AI Article Synopsis
- The study evaluates the performance of AI components in a telehealth platform for eye screening, connecting ophthalmologists with remote indigenous communities in Australia.
- The AI included an image quality alert system and a diabetic retinopathy detection system, with the image quality detection achieving 72% accuracy per image and 85% at the patient level, while the retinopathy detection reached 85% and 87% accuracy respectively.
- These results suggest that AI can effectively support eye health assessments, indicating its potential for future healthcare models.
Article Abstract
We report on the prediction performance of artificial intelligence components embedded into a telehealth platform underlying a newly established eye screening service connecting metropolitan-based ophthalmologists to patients in remote indigenous communities in Northern Territory and Queensland. Two AI-based components embedded into the telehealth platform were evaluated on retinal images collected from 328 unique patients: an image quality alert system and a diabetic retinopathy detection system. Compared to ophthalmologists, at an individual image level, the image quality detection algorithm was correct 72% of the time, and 85% accurate at a patient level. The retinopathy detection algorithm was correct 85% accurate at an individual image level, and 87% accurate at a patient level. This evaluation provides assurances for future service models using AI to complement and support decisions of eye health assessment teams.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI231259 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Characterization of cognitive decline in long-duration type 1 diabetes by cognitive, neuroimaging and pathological examinations.
JCI Insight
January 2025
Dianne Hoppes Nunnally Laboratory Research Division, Joslin Diabetes Center, Boston, United States of America.
Background: We aimed to characterize factors associated with the under-studied complication of cognitive decline in aging people with long-duration type 1 diabetes (T1D).
Methods: Joslin "Medalists" (n = 222; T1D ≥ 50 years) underwent cognitive testing. Medalists (n = 52) and age-matched non-diabetic controls (n = 20) underwent neuro- and retinal imaging.
Comparisons of oscillatory potentials and 30 Hz flicker electroretinograms for discriminating eyes with diabetic retinopathy from normal eyes.
Jpn J Ophthalmol
January 2025
Department of Ophthalmology, Dokkyo Medical University Saitama Medical Center, 2-1-50 Minami-Koshigaya Koshigaya, Saitama, 343-8555, Japan.
Purpose: To compare the amplitudes and implicit times of the oscillatory (OPs) of the full-field electroretinograms (ERGs) to those of the 30 Hz flicker ERGs in differentiating eyes with diabetic retinopathy (DR) from normal eyes.
Study Design: Single-center observational study.
Methods: Full-field ERGs were recorded in 55 patients with Type 2 diabetes mellitus (DM) and 20 normal control subjects.
Bayesian deep learning applied to diabetic retinopathy with uncertainty quantification.
Heliyon
January 2025
Information Technology Department, Technical College of Informatics-Akre, Akre University for Applied Sciences, Kurdistan Regain, Iraq.
Deep Learning (DL) has significantly contributed to the field of medical imaging in recent years, leading to advancements in disease diagnosis and treatment. In the case of Diabetic Retinopathy (DR), DL models have shown high efficacy in tasks such as classification, segmentation, detection, and prediction. However, DL model's opacity and complexity lead to errors in decision-making, particularly in complex cases, making it necessary to estimate the model's uncertainty in predictions.
View Article and Find Full Text PDFPrevalence of chronic kidney disease among Chinese adults with diabetes: a nationwide population-based cross-sectional study.
Lancet Reg Health West Pac
February 2025
Department of Endocrinology and Metabolism, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai Diabetes Institute, Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Clinical Center for Diabetes, Shanghai Key Clinical Center for Metabolic Disease, Shanghai, China.
Background: To date, comprehensive data on the distribution of chronic kidney disease (CKD), the most prevalent comorbidity in diabetes, among Chinese adults with diabetes is lacking. Additionally, research gaps exist in understanding the association between CKD and cardiovascular health (CVH), an integrated indicator of lifestyle and metabolic control, within a nationwide sample of Chinese adults with diabetes.
Methods: A nationally community-based cross-sectional survey was conducted in 2018-2020.
A systematic review of the cost-effectiveness of anti-VEGF drugs for the treatment of diabetic retinopathy.
Health Technol Assess
January 2025
Centre for Reviews and Dissemination, University of York, York, UK.
Background: Non-proliferative and proliferative diabetic retinopathy are common complications of diabetes and a major cause of sight loss. Anti-vascular endothelial growth factor drugs represent a treatment option for people with diabetic retinopathy and are routinely used to treat various other eye conditions. However, anti-vascular endothelial growth factor drugs are expensive relative to current care options, and it is unclear whether this additional cost is justified when the immediate risk of vision loss is lower compared to patients with more aggressive ophthalmological conditions.
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!