Interconnections between diabetic corneal neuropathy and diabetic retinopathy:diagnostic and therapeutic implications

Diabetic corneal neuropathy and diabetic retinopathy are ocular complications occurring in the context of diabetes mellitus.Diabetic corneal neuropathy refers to the progressive damage of corneal nerves.Diabetic retinopathy has traditionally been considered as damage to the retinal microvasculature.However,growing evidence suggests that diabetic retinopathy is a complex neurovascular disorder resulting from dysfunction of the neurovascular unit,which includes both the retinal vascular structures and neural tissues.Diabetic retinopathy is one of the leading causes of blindness and is frequently screened for as part of diabetic ocular screening.However,diabetic corneal neuropathy is commonly overlooked and underdiagnosed,leading to severe ocular surface impairment.Several studies have found that these two conditions tend to occur together,and they share similarities in their pathogenesis pathways,being triggered by a status of chronic hyperglycemia.This review aims to discuss the interconnection between diabetic corneal neuropathy and diabetic retinopathy,whether diabetic corneal neuropathy precedes diabetic retinopathy,as well as the relation between the stage of diabetic retinopathy and the severity of corneal neuropathy.We also endeavor to explore the relevance of a corneal screening in diabetic eyes and the possibility of using corneal nerve measurements to monitor the progression of diabetic retinopathy.

Revolutionizing diabetic retinopathy screening and management:The role of artificial intelligence and machine learning

Diabetic retinopathy(DR)remains a leading cause of vision impairment and blindness among individuals with diabetes,necessitating innovative approaches to screening and management.This editorial explores the transformative potential of artificial intelligence(AI)and machine learning(ML)in revolutionizing DR care.AI and ML technologies have demonstrated remarkable advancements in enhancing the accuracy,efficiency,and accessibility of DR screening,helping to overcome barriers to early detection.These technologies leverage vast datasets to identify patterns and predict disease progression with unprecedented precision,enabling clinicians to make more informed decisions.Furthermore,AI-driven solutions hold promise in personalizing management strategies for DR,incorpo-rating predictive analytics to tailor interventions and optimize treatment path-ways.By automating routine tasks,AI can reduce the burden on healthcare providers,allowing for a more focused allocation of resources towards complex patient care.This review aims to evaluate the current advancements and applic-ations of AI and ML in DR screening,and to discuss the potential of these techno-logies in developing personalized management strategies,ultimately aiming to improve patient outcomes and reduce the global burden of DR.The integration of AI and ML in DR care represents a paradigm shift,offering a glimpse into the future of ophthalmic healthcare.

Advancements in diabetic retinopathy:Insights and future directions

This editorial discusses recent advancements and ongoing challenges in diabetic retinopathy,as reviewed by Morya et al in their comprehensive analysis.In their review,Morya et al discussed the pathophysiology of diabetic retinopathy and explored novel treatment modalities.This editorial highlights the importance of these advancements and emphasizes the need for continued research and innovation for the enhanced management of diabetic retinopathy.It also reflects upon the implications of the authors’review findings for clinical practice and future research directions,underscoring the potential of emerging therapies for improving patient outcomes and providing a deeper understanding of disease mechanisms.

Diabetic retinopathy identification based on multi-sourcefree domain adaptation

AIM:To address the challenges of data labeling difficulties,data privacy,and necessary large amount of labeled data for deep learning methods in diabetic retinopathy(DR)identification,the aim of this study is to develop a source-free domain adaptation(SFDA)method for efficient and effective DR identification from unlabeled data.METHODS:A multi-SFDA method was proposed for DR identification.This method integrates multiple source models,which are trained from the same source domain,to generate synthetic pseudo labels for the unlabeled target domain.Besides,a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances.Validation is performed using three color fundus photograph datasets(APTOS2019,DDR,and EyePACS).RESULTS:The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks.It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains.CONCLUSION:The multi-SFDA method provides an effective approach to overcome the challenges in DR identification.The method not only addresses difficulties in data labeling and privacy issues,but also reduces the need for large amounts of labeled data required by deep learning methods,making it a practical tool for early detection and preservation of vision in diabetic patients.

Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

Enhancing the outcomes of diabetic vitrectomy with pharmacological adjuvants

This editorial offers insights from a minireview by Venkatesh et al,who explored pharmacological adjuvants for diabetic vitrectomy.Specifically,they synthesized current knowledge and evaluated the efficacy of various adjunctive therapies in improving the outcomes of diabetic retinopathy and managing associated complications.Herein,we highlight the key roles of pharmacological adjuvants in optimizing surgical techniques,minimizing intraoperative challenges,and enhancing postoperative recovery.We further discuss the potential implications of this approach for clinical practice and future research directions in this evolving field.Overall,this editorial underscores the importance of incorporating pharmacological adjuvants into standard diabetic vitrectomy care to improve surgical outcomes and thus patients’quality of life.

DeepSVDNet:A Deep Learning-Based Approach for Detecting and Classifying Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

Artificial Intelligence(AI)is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy(VTDR),which is a leading cause of visual impairment and blindness worldwide.However,previous automated VTDR detection methods have mainly relied on manual feature extraction and classification,leading to errors.This paper proposes a novel VTDR detection and classification model that combines different models through majority voting.Our proposed methodology involves preprocessing,data augmentation,feature extraction,and classification stages.We use a hybrid convolutional neural network-singular value decomposition(CNN-SVD)model for feature extraction and selection and an improved SVM-RBF with a Decision Tree(DT)and K-Nearest Neighbor(KNN)for classification.We tested our model on the IDRiD dataset and achieved an accuracy of 98.06%,a sensitivity of 83.67%,and a specificity of 100%for DR detection and evaluation tests,respectively.Our proposed approach outperforms baseline techniques and provides a more robust and accurate method for VTDR detection.

Non-linear relationship between age and subfoveal choroidal thickness in Chinese patients with proliferative diabetic retinopathy

BACKGROUND No study has investigated the change regularity between age and subfoveal choroidal thickness(SFCT)in proliferative diabetic retinopathy(PDR).AIM To investigate the relationship between the SFCT and age in Chinese patients with PDR.METHODS This was a cross-sectional retrospective study.The participants were hospitalized individuals with type 2 diabetes who underwent vitrectomy for PDR.Contralateral eyes that met the criteria were included in the study.All necessary laboratory tests were performed at the time of admission.Central macular thickness(CMT)and SFCT were two quantitative assessments made using enhanced depth imaging optical coherence tomography.CMT was measured automatically and SFCT was measured manually with digital calipers provided by the Heidelberg Eye Explorer software.RESULTS The final analysis included a total of 234 individuals with PDR.The average age was 55.60 years old±10.03 years old,and 57.69%of the population was male.Univariate analysis revealed a significant negative connection between age and SFCT in patients with PDR[β=-2.44,95%confidence interval(95%CI):-3.46 to-1.42;P<0.0001].In the fully adjusted model,the correlation between SFCT and age remained steady(β=-1.68,95%CI:-2.97 to-0.39;P=0.0117).Spline smoothing showed that the relationship between SFCT and age in patients with PDR was non-linear,with an inflection point at 54 years of age.CONCLUSION Our findings suggest that age is a key determinant of choroidal thickness.The non-linear link between SFCT and age in PDR patients should be taken into account.

Application of non-mydriatic fundus photography-assisted telemedicine in diabetic retinopathy screening

BACKGROUND Early screening and accurate staging of diabetic retinopathy(DR)can reduce blindness risk in type 2 diabetes patients.DR’s complex pathogenesis involves many factors,making ophthalmologist screening alone insufficient for prevention and treatment.Often,endocrinologists are the first to see diabetic patients and thus should screen for retinopathy for early intervention.AIM To explore the efficacy of non-mydriatic fundus photography(NMFP)-enhanced telemedicine in assessing DR and its various stages.METHODS This retrospective study incorporated findings from an analysis of 93 diabetic patients,examining both NMFP-assisted telemedicine and fundus fluorescein angiography(FFA).It focused on assessing the concordance in DR detection between these two methodologies.Additionally,receiver operating characteristic(ROC)curves were generated to determine the optimal sensitivity and specificity of NMFP-assisted telemedicine,using FFA outcomes as the standard benchmark.RESULTS In the context of DR diagnosis and staging,the kappa coefficients for NMFPassisted telemedicine and FFA were recorded at 0.775 and 0.689 respectively,indicating substantial intermethod agreement.Moreover,the NMFP-assisted telemedicine’s predictive accuracy for positive FFA outcomes,as denoted by the area under the ROC curve,was remarkably high at 0.955,within a confidence interval of 0.914 to 0.995 and a statistically significant P-value of less than 0.001.This predictive model exhibited a specificity of 100%,a sensitivity of 90.9%,and a Youden index of 0.909.CONCLUSION NMFP-assisted telemedicine represents a pragmatic,objective,and precise modality for fundus examination,particularly applicable in the context of endocrinology inpatient care and primary healthcare settings for diabetic patients.Its implementation in these scenarios is of paramount significance,enhancing the clinical accuracy in the diagnosis and therapeutic management of DR.This methodology not only streamlines patient evaluation but also contributes substantially to the optimization of clinical outcomes in DR management.

Diabetic retinopathy:A review on its pathophysiology and novel treatment modalities

Diabetes mellitus(DM)is a chronic metabolic non-communicable disease with the ability to cause serious microvascular and macrovascular complications throughout the body,including in the eye.Diabetic retinopathy(DR),present in onethird of patients with diabetes,is a vision-threatening complication caused by uncontrolled diabetes,which greatly affects the retinal blood vessels and the lightsensitive inner retina,eventually leading to blindness.Several epidemiological studies elucidate that DR can vary by age of onset,duration,types of diabetes,and ethnicity.Recent studies show that the pathogenesis of diabetic retinopathy has spread its roots beyond merely being the result of hyperglycemia.The complexity of its etiopathology and diagnosis makes therapeutic intervention challenging.This review throws light on the pathological processes behind DR,the cascade of events that follow it,as well as the available and emerging treatment options.

Diabetic peripheral neuropathy and neuromodulation techniques:a systematic review of progress and prospects

Neuromodulation for diabetic peripheral neuropathy represents a significant area of interest in the management of chronic pain associated with this condition.Diabetic peripheral neuropathy,a common complication of diabetes,is characterized by nerve damage due to high blood sugar levels that lead to symptoms,such as pain,tingling,and numbness,primarily in the hands and feet.The aim of this systematic review was to evaluate the efficacy of neuromodulatory techniques as potential therapeutic interventions for patients with diabetic peripheral neuropathy,while also examining recent developments in this domain.The investigation encompassed an array of neuromodulation methods,including frequency rhythmic electrical modulated systems,dorsal root ganglion stimulation,and spinal cord stimulation.This systematic review suggests that neuromodulatory techniques may be useful in the treatment of diabetic peripheral neuropathy.Understanding the advantages of these treatments will enable physicians and other healthcare providers to offer additional options for patients with symptoms refractory to standard pharmacologic treatments.Through these efforts,we may improve quality of life and increase functional capacity in patients suffering from complications related to diabetic neuropathy.

Gut microbiota induced abnormal amino acids and their correlation with diabetic retinopathy

AIM:To explore the correlation of gut microbiota and the metabolites with the progression of diabetic retinopathy(DR)and provide a novel strategy to elucidate the pathological mechanism of DR.METHODS:The fecal samples from 32 type 2 diabetes patients with proliferative retinopathy(PDR),23 with nonproliferative retinopathy(NPDR),27 without retinopathy(DM),and 29 from the sex-,age-and BMI-matched healthy controls(29 HC)were analyzed by 16S rDNA gene sequencing.Sixty fecal samples from PDR,DM,and HC groups were assayed by untargeted metabolomics.Fecal metabolites were measured using liquid chromatographymass spectrometry(LC-MS)analysis.Associations between gut microbiota and fecal metabolites were analyzed.RESULTS:A cluster of 2 microbiome and 12 metabolites accompanied with the severity of DR,and the close correlation of the disease progression with PDR-related microbiome and metabolites were found.To be specific,the structure of gut microbiota differed in four groups.Diversity and richness of gut microbiota were significantly lower in PDR and NPDR groups,than those in DM and HC groups.A cluster of microbiome enriched in PDR group,including Pseudomonas,Ruminococcaceae-UCG-002,Ruminococcaceae-UCG-005,Christensenellaceae-R-7,was observed.Functional analysis showed that the glucose and nicotinate degradations were significantly higher in PDR group than those in HC group.Arginine,serine,ornithine,and arachidonic acid were significantly enriched in PDR group,while proline was enriched in HC group.Functional analysis illustrated that arginine biosynthesis,lysine degradation,histidine catabolism,central carbon catabolism in cancer,D-arginine and D-ornithine catabolism were elevated in PDR group.Correlation analysis revealed that Ruminococcaceae-UCG-002 and Christensenellaceae-R-7 were positively associated with L-arginine,ornithine levels in fecal samples.CONCLUSION:This study elaborates the different microbiota structure in the gut from four groups.The relative abundance of Ruminococcaceae-UCG-002 and Parabacteroides are associated with the severity of DR.Amino acid and fatty acid catabolism is especially disordered in PDR group.This may help provide a novel diagnostic parameter for DR,especially PDR.

On implications of somatostatin in diabetic retinopathy

Somatostatin,a naturally produced neuroprotective peptide,depresses excitatory neurotransmission and exerts anti-proliferative and anti-inflammatory effects on the retina.In this review,we summarize the progress of somatostatin treatment of diabetic retinopathy through analysis of relevant studies published from February 2019 to February 2023 extracted from the PubMed and Google Scholar databases.Insufficient neuroprotection,which occurs as a consequence of declined expression or dysregulation of retinal somatostatin in the very early stages of diabetic retinopathy,triggers retinal neurovascular unit impairment and microvascular damage.Somatostatin replacement is a promising treatment for retinal neurodegeneration in diabetic retinopathy.Numerous pre-clinical and clinical trials of somatostatin analog treatment for early diabetic retinopathy have been initiated.In one such trial(EUROCONDOR),topical administration of somatostatin was found to exert neuroprotective effects in patients with pre-existing retinal neurodysfunction,but had no impact on the onset of diabetic retinopathy.Overall,we concluded that somatostatin restoration may be especially beneficial for the growing population of patients with early-stage retinopathy.In order to achieve early prevention of diabetic retinopathy initiation,and thereby salvage visual function before the appearance of moderate non-proliferative diabetic retinopathy,several issues need to be addressed.These include the needs to:a)update and standardize the retinal screening scheme to incorporate the detection of early neurodegeneration,b)identify patient subgroups who would benefit from somatostatin analog supplementation,c)elucidate the interactions of somatostatin,particularly exogenously-delivered somatostatin analogs,with other retinal peptides in the context of hyperglycemia,and d)design safe,feasible,low cost,and effective administration routes.

Diabetic Retinopathy Detection: A Hybrid Intelligent Approach

Diabetes is a serious health condition that can cause several issues in human body organs such as the heart and kidney as well as a serious eye disease called diabetic retinopathy(DR).Early detection and treatment are crucial to prevent complete blindness or partial vision loss.Traditional detection methods,which involve ophthalmologists examining retinal fundus images,are subjective,expensive,and time-consuming.Therefore,this study employs artificial intelligence(AI)technology to perform faster and more accurate binary classifications and determine the presence of DR.In this regard,we employed three promising machine learning models namely,support vector machine(SVM),k-nearest neighbors(KNN),and Histogram Gradient Boosting(HGB),after carefully selecting features using transfer learning on the fundus images of the Asia Pacific Tele-Ophthalmology Society(APTOS)(a standard dataset),which includes 3662 images and originally categorized DR into five levels,now simplified to a binary format:No DR and DR(Classes 1-4).The results demonstrate that the SVM model outperformed the other approaches in the literature with the same dataset,achieving an excellent accuracy of 96.9%,compared to 95.6%for both the KNN and HGB models.This approach is evaluated by medical health professionals and offers a valuable pathway for the early detection of DR and can be successfully employed as a clinical decision support system.

Automatic diagnosis of diabetic retinopathy using vision transformer based on wide-field optical coherence tomography angiography

Diabetic retinopathy(DR)is one of the major causes of visual impairment in adults with diabetes.Optical coherence tomography angiography(OCTA)is nowadays widely used as the golden criterion for diagnosing DR.Recently,wide-field OCTA(WF-OCTA)provided more abundant information including that of the peripheral retinal degenerative changes and it can contribute in accurately diagnosing DR.The need for an automatic DR diagnostic system based on WF-OCTA pictures attracts more and more attention due to the large diabetic population and the prevalence of retinopathy cases.In this study,automatic diagnosis of DR using vision transformer was performed using WF-OCTA images(12 mm×12 mm single-scan)centered on the fovea as the dataset.WF-OCTA images were automatically classified into four classes:No DR,mild nonproliferative diabetic retinopathy(NPDR),moderate to severe NPDR,and proliferative diabetic retinopathy(PDR).The proposed method for detecting DR on the test set achieves accuracy of 99.55%,sensitivity of 99.49%,and specificity of 99.57%.The accuracy of the method for DR staging reaches up to 99.20%,which has been proven to be higher than that attained by classical convolutional neural network models.Results show that the automatic diagnosis of DR based on vision transformer and WF-OCTA pictures is more effective for detecting and staging DR.

TCERG1L hypermethylation is a risk factor of diabetic retinopathy in Chinese children with type 1 diabetes

●AIM:To identify the differential methylation sites(DMS)and their according genes associated with diabetic retinopathy(DR)development in type 1 diabetes(T1DM)children.●METHODS:This study consists of two surveys.A total of 40 T1DM children was included in the first survey.Because no participant has DR,retina thinning was used as a surrogate indicator for DR.The lowest 25%participants with the thinnest macular retinal thickness were included into the case group,and the others were controls.The DNA methylation status was assessed by the Illumina methylation 850K array BeadChip assay,and compared between the case and control groups.Four DMS with a potential role in diabetes were identified.The second survey included 27 T1DM children,among which four had DR.The methylation patterns of the four DMS identified by 850K were compared between participants with and without DR by pyrosequencing.●RESULTS:In the first survey,the 850K array revealed 751 sites significantly and differentially methylated in the case group comparing with the controls(|Δβ|>0.1 and Adj.P<0.05),and 328 of these were identified with a significance of Adj.P<0.01.Among these,319 CpG sites were hypermethylated and 432 were hypomethylated in the case group relative to the controls.Pyrosequencing revealed that the transcription elongation regulator 1 like(TCERG1L,cg07684215)gene was hypermethylated in the four T1DM children with DR(P=0.018),which was consistent with the result from the first survey.The methylation status of the other three DMS(cg26389052,cg25192647,and cg05413694)showed no difference(all P>0.05)between participants with and without DR.●CONCLUSION:The hypermethylation of the TCERG1L gene is a risk factor for DR development in Chinese children with T1DM.

Key genes and regulatory networks for diabetic retinopathy based on hypoxia-related genes:a bioinformatics analysis

AIM:To prevent neovascularization in diabetic retinopathy(DR)patients and partially control disease progression.METHODS:Hypoxia-related differentially expressed genes(DEGs)were identified from the GSE60436 and GSE102485 datasets,followed by gene ontology(GO)functional annotation and Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway enrichment analysis.Potential candidate drugs were screened using the CMap database.Subsequently,a protein-protein interaction(PPI)network was constructed to identify hypoxia-related hub genes.A nomogram was generated using the rms R package,and the correlation of hub genes was analyzed using the Hmisc R package.The clinical significance of hub genes was validated by comparing their expression levels between disease and normal groups and constructing receiver operating characteristic curve(ROC)curves.Finally,a hypoxia-related miRNA-transcription factor(TF)-Hub gene network was constructed using the NetworkAnalyst online tool.RESULTS:Totally 48 hypoxia-related DEGs and screened 10 potential candidate drugs with interaction relationships to upregulated hypoxia-related genes were identified,such as ruxolitinib,meprylcaine,and deferiprone.In addition,8 hub genes were also identified:glycogen phosphorylase muscle associated(PYGM),glyceraldehyde-3-phosphate dehydrogenase spermatogenic(GAPDHS),enolase 3(ENO3),aldolase fructose-bisphosphate C(ALDOC),phosphoglucomutase 2(PGM2),enolase 2(ENO2),phosphoglycerate mutase 2(PGAM2),and 6-phosphofructo-2-kinase/fructose-2,6-biphosphatase 3(PFKFB3).Based on hub gene predictions,the miRNA-TF-Hub gene network revealed complex interactions between 163 miRNAs,77 TFs,and hub genes.The results of ROC showed that the except for GAPDHS,the area under curve(AUC)values of the other 7 hub genes were greater than 0.758,indicating their favorable diagnostic performance.CONCLUSION:PYGM,GAPDHS,ENO3,ALDOC,PGM2,ENO2,PGAM2,and PFKFB3 are hub genes in DR,and hypoxia-related hub genes exhibited favorable diagnostic performance.

Risk evaluation for diabetic retinopathy in Chinese renalbiopsied type 2 diabetes mellitus patients

AIM:To investigate diabetic retinopathy(DR)prevalence in Chinese renal-biopsied type 2 diabetes mellitus(T2DM)patients with kidney dysfunction,and to further evaluate its relationship with diabetic nephropathy(DN)incidence and the risk factors for DR development in this population.METHODS:A total of 84 renal-biopsied T2DM patients were included.Fundus and imaging examinations were employed for DR diagnosis.Demographic information and clinical measures along with renal histopathology were analyzed for comparisons between the DR and non-DR groups.Risk factors on DR development were analyzed with multiple logistic regression.RESULTS:DR prevalence was 50%in total.The incidences of DN,non-diabetic renal disease(NDRD)and mixed-type pathology were 47.6%,19.0%and 33.3%in the DR group respectively,while 11.9%,83.3%and 4.8%in the non-DR group.Systolic blood pressure,ratio of urinary albumin to creatine ratio,urinary albumin,24-hours urinary protein,the incidence and severity of DN histopathology were found statistically increased in the DR group.Multiple logistic regression analysis showed histopathological DN incidence significantly increased the risk of DR development[odds ratio(OR)=21.664,95%confidential interval(CI)5.588 to 83.991,P<0.001 for DN,and OR=45.475,95%CI 6.949 to 297.611,P<0.001 for mixed-type,respectively,in reference to (NDRD)],wherein DN severity positively correlated.CONCLUSION:Renal histopathological evidence indicates DN incidence and severity increases the risk of DR development in Chinese T2DM patients inexperienced of regular fundus examinations.

Retinal vascular morphological characteristics in diabetic retinopathy: an artificial intelligence study using a transfer learning system to analyze ultra-wide field images

AIM:To investigate the morphological characteristics of retinal vessels in patients with different severity of diabetic retinopathy(DR)and in patients with or without diabetic macular edema(DME).METHODS:The 239 eyes of DR patients and 100 eyes of healthy individuals were recruited for the study.The severity of DR patients was graded as mild,moderate and severe non-proliferative diabetic retinopathy(NPDR)according to the international clinical diabetic retinopathy(ICDR)disease severity scale classification,and retinal vascular morphology was quantitatively analyzed in ultra-wide field images using RU-net and transfer learning methods.The presence of DME was determined by optical coherence tomography(OCT),and differences in vascular morphological characteristics were compared between patients with and without DME.RESULTS:Retinal vessel segmentation using RU-net and transfer learning system had an accuracy of 99%and a Dice metric of 0.76.Compared with the healthy group,the DR group had smaller vessel angles(33.68±3.01 vs 37.78±1.60),smaller fractal dimension(Df)values(1.33±0.05 vs 1.41±0.03),less vessel density(1.12±0.44 vs 2.09±0.36)and fewer vascular branches(206.1±88.8 vs 396.5±91.3),all P<0.001.As the severity of DR increased,Df values decreased,P=0.031.No significant difference between the DME and non-DME groups were observed in vascular morphological characteristics.CONCLUSION:In this study,an artificial intelligence retinal vessel segmentation system is used with 99%accuracy,thus providing with relatively satisfactory performance in the evaluation of quantitative vascular morphology.DR patients have a tendency of vascular occlusion and dropout.The presence of DME does not compromise the integral retinal vascular pattern.

HHO optimized support vector machine classifier for traditional Chinese medicine syndrome differentiation of diabetic retinopathy

AIM:To develop a classifier for traditional Chinese medicine(TCM)syndrome differentiation of diabetic retinopathy(DR),using optimized machine learning algorithms,which can provide the basis for TCM objective and intelligent syndrome differentiation.METHODS:Collated data on real-world DR cases were collected.A variety of machine learning methods were used to construct TCM syndrome classification model,and the best performance was selected as the basic model.Genetic Algorithm(GA)was used for feature selection to obtain the optimal feature combination.Harris Hawk Optimization(HHO)was used for parameter optimization,and a classification model based on feature selection and parameter optimization was constructed.The performance of the model was compared with other optimization algorithms.The models were evaluated with accuracy,precision,recall,and F1 score as indicators.RESULTS:Data on 970 cases that met screening requirements were collected.Support Vector Machine(SVM)was the best basic classification model.The accuracy rate of the model was 82.05%,the precision rate was 82.34%,the recall rate was 81.81%,and the F1 value was 81.76%.After GA screening,the optimal feature combination contained 37 feature values,which was consistent with TCM clinical practice.The model based on optimal combination and SVM(GA_SVM)had an accuracy improvement of 1.92%compared to the basic classifier.SVM model based on HHO and GA optimization(HHO_GA_SVM)had the best performance and convergence speed compared with other optimization algorithms.Compared with the basic classification model,the accuracy was improved by 3.51%.CONCLUSION:HHO and GA optimization can improve the model performance of SVM in TCM syndrome differentiation of DR.It provides a new method and research idea for TCM intelligent assisted syndrome differentiation.