Meta analysis and data mining of the method of yishenhuoxue in the treatment of nonproliferative diabetic retinopathy

Objective:To evaluate the efficacy and safety of the method of Yishen Huoxue in the intervention of nonproliferative diabetic retinopathy(NPDR)by Meta analysis and explore the medication regularity of Chinese Medicine(TCM)based on data mining.Methods:The related literature of TCM in the treatment of NPDR published in CNKI,VIP,WF,PubMed,the Cochrane Library,SinoMed,Embase were collected.The quality of the included literature was evaluated with reference to the Cochrane System Evaluators'Handbook,and statistical analysis was performed by applying Revman 5.4.1 software.After normalization of the Chinese medicine names,association rule analysis was performed by using SPSS Modeler 18,and then Cytoscape was used to produce complex network diagrams.Results:20 RCTs were included.Meta-analysis results showed that the method of Yishen Huoxue or Yishen Huoxue combined with western medicine were better than the control group in improving the total clinical efficiency[RR=1.21,95%CI(1.16,1.27),P<0.00001],TCM symptom efficacy[RR=1.28,95%CI(1.18,1.39),P<0.00001],and visual acuity[MD=0.11,95%CI(0.05,0.17),P=0.0001],HDL-C[MD=0.14,95%CI(0.03,0.25),P=0.02];reducing the number of fundus hemangiomas[MD=-3.51,95%CI(-5.73,-1.28),P=0.002],hemorrhagic spot area[MD=-0.70,95%CI(-0.95,-0.46),P<0.00001],CMT[MD=-35.31,95%CI(-55.47,-15.14),P=0.0006],FBG[MD=-0.39,95%CI(-0.72,-0.05),P=0.02],LDL-C[MD=-0.36,95%CI(-0.64,-0.08),P=0.01],whole high blood viscosity[MD=-0.43,95%CI(-0.75,-0.12),P=0.006],plasma viscosity[MD=-0.36,95%CI(-0.67,-0.06),P=0.02]and fibrinogen[MD=-0.50,95%CI(-0.81,-0.19),P=0.002].The differences were statistically significant.The 20 recipes entered involved a total of 70 herbal medicines.It is analyzed that the high-frequency drugs and the core drugsare gou qi,san qi,dan shen,haung qi,sheng di huang,et al.The association rule analysis summarizes the commonly used pairs including:sheng di huang-san qi,sheng di huang-gou qi,et al.Conclusions:Compared with western medicine treatment alone,the method of Yishen Huoxue or Yishen Huoxue combined with western medicine produce better effects,but it still needs to be verified by higher quality clinical studies.

Efficacy of intravitreal conbercept combined with panretinal photocoagulation for severe nonproliferative diabetic retinopathy without macular edema

AIM: To assess efficacy of intravitreal conbercept(IVC) injection in combination with panretinal photocoagulation(PRP) vs PRP alone in patients with severe nonproliferative diabetic retinopathy(SNPDR) without macular edema(ME).METHODS: Forty-eight patients with SNPDR without ME(56 eyes) were divided into the PRP group and IVC+PRP group(the pulse group) in this retrospective clinical study. Conbercept was intravitreally administered to patients in the pulse group 1 wk before treatment with PRP and followed up for 1, 3, and 6 mo. The best-corrected visual acuity(BCVA, log MAR), center foveal thickness(CFT), visual acuity(VA) improvement, and adverse reactions were compared between groups.RESULTS: In the PRP group, the BCVA reduced at 1 and 3 mo before improving at 6 mo. In the pulse group, baseline BCVA decreased continuously at 1 mo, increased at 3 and 6 mo. BCVA in the pulse group was better than that in the PRP group at 1, 3, and 6 mo. There was an increase in CFT in the PRP group during follow-up compared with baseline. In the pulse group, CFT was increased at 1 mo relative to baseline, steadily decreased to the baseline level at 3 and 6 mo. There was a more significant reduction in CFT in the pulse group during follow-up compared with the PRP group. The effective rates of VA in the PRP and the pulse groups were 81.48% and 100%, respectively. CONCLUSION: As PRP pretreatment, a single dose of IVC administration has beneficial effects for preventing PRPinduced foveal thickening and increasing VA in patients with SNPDR without ME.

Review of the management of sight-threatening diabetic retinopathy during pregnancy

Diabetes mellitus(DM)is a noncommunicable disease reaching epidemic proportions around the world.It affects younger individuals,including women of childbearing age.Diabetes can cause diabetic retinopathy(DR),which is potentially sight threatening when severe nonproliferative DR(NPDR),proliferative DR(PDR),or sight-threatening diabetic macular oedema(STDME)develops.Pregnancy is an independent risk factor for the progression of DR.Baseline DR at the onset of pregnancy is an important indicator of progression,with up to 10% of women with baseline NPDR progressing to PDR.Progression to sight-threatening DR(STDR)during pregnancy causes distress to the patient and often necessitates ocular treatment,which may have a systemic effect.Management includes prepregnancy counselling and,when possible,conventional treatment prior to pregnancy.During pregnancy,closer follow-up is required for those with a long duration of DM,poor baseline control of blood sugar and blood pressure,and worse DR,as these are risk factors for progression to STDR.Conventional treatment with anti-vascular endothelial growth factor agents for STDME can potentially lead to foetal loss.Treatment with laser photocoagulation may be preferred,and surgery under general anaesthesia should be avoided.This review provides a management plan for STDR from the perspective of practising ophthalmologists.A review of strategies for maintaining the eyesight of diabetic women with STDR with emphasis on prepregnancy counselling and planning,monitoring and safe treatment during pregnancy,and management of complications is presented.

Detection and Classification of Diabetic Retinopathy Using DCNN and BSN Models

Diabetes is associated with many complications that could lead to death.Diabetic retinopathy,a complication of diabetes,is difficult to diagnose and may lead to vision loss.Visual identification of micro features in fundus images for the diagnosis of DR is a complex and challenging task for clinicians.Because clinical testing involves complex procedures and is timeconsuming,an automated system would help ophthalmologists to detect DR and administer treatment in a timelymanner so that blindness can be avoided.Previous research works have focused on image processing algorithms,or neural networks,or signal processing techniques alone to detect diabetic retinopathy.Therefore,we aimed to develop a novel integrated approach to increase the accuracy of detection.This approach utilized both convolutional neural networks and signal processing techniques.In this proposed method,the biological electro retinogram(ERG)sensor network(BSN)and deep convolution neural network(DCNN)were developed to detect and classify DR.In the BSN system,electrodes were used to record ERGsignal,which was preprocessed to be noise-free.Processing was performed in the frequency domain by the application of fast Fourier transform(FFT)and mel frequency cepstral coefficients(MFCCs)were extracted.Artificial neural network(ANN)classifier was used to classify the signals of eyes with DR and normal eye.Additionally,fundus images were captured using a fundus camera,and these were used as the input for DCNN-based analysis.The DCNN consisted of many layers to facilitate the extraction of features and classification of fundus images into normal images,non-proliferative DR(NPDR)or earlystage DR images,and proliferative DR(PDR)or advanced-stage DR images.Furthermore,it classifiedNPDRaccording tomicroaneurysms,hemorrhages,cotton wool spots,and exudates,and the presence of new blood vessels indicated PDR.The accuracy,sensitivity,and specificity of the ANNclassifier were found to be 94%,95%,and 93%,respectively.Both the accuracy rate and sensitivity rate of theDCNNclassifierwas 96.5%for the images acquired from various hospitals as well as databases.A comparison between the accuracy rates of BSN andDCNN approaches showed thatDCNNwith fundus images decreased the error rate to 4%.