published literature on the genetic variants associated with nonalcoholic fatty liver disease(NAFLD).Methods Literature from Web of Science,PubMed,and Embase between January 1980 and September 2022 was systematically searched.Meta-analyses of the genetic variants were conducted using at least five data sources.The epidemiologic credibility of the significant associations was graded using the Venice criteria.Results Based on literature screening,399 eligible studies were included,comprising 381 candidate gene association,16 genome-wide association,and 2 whole-exome sequencing studies.We identified 465 genetic variants in 173 genes in candidate gene association studies,and 25 genetic variants in 17 genes were included in the meta-analysis.The meta-analysis identified 11 variants in 10 genes that were significantly associated with NAFLD,with cumulative epidemiological evidence of an association graded as strong for two variants in two genes(HFE,TNF),moderate for four variants in three genes(TM6SF2,GCKR,and ADIPOQ),and weak for five variants in five genes(MBOAT7,PEMT,PNPLA3,LEPR,and MTHFR).Conclusion This study identified six variants in five genes that had moderate to strong evidence of an association with NAFLD,which may help understand the genetic architecture of NAFLD risk.

Indirubin alleviates retinal neurodegeneration through the regulation of PI3K/AKT signaling

Retinal neurodegenerative disease is a leading cause of blindness among the elderly in developed countries,including glaucoma,diabetic retinopathy,traumatic optic neuropathy and optic neuritis,etc.The current clinical treatment is not very effective.We investigated indirubin,one of the main bioactive components of the traditional Chinese medicine Danggui Longhui Pill,in the present study for its role in retinal neurodegeneration.Indirubin exhibited no detectable tissue toxicity in vivo or cytotoxicity in vitro.Moreover,indirubin improved visual function and ameliorated retinal neurodegeneration in mice after optic nerve crush injury in vivo.Furthermore,indirubin reduced the apoptosis of retinal ganglion cells induced by oxidative stress in vitro.In addition,indirubin significantly suppressed the increased production of intracellular reactive oxygen species and the decreased activity of superoxide dismutase induced by oxidative stress.Mechanically,indirubin played a neuroprotective role by regulating the PI3K/AKT/BAD/BCL-2 signaling.In conclusion,indirubin protected retinal ganglion cells from oxidative damage and alleviated retinal neurodegeneration induced by optic nerve crush injury.The present study provides a potential therapeutic medicine for retinal neurodegenerative diseases.

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.

Genetic risk stratification of inflammatory bowel disease-associated venous thromboembolism:An Asian perspective

The utilisation of polygenic scoring models may enhance the clinician’s ability to risk stratify an inflammatory bowel disease patient’s individual risk for venous thromboembolism(VTE)and guide the appropriate usage of VTE thromboprophylaxis,yet there is a need to validate such models in ethnically diverse populations.

N-acetylserotonin alleviates retinal ischemia-reperfusion injury via HMGB1/RAGE/NF-κB pathway in rats

AIM:To observe the effects of N-acetylserotonin(NAS)administration on retinal ischemia-reperfusion(RIR)injury in rats and explore the underlying mechanisms involving the high mobility group box 1(HMGB1)/receptor for advanced glycation end-products(RAGE)/nuclear factor-kappa B(NF-κB)signaling pathway.METHODS:A rat model of RIR was developed by increasing the pressure of the anterior chamber of the eye.Eighty male Sprague Dawley were randomly divided into five groups:sham group(n=8),RIR group(n=28),RIR+NAS group(n=28),RIR+FPS-ZM1 group(n=8)and RIR+NAS+FPS-ZM1 group(n=8).The therapeutic effects of NAS were examined by hematoxylin-eosin(H&E)staining,and retinal ganglion cells(RGCs)counting.The expression of interleukin 1 beta(IL-1β),HMGB1,RAGE,and nod-like receptor 3(NLRP3)proteins and the phosphorylation of nuclear factorkappa B(p-NF-κB)were analyzed by immunohistochemistry staining and Western blot analysis.The expression of HMGB1 protein was also detected by enzyme-linked immunosorbent assay(ELISA).RESULTS:H&E staining results showed that NAS significantly reduced retinal edema and increased the number of RGCs in RIR rats.With NAS therapy,the HMGB1 and RAGE expression decreased significantly,and the activation of the NF-κB/NLRP3 pathway was antagonized along with the inhibition of p-NF-κB and NLRP3 protein expression.Additionally,NAS exhibited an anti-inflammatory effect by reducing IL-1βexpression.The inhibitory of RAGE binding to HMGB1 by RAGE inhibitor FPS-ZM1 led to a significant decrease of p-NF-κB and NLRP3 expression,so as to the IL-1βexpression and retinal edema,accompanied by an increase of RGCs in RIR rats.CONCLUSION:NAS may exhibit a neuroprotective effect against RIR via the HMGB1/RAGE/NF-κB signaling pathway,which may be a useful therapeutic target for retinal disease.

Age-specific heterogeneity of genetic susceptibility to cardiovascular disease might have opposite outcomes depending on the presence of prediabetes

Examining age-specific heterogeneity of susceptibility to cardiovascular disease is also essential in individuals without prediabetes to determine its relative size and direction compared to those with prediabetes.Of particular interest,age-specific heterogeneity in genetic susceptibility may exhibit opposite directions depending on the presence or absence of prediabetes.

Integration between Genomic and Computational Statistical Surveys for the Screening of SNP Genetic Variants in Inflammatory Bowel Disease (IBD) Pediatric Patients*

Inflammatory bowel diseases (IBD) are complex multifactorial disorders that include Crohn’s disease (CD) and ulcerative colitis (UC). Considering that IBD is a genetic and multifactorial disease, we screened for the distribution dynamism of IBD pathogenic genetic variants (single nucleotide polymorphisms;SNPs) and risk factors in four (4) IBD pediatric patients, by integrating both clinical exome sequencing and computational statistical approaches, aiming to categorize IBD patients in CD and UC phenotype. To this end, we first aligned genomic read sequences of these IBD patients to hg19 human genome by using bowtie 2 package. Next, we performed genetic variant calling analysis in terms of single nucleotide polymorphism (SNP) for genes covered by at least 20 read genomic sequences. Finally, we checked for biological and genomic functions of genes exhibiting statistically significant genetic variant (SNPs) by introducing Fitcon genomic parameter. Findings showed Fitcon parameter as normalizing IBD patient’s population variability, as well as inducing a relative good clustering between IBD patients in terms of CD and UC phenotypes. Genomic analysis revealed a random distribution of risk factors and as well pathogenic SNPs genetic variants in the four IBD patient’s genome, claiming to be involved in: i) Metabolic disorders, ii) Autoimmune deficiencies;iii) Crohn’s disease pathways. Integration of genomic and computational statistical analysis supported a relative genetic variability regarding IBD patient population by processing IBD pathogenic SNP genetic variants as opposite to IBD risk factor variants. Interestingly, findings clearly allowed categorizing IBD patients in CD and UC phenotypes by applying Fitcon parameter in selecting IBD pathogenic genetic variants. Considering as a whole, the study suggested the efficiency of integrating clinical exome sequencing and computational statistical tools as a right approach in discriminating IBD phenotypes as well as improving inflammatory bowel disease (IBD) molecular diagnostic process.

Sickle cell retinopathy and systemic disease

Sickle cell disease(SCD)is a widespread hemoglobinopathy that results in significant patient morbidity and mortality.Vascular occlusion can cause acute pain,acute chest syndrome,and avascular necrosis,while hemolysis and endothelial disruption can cause ischemic stroke,leg ulcers,pulmonary hypertension,and priapism.All ocular and orbital structures can be affected by SCD ischemic events,including orbital bone infarction,ischemic optic neuropathy,retinal artery occlusion,hyphema,secondary glaucoma,sickle cell maculopathy,and sickle cell retinopathy.Proliferative sickle cell retinopathy(PSR)is the most common cause of vision loss.Untreated PSR can lead to macular ischemia,vitreous hemorrhage,and tractional retinal detachment.Ophthalmic screening exams and multimodal imaging can lead to earlier detection of sickle cell retinopathy and improved patient outcomes.SCD patients undergoing vitreoretinal surgery may require coordination of care with hematologists to avoid ischemic complications.While hydroxyurea was the only United States Food and Drug Administration approved treatment for several decades,patients with SCD now have several more treatment options.Despite the United States screening all infants for SCD,there can be delays in diagnosis and treatment.This review article aims to provide an overview of sickle disease for the ophthalmologist,and to discuss emerging treatment options and current management of SCD ocular complications.

Game Theory-Based Dynamic Weighted Ensemble for Retinal Disease Classification

An automated retinal disease detection system has long been in exis-tence and it provides a safe,no-contact and cost-effective solution for detecting this disease.This paper presents a game theory-based dynamic weighted ensem-ble of a feature extraction-based machine learning model and a deep transfer learning model for automatic retinal disease detection.The feature extraction-based machine learning model uses Gaussian kernel-based fuzzy rough sets for reduction of features,and XGBoost classifier for the classification.The transfer learning model uses VGG16 or ResNet50 or Inception-ResNet-v2.A novel ensemble classifier based on the game theory approach is proposed for the fusion of the outputs of the transfer learning model and the XGBoost classifier model.The ensemble approach significantly improves the accuracy of retinal disease pre-diction and results in an excellent performance when compared to the individual deep learning and feature-based models.