Predictive Modeling Of Diabetic Retinopathy Disease By Use Of Machine Learning

According to a report by the World Health Organization (WHO), one of the leading causes of death by the end of 2030 will be diabetes, which is a serious disease. Timely treatment of this disease can prevent serious complications, including death. The number of people getting infected with diabetes is millions. The risk of getting this infection is common now a days and is more prevalent in women than men. Diagnosis process for diabetes is quite tedious. Diabetes retinopathy is a disorder that is caused by uncontrolled diabetes and can cause complete blindness if left untreated. Therefore, if detected early its treatment can prevent the unfavourable effects of diabetic retinopathy. The actual diagnosis of diabetes retinopathy by eye doctors takes a lot of time and patients need to suffer more during this time. Thus the latest achievements in science and technology makes it easier to predict the disease. The aim is to diagnose whether a person is diabetic or not using a phase-based machine learning method. This paper reviews, classifies and compares algorithms with previously suggested strategies to develop better and more efficient algorithms.

SCREEN NOW: a new educational resource for diabetes and eye health

Diabetes retinopathy is a feared complication of diabetes. Anne Phillips describes a new educational resource to explain the need for retinal screening to people living with diabetes and health professionals

Epigenetic Mechanisms in Type 2 Diabetes Retinopathy: A Systematic Review

Diabetic retinopathy (DR) is one of the main causes of vision loss in middle-aged economically active people. Modifiable (i.e., hyperglycaemia, hypertension, hyperlipidaemia, obesity, and cigarette smoke) and non-modifiable factors (i.e., duration of diabetes, puberty, pregnancy and genetic susceptibility) are involved in the development of DR. Epigenetic mechanisms, modulating the oxidative stress, inflammation, apoptosis, and aging, could influence the course of DR. Herein, we conducted a systematic review of observational studies investigating how epigenetics affects type 2 diabetes retinopathy (T2DR). A total of 23 epidemiological studies were included: 14 studies focused on miRNA, 4 studies on lnc-RNA, one study on both miRNA and lnc-RNA, and 4 studies on global or gene-specific DNA methylation. A direct relation between the dysregulation of miR-21, miR-93, and miR-221 and FPG, HbA1c, and HOMA-IR was identified. A panel of three miRNAs (hsa-let-7a-5p, hsa-miR-novel-chr5_15976, and hsa-miR-28-3p) demonstrated a good sensitivity and specificity for predicting T2DR. Little evidence is available regarding the possible role of the long non-coding MALAT1 dysregulation and MTHFR gene promoter hypermethylation. Despite these initial, encouraging findings potentially suggesting a role of epigenetics in T2DR, the use in clinical practice for the diagnosis and staging of this complication encounters several difficulties and further targeted investigations are still necessary.

Komparasi Akurasi Algoritme CART Dan Neural Network Untuk Diagnosis Penyakit Diabetes Retinopathy

Penyakit Diabetes Retinopathy atau DR adalah salah satu komplikasi mikrovaskular diabetes melitus dengan angka prevalensi yang cukup tinggi yang bisa menyebabkan kematian. Penderita DR hingga saat ini masih sulit disembuhkan karena mayoritas penderita melakukan pemeriksaan di saat kondisi penyakit telah memasuki tahap berbahaya, hal ini dikarenakan sifat dari penyakit DR ini tidak menunjukkan gejala yang terlihat bila masih pada tahap awal. Penelitian ini menguji diagnosis penyakit diabetes retinopathy dengan melakukan klasiifikasi menggunakan metode data mining. Metode yang digunakan ialah algoritme Classification And Regression Trees (CART) dan Algoritme Neural Network menggunakan dataset diambil dari UCI Repository Learning diperoleh daro Universitas Debreen, Hongaria. Adapun metode validasi dan evaluasi yang digunakan dalam penelitian ini yaitu 10-cross validation dan confusion matrix. Hasil dari akurasi pada algoritme CART yaitu 63.4231% dengan nilai precision 0.64%, Recall 0.634%, dan F-Measure 0.634% dan algoritme Neural Network mendapatkankan nilai akurasi sebesar 72.285% dengan nilai precision 0.723%, Recall 0.723%, dan F-Measure 0.723%. Dari hasil tersebut dapat disimpulkan bahwa algoritme Neural Network lebih baik dalam mendiagnosis penyakit diabetes retinopathy. Kata kunci— Klasifikasi, Diagnosis, Diabetes Retinopathy, Algoritme, CART, Neural Network

Diabetic Retinopathy Prediction by Ensemble Learning Based on Biochemical and Physical Data

(1) Background: Diabetic retinopathy, one of the most serious complications of diabetes, is the primary cause of blindness in developed countries. Therefore, the prediction of diabetic retinopathy has a positive impact on its early detection and treatment. The prediction of diabetic retinopathy based on high-dimensional and small-sample-structured datasets (such as biochemical data and physical data) was the problem to be solved in this study. (2) Methods: This study proposed the XGB-Stacking model with the foundation of XGBoost and stacking. First, a wrapped feature selection algorithm, XGBIBS (Improved Backward Search Based on XGBoost), was used to reduce data feature redundancy and improve the effect of a single ensemble learning classifier. Second, in view of the slight limitation of a single classifier, a stacking model fusion method, Sel-Stacking (Select-Stacking), which keeps Label-Proba as the input matrix of meta-classifier and determines the optimal combination of learners by a global search, was used in the XGB-Stacking model. (3) Results: XGBIBS greatly improved the prediction accuracy and the feature reduction rate of a single classifier. Compared to a single classifier, the accuracy of the Sel-Stacking model was improved to varying degrees. Experiments proved that the prediction model of XGB-Stacking based on the XGBIBS algorithm and the Sel-Stacking method made effective predictions on diabetes retinopathy. (4) Conclusion: The XGB-Stacking prediction model of diabetic retinopathy based on biochemical and physical data had outstanding performance. This is highly significant to improve the screening efficiency of diabetes retinopathy and reduce the cost of diagnosis.

Effect of Statin Therapy on Diabetes Retinopathy in People With Type 2 Diabetes Mellitus: A Meta-Analysis

Objective: We tried to find the relationship between statin and diabetes retinopathy (DR) in patients with type 2 diabetes mellitus (T2DM). Methods: We searched the databases of PubMed, EMBASE, and the Cochrane Library for eligible studies reporting on the relationships between statin use and DR, from inception to September 25, 2020. The terms searched including Diabetes Mellitus, Type 2, Hydroxymethylglutaryl-CoA Reductase Inhibitors, and Diabetic Retinopathy. We expressed the results as the odds ratios (ORs) with 95% confidence intervals (CIs) which were calculated using a random-effects model. Results: A total of 6 eligible studies, including 43 826 patients, were included in the meta-analysis. The meta-analysis showed that statin was not associated with elevated risk of DR [OR = 0.96 (95% CI: 0.80-1.16), P = .68]. Similarly, no differences were found between statin and placebo in participants ≥500 [OR = 0.98 (95% CI: 0.80-1.21)] or participants <500 [OR = 0.90 (95% CI: 0.49-1.66)]. Further, we conducted a meta-analysis to study the effect of statin therapy on DR in people with type 2 diabetes according to age and found that statin use was associated with a decreased risk of DR in patients with type 2 diabetes 40 years of age or older [OR = 0.87 (95% CI: 0.82-0.92)]. Conclusion: Our meta-analysis revealed that statin was not associated with elevated risk of DR in patients with T2DM. Moreover, statin use was associated with a lower incidence of DR in patients with type 2 diabetes 40 years of age or older.

The prevalence of Diabetic Retinopathy in a Tertiary Centre in Western Region, Nepal

Background: Diabetes mellitus is a multisystem disease. It has multiple complications like retinopathy, neuropathy, nephropathy, diabetes ketoacidosis, and stroke. Diabetes retinopathy (DR) is one of the blinding complications of diabetes. This study was done to find out the prevalence of diabetic retinopathy among diabetic patients attending in the outpatient department (OPD) of internal medicine, Gandaki Medical College and Teaching Hospital (GMCTHRC), Pokhara, Nepal. Materials and Methods: A hospital based cross-sectional study was performed among the 200 diabetes mellitus patients attending in the medicine OPD from 15th December 2017 to 15thDecember 2018. They were referred to eye OPD of GMC. The detailed eye examination including fundus evaluation under mydriasis was done to all the patients. The diagnosis of DR was graded using the Early Treatment Diabetic Retinopathy Study classification (ETDRS). Patients having hypertension and other retinal diseases were excluded from the study. Data analysis was done using statistical package for social sciences (SPPS) version 11.20. Results: The mean age of the patients was 63.02 ±11.8 years. In our study 60.5% of the patients were male and 39.5% were female. Diabetes retinopathy was seen in 29.5% patients, of which non proliferative diabetes retinopathy (NPDR) was present in 19.5%, proliferative diabetes retinopathy (PDR) in 9.5% and 0.5% had diabetes maculopathy. Conclusion: The prevalence of DR is quite significant in the people with diabetes. Early diagnosis and management of retinopathy will help to avoid blindness due to the diabetic retinopathy.