The demand for AI to improve patients outcome has been increased; we, therefore, aim to establish the diagnostic values of AI in diabetic retinopathy by pooling the published studies of deep learning on this subject. A total of eight studies included which evaluated deep learning in a total of 706,922 retinal images. The overall pooled area under receiver operating curve (AUROC) was 98.93% (95%CI:98.37%-99.49%). However, the overall pooled sensitivity and specificity for detecting referable diabetic retinopathy (RDR) was 74% (95% CI: 73%-74%), and 95% (95% CI: 95%-95%). The findings of this study show that deep learning had high sensitivity and specificity for identifying diabetic retinopathy.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI190532 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Efficacy and Safety of Static Stretching and Daily Walking on the Cardio-Ankle Vascular Index in a Patient With Type 2 Diabetes Mellitus, Proliferative Retinopathy, and Lower-Extremity Peripheral Arterial Disease: A Case Report.
Cureus
November 2024
Research Institute of Health and Welfare, Kibi International University, Takahashi, JPN.
Proliferative diabetic retinopathy (PDR) and peripheral arterial disease (PAD) of the lower extremities are serious complications of type 2 diabetes mellitus (T2DM). Aerobic exercise has been shown to be primarily effective for glycemic control and gait disturbance owing to PAD. However, the safety and efficacy of exercise therapy in patients with PDR remain unclear.
View Article and Find Full Text PDFPrevalence and impact of obstructive sleep apnea in type 2 diabetes mellitus: A descriptive cross-sectional study.
Med J Armed Forces India
December 2024
Commandant, Military Hospital, Jabalpur, India.
Background: Obstructive sleep apnea (OSA) has been reported to have a high prevalence in patients with type 2 diabetes mellitus. There is scarcity of literature on relationship between OSA and diabetes in Indian population.
Methods: A cross-sectional observational study was conducted at a tertiary care hospital and 80 consecutive and consenting patients with diabetes were enrolled over 24 months from 01 Sep 2014 to 31 Aug 2016.
Alternative splicing: Therapeutic target for vasculopathy in diabetic complications.
Life Sci
December 2024
Department of Plastic Surgery, Affiliated Hospital of Xuzhou Medical University, Xuzhou, China. Electronic address:
It is becoming increasingly evident that diabetic vascular complications seriously threaten human health. The most prevalent microvascular complications include kidney disease, retinal disease, cardiovascular diseases and amputation. Conventional treatments can only relieve the progression of the diseases, and is no longer appropriate for the long-term management of diabetic patients.
View Article and Find Full Text PDFImpact of COVID-19 and recovery of routine diabetic retinopathy digital screening across different regions in England: an analysis of publicly available data.
BMJ Open
December 2024
Vision and Eye Research Institute, School of Medicine, Anglia Ruskin University, Cambridge, UK.
Objective: This study aims to examine the reduction and subsequent recovery of routine digital screening (RDS) uptake in England from 2018 to 2022, exploring national, regional and individual Diabetic Eye Screening Programme (DESP) levels. The COVID-19 lockdown in most areas of England was from 26 March 2020 to 23 June 2020 (first national lockdown), 5 November 2020 to 2 December 2020 (second national lockdown) and 6 January 2021 to 8 March 2021 (third national lockdown).
Design: Retrospective data analysis.
Prevalence of microvascular complications and associated factors among diabetes mellitus patients in Ethiopia: A systematic review and Meta-analysis.
Microvasc Res
December 2024
Department of Medical Laboratory Science, College of Health Sciences, Woldia University, P.O. box 400, Woldia, Ethiopia; Research Center for Tuberculosis and Department of Medical Microbiology, Faculty of Health Sciences, University of Pretoria, Prinshof, 0084 Pretoria, South Africa.
Background: Diabetes mellitus (DM) is a metabolic abnormality affecting 537 million people worldwide. Poor glycemic control, longer duration, and poor medication adherence increased the risk of DM complications. Comprehensive evidence on the pooled prevalence of microvascular complications in DM patients in Ethiopia is not available.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!