| 1. |
- Daley, Jason R., et al.
(författare)
-
Development of a deep learning algorithm for provision of a South Western Sydney diabetes retinal screening service
- 2022
-
Ingår i: Clinical and Experimental Ophthalmology. - : Blackwell Publishing. - 1442-6404 .- 1442-9071. ; 49:8, s. 805-805
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Purpose: Diabetic retinopathy (DR) is highly prevalent in the multi-ethnic and low socioeconomic population of South Western Sydney. This is a significant public health burden, demanding efficient and cost-effective diabetes retinal screening. The multi-centre South Western Eye and Diabetes Deep Learning Algorithm study, supported by an Ophthalmic Research Institute of Australia grant, aims to develop and validate a novel deep learning algorithm, capable of grading DR, for a new diabetes retinal screening service. This abstract evaluates the performance of the Diabetic retinopathy OCT Open souRce Artificial Intelligence (Doctor AI©SK) program.Methods: Doctor AI analyses fundus photographs and optical coherence tomography (OCT) images simultaneously to grade diabetic retinopathy. It was trained with over 50,000 fundus photographs and 8000 OCT scans, using a combination of Australasian and publicly available datasets. As a screening tool, the algorithm's operating point was optimised for sensitivity and negative predictive value, and its performance reevaluated. Clinical validation is being undertaken in the recruited population at each study site.Results: For the detection of diabetic macula oedema from OCT images, Doctor AI achieved a 96.8% sensitivity, 98.1% specificity and 97.5% accuracy. Area under the receiver operating characteristic curve was 0.996. For the diagnosis of DR from fundus photographs, Doctor AI achieved a 90.4% sensitivity, 96.8% specificity and 88.9% accuracy. Preliminary clinical validation revealed an accuracy of 89% and 85% for the OCT and fundus photograph modules of the algorithm, respectively.Conclusion: Doctor AI is a unique deep learning algorithm capable of diagnosing DR and diabetic macula oedema with high sensitivity and accuracy.
|
|
| 2. |
- Wang, Xingdi, et al.
(författare)
-
Establishing a diabetes retinal screening service in South Western Sydney : Patient satisfaction with retinal imaging and the correlation between diabetic retinopathy and quality of life
- 2022
-
Ingår i: Clinical and Experimental Ophthalmology. - : Blackwell Publishing. - 1442-6404 .- 1442-9071. ; 49:8, s. 899-900
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Purpose: The multicentre, prospective South Western Eye and Diabetes Deep Learning Algorithm study has developed a new diabetes retinal screening service, incorporating a novel deep learning algorithm, for a low socio-economic, multi-ethnic, outer-metropolitan Sydney region. This preliminary report examines patient satisfaction with retinal imaging and correlation between diabetic retinopathy (DR) and quality of life (QOL).Methods: Supported by an Ophthalmic Research Institute of Australia grant, South Western Eye and Diabetes Deep Learning Algorithm participants were recruited from diabetes outpatient clinics and underwent two-field, table-top fundus photography and ocular coherence tomography. Questionnaires regarding patient satisfaction with retinal imaging and self-perceived QOL (EQ5D) were completed. Proportion of participants with high satisfaction levels were reported and mean self-perceivedQ OL (EQ-VAS) scores for those with and without DR were compared.Results: The study is ongoing and preliminary data (n=54) is presented. DR was detected in 50.0% of recruited participants. All participants found it very convenient to undergo photography on the same day as their diabetes appointment and 83.3% would undergo retinal imaging for DR screening again. This was despite 50.0% of participants requiring pharmacological pupil dilation. Preliminary QOL data showed that although DR did not correlate with greater disability, pain or anxiety/depression, average self-perceived health was lower (mean EQ-VAS scores of 68.3% vs 76.3%) in participants with DR than those without DR.Conclusions: The correlation between DR and lower self-perceived QOL, occurring independently of both visual acuity and knowledge of DR diagnosis, supports the need for efficient screening and early treatment. Retinal imaging was well-tolerated with an overwhelming preference for same-day outpatient DR screening.
|
|
