Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Background/aims: Deep learning systems (DLSs) for diabetic retinopathy (DR) detection show promising results but can underperform in racial and ethnic minority groups, therefore external validation within these populations is critical for health equity. This study evaluates the performance of a DLS for DR detection among Indigenous Australians, an understudied ethnic group who suffer disproportionately from DR-related blindness.
Methods: We performed a retrospective external validation study comparing the performance of a DLS against a retinal specialist for the detection of more-than-mild DR (mtmDR), vision-threatening DR (vtDR) and all-cause referable DR. The validation set consisted of 1682 consecutive, single-field, macula-centred retinal photographs from 864 patients with diabetes (mean age 54.9 years, 52.4% women) at an Indigenous primary care service in Perth, Australia. Three-person adjudication by a panel of specialists served as the reference standard.
Results: For mtmDR detection, sensitivity of the DLS was superior to the retina specialist (98.0% (95% CI, 96.5 to 99.4) vs 87.1% (95% CI, 83.6 to 90.6), McNemar's test p<0.001) with a small reduction in specificity (95.1% (95% CI, 93.6 to 96.4) vs 97.0% (95% CI, 95.9 to 98.0), p=0.006). For vtDR, the DLS's sensitivity was again superior to the human grader (96.2% (95% CI, 93.4 to 98.6) vs 84.4% (95% CI, 79.7 to 89.2), p<0.001) with a slight drop in specificity (95.8% (95% CI, 94.6 to 96.9) vs 97.8% (95% CI, 96.9 to 98.6), p=0.002). For all-cause referable DR, there was a substantial increase in sensitivity (93.7% (95% CI, 91.8 to 95.5) vs 74.4% (95% CI, 71.1 to 77.5), p<0.001) and a smaller reduction in specificity (91.7% (95% CI, 90.0 to 93.3) vs 96.3% (95% CI, 95.2 to 97.4), p<0.001).
Conclusion: The DLS showed improved sensitivity and similar specificity compared with a retina specialist for DR detection. This demonstrates its potential to support DR screening among Indigenous Australians, an underserved population with a high burden of diabetic eye disease.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10850716 | PMC |
| http://dx.doi.org/10.1136/bjo-2022-322237 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Two step approach for detecting and segmenting the second mesiobuccal canal of maxillary first molars on cone beam computed tomography (CBCT) images via artificial intelligence.
BMC Oral Health
September 2025
Oral and Maxillofacial Radiology Department, Cairo university, Cairo, Egypt.
Aim: The purpose of this study was to assess the accuracy of a customized deep learning model based on CNN and U-Net for detecting and segmenting the second mesiobuccal canal (MB2) of maxillary first molar teeth on cone beam computed tomography (CBCT) scans.
Methodology: CBCT scans of 37 patients were imported into 3D slicer software to crop and segment the canals of the mesiobuccal (MB) root of the maxillary first molar. The annotated data were divided into two groups: 80% for training and validation and 20% for testing.
A systematic review of EEG-based machine learning classifications for obsessive-compulsive disorder: current status and future directions.
BMC Psychiatry
September 2025
Department of Cognitive Neuroscience, Faculty of Biology, Bielefeld University, Bielefeld, Germany.
Obsessive-compulsive disorder (OCD) is a chronic and disabling condition affecting approximately 3.5% of the global population, with diagnosis on average delayed by 7.1 years or often confounded with other psychiatric disorders.
View Article and Find Full Text PDFUse of artificial intelligence for classification of fractures around the elbow in adults according to the 2018 AO/OTA classification system.
BMC Musculoskelet Disord
September 2025
Department of Clinical Sciences at Danderyds Hospital, Department of Orthopedic Surgery, Karolinska Institutet, Stockholm, 182 88, Sweden.
Background: This study evaluates the accuracy of an Artificial Intelligence (AI) system, specifically a convolutional neural network (CNN), in classifying elbow fractures using the detailed 2018 AO/OTA fracture classification system.
Methods: A retrospective analysis of 5,367 radiograph exams visualizing the elbow from adult patients (2002-2016) was conducted using a deep neural network. Radiographs were manually categorized according to the 2018 AO/OTA system by orthopedic surgeons.
The imitation game: large language models versus multidisciplinary tumor boards: benchmarking AI against 21 sarcoma centers from the ring trial.
J Cancer Res Clin Oncol
September 2025
Department of Surgery, Mannheim School of Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany.
Purpose: The study aims to compare the treatment recommendations generated by four leading large language models (LLMs) with those from 21 sarcoma centers' multidisciplinary tumor boards (MTBs) of the sarcoma ring trial in managing complex soft tissue sarcoma (STS) cases.
Methods: We simulated STS-MTBs using four LLMs-Llama 3.2-vison: 90b, Claude 3.
Deep learning based solar forecasting for optimal PV BESS sizing in ultra fast charging stations.
Sci Rep
September 2025
Fukushima Renewable Energy Institute, Koriyama, Japan.
Ultra-fast charging stations (UFCS) present a significant challenge due to their high power demand and reliance on grid electricity. This paper proposes an optimization framework that integrates deep learning-based solar forecasting with a Genetic Algorithm (GA) for optimal sizing of photovoltaic (PV) and battery energy storage systems (BESS). A Gated Recurrent Unit (GRU) model is employed to forecast PV output, while the GA maximizes the Net Present Value (NPV) by selecting optimal PV and BESS sizes tailored to weekday and weekend demand profiles.
View Article and Find Full Text PDF