Objective
Design
Participants
Testing
Main Outcome Measures
Results
Conclusions
Keywords
Abbreviations and Acronyms:
AI (artificial Intelligence), CI (confidence interval), CSDME (clinically significant diabetic macular edema), DME (diabetic macular edema), DR (diabetic retinopathy), FDA (Food and Drug Administration), NPDR (nonproliferative diabetic retinopathy), mtmDr (more than mild diabetic retinopathy), PDR (proliferative diabetic retinopathy), vtDR (vision-threatening diabetic retinopathy), WFPRC (Wisconsin Fundus Photograph Reading Center)IDF Diabetes Atlas.
American Foundation for the Blind. Key Definitions of Statistical Terms. https://www.afb.org/research-and-initiatives/statistics/key-definitions-statistical-terms. Accessed June 13, 2022.
Methods
American Foundation for the Blind. Key Definitions of Statistical Terms. https://www.afb.org/research-and-initiatives/statistics/key-definitions-statistical-terms. Accessed June 13, 2022.
Results
Subgroup | Total n/N (%) | Nonretina sites n/N (%) | Retina sites n/N (%) | ||||
---|---|---|---|---|---|---|---|
Age | < 65 yrs | 370/521 | (71.0) | 291/406 | (71.7) | 79/115 | (68.7) |
≥ 65 yrs | 151/521 | (29.0) | 115/406 | (28.3) | 36/115 | (31.3) | |
Gender | Male | 244/521 | (46.8) | 176/406 | (43.3) | 68/115 | (59.1) |
Female | 277/521 | (53.2) | 230/406 | (56.7) | 47/115 | (40.9) | |
Ethnicity | Hispanic/Latino | 169/521 | (32.4) | 149/406 | (36.7) | 20/115 | (17.4) |
Non-Hispanic/Latino | 352/521 | (67.6) | 257/406 | (63.3) | 95/115 | (82.6) | |
Race | American Indian or Alaska Native | 2/521 | (0.4) | 2/406 | (0.5) | 0/115 | (0.0) |
Asian | 18/521 | (3.5) | 14/406 | (3.4) | 4/115 | (3.5) | |
Black or African American | 105/521 | (20.2) | 58/406 | (14.3) | 47/115 | (40.9) | |
Native Hawaiian or other Pacific Islander | 3/521 | (0.6) | 3/406 | (0.7) | 0/115 | (0.0) | |
Other | 44/521 | (8.4) | 24/406 | (5.9) | 20/115 | (17.4) | |
White | 349/521 | (67.0) | 305/406 | (75.1) | 44/115 | (38.3) |
DR level CSDME | No Apparent DR | Mild NPDR | Moderate NPDR | Severe NPDR | PDR | Questionable | Total |
---|---|---|---|---|---|---|---|
Absent | 669 | 108 | 122 | 1 | 8 | 0 | 908 |
Present | 0 | 0 | 51 | 0 | 2 | 1 | 54 |
Questionable | 0 | 0 | 10 | 0 | 1 | 0 | 11 |
Total | 669 | 108 | 183 | 1 | 11 | 1 | 973 |

Cohort (No. of Eyes with CRS) | Screening Methodology | Sensitivity (95% CI) | Specificity (95% CI) | Imageability/Gradability (95% CI) |
---|---|---|---|---|
Subjects with dilated ophthalmoscopy (n = 999 eyes) | Dilated ophthalmoscopy | 27.7% [20.1%–35.2%] | 99.6% [99.1%– 100.0%] | 99.9% [99.7%–100.0%] |
EyeArt system (with dilation-if-needed) (147 eyes dilated) | 96.4% [93.1%–99.8%] | 88.4% [85.8%–91.1%] | 97.4% [96.0%–98.8%] | |
Subjects enrolled at nonretina specialty centers (n = 778 eyes) | Dilated ophthalmoscopy | 20.6% [13.1%–28.0%] | 99.8% [99.5%–100.0%] | 99.9% [99.6%–100.0%] |
EyeArt system (with dilation-if-needed) (109 eyes dilated) | 96.5% [92.9%–100.0%] | 86.3% [83.0%–89.7%] | 97.6% [96.0%–99.1%] | |
Subjects enrolled at retina specialty centers (n = 221 eyes) | Dilated ophthalmoscopy | 59.5% [40.2%–78.7%] | 98.9% [97.1%– 100.0%] | 100.0% [100.0%–100.0%] |
EyeArt system (with dilation-if-needed) (38 eyes dilated) | 97.3% [90.3%–100.0%] | 88.0% [82.5%–93.5%] | 96.8% [93.6%–100.0%] |


Discussion
Acknowledgments
References
- IDF Diabetes Atlas.9th ed. International Diabetes Federation, 2019https://diabetesatlas.org/atlas/ninth-edition/Date accessed: December 9, 2019
- Diabetes health disparities: a systematic review of health care interventions.Med Care Res Rev. 2007; 64: 101S-156S
- Diabetes Report Card 2019. Centers for Disease Control and Prevention.US Dept of Health and Human Services, 2020: 26
- Fundus photographic risk factors for progression of diabetic retinopathy: ETDRS report number 12.Ophthalmology. 1991; 98: 823-833
- Diabetic retinopathy preferred practice pattern.Ophthalmology. 2020; 127: P66-P145
- Four risk factors for severe visual loss in diabetic retinopathy. The third report from the diabetic retinopathy study.Arch Ophthalmol. 1979; 97: 654-655
- Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices.npj Digit Med. 2018; 1: 39
- Pivotal evaluation of an artificial intelligence system for autonomous detection of referrable and vision-threatening diabetic retinopathy.JAMA Netw Open. 2021; 4e2134254
- The value of automated diabetic retinopathy screening with the EyeArt system: a study of more than 100,000 consecutive encounters from people with diabetes.Diabetes Technol Ther. 2019; 21: 635-643
- Grading diabetic retinopathy from stereoscopic color fundus photographs - an extension of the modified Airlie House classification. ETDRS report number 10.Ophthalmology. 1991; 98: 786-806
- Comparison of two reference standards in validating two field mydriatic digital photography as a method of screening for diabetic retinopathy.Br J Ophthalmol. 2003; 87: 1258-1263
- Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients.Br J Ophthalmol. 2021; 105: 723-728
American Foundation for the Blind. Key Definitions of Statistical Terms. https://www.afb.org/research-and-initiatives/statistics/key-definitions-statistical-terms. Accessed June 13, 2022.
- Comparison of film and digital fundus photographs in eyes of individuals with diabetes mellitus.Invest Ophthalmol Vis Sci. 2011; 52: 6168-6173
- New confidence intervals for the proportion of interest in one-sample correlated binary data.Commun Stat - Theory Methods. 2010; 39: 2865-2876
- Diabetic retinopathy screening with automated retinal image analysis in a primary care setting improves adherence to ophthalmic care.Ophthalmol Retina. 2021; 5: 71-77
Article info
Publication history
Footnotes
Presented at the 2019 Annual Meeting of the American Society of Retina Specialists, Chicago Illinois, July 30, 2019.
SriniVas R Sadda, MD, an Editor of this journal, was recused from the peer-review process of this article and had no access to information regarding its peer-review.
Disclosure(s):
All authors have completed and submitted the ICMJE disclosures form.
The author(s) have made the following disclosure(s): J.I.L.: Grants – Eyenuk Inc., Genentech, Regeneron, Aldeyra, NGM, Stealth, Janssen, Graybug, Spring Vision, Chengdu; Royalties – CRC Press (AMD Book); Consultant – Genentech/Roche, Novartis, Iveric, Cognition, Adverum, Alcon, Eyenuk (starting October 2020 but not during the trial); Honoraria – Eyenuk, PRIME, Medscape; Participation on a Data Safety Monitoring Board or Advisory Board – Opthea, Viridian, Luxa, Aura, Santen, Allergan, Quark; Medical writing support – Genenteck (phase 3 data)
S.R.S.: Consultant – Apellis, Biogen, Boehringer Ingelheim, Jansen, Nanoscope, Pfizer, Bayer, Regeneron, Astellas, Notal, Optos, Centervue, Heidelberg Engineering, AbbVie/Allergan, Amgen, Roche/Genentech, Novartis, Merck, 4DMT, Oxurion; Honoraria – Nidek, Heidelbery Engineering, Optos, Novartis, Biogen; Reimbursement – Optos; Participation on Data Safety Monitoring Board or Adivsory Board – Regeneron; Secretary – Macula Society; Trustee – Arvo, IntRIS; Research Instruments – Optos, Centervue, Heidelberg Engineering, Carl Zeiss Meditec, Topcon, Nidek; Grant Support – Carl Zeiss Meditec, NIH STTR/SBIR grant (Eyenuk) - investigator for Doheny subcontract.
E.I.: Research Support – The Lundquist Institute from California Community Foundation from Genentech Foundation, Eyenuk, Inc., and Norris Foundation; Participation on a Data Safety Monitoring Board or Advisory Board – City of Hope Medical Centerr (DSMB).
M.B.: Employee – Eyenuk, Inc.; Shares – Eyenuk, Inc.; Patents – US Patent 9008391, US Patent 9002085, US Patent 8885901, US Patent 8879813, and US Patent 11051693 assigned to Eyenuk, Inc.
C.R.: Employee – Eyenuk, Inc.; Shares – Eyenuk, Inc.; Patents – US Patent 9008391, US Patent 9002085, US Patent 8885901, US Patent 8879813, and US Patent 11051693 assigned to Eyenuk, Inc.
K.S.: Employee – Eyenuk, Inc.; Shares – Eyenuk, Inc.; Patents – US Patent 9008391, US Patent 9002085, US Patent 8885901, US Patent 8879813, and US Patent 11051693 assigned to Eyenuk, Inc.
The other author has no proprietary or commercial interest in any materials discussed in this article.
Supported in part by grants from the National Institutes of Health (NIH): 9SB1EY027241 (Eyenuk), 2R44EY026864 (Eyenuk), and EY01792 (Core Grant University of Illinois at Chicago), unrestricted grant from Research to Prevent Blindness (University of Illinois at Chicago) and in part by Eyenuk, Inc., Los Angeles, California.
HUMAN SUBJECTS: Human subjects were included in this study.
Approval from the University of Illinois at Chicago instituional review board was obtained and the study was conducted in adherence to the tenets of the Declaration of Helsinki. Following IRB approval and informed consent, patients were deemed eligible if they were diagnosed with diabetes mellitus, were 18 years of age or older and could tolerate fundus photography.
No animal subjects were used in this study.
Author Contributions:
Conception and design: Bhaskaranand, Ramachandra, Solanki
Analysis and interpretation: Lim, Regillo, Sadda, Ipp, Bhaskaranand, Ramachandra, Solanki
Data collection: Lim, Regillo, Sadda, Ipp, Bhaskaranand, Ramachandra, Solanki
Obtained funding: Bhaskaranand, Ramachandra, Solanki
Overall responsibility: Lim, Bhaskaranand
Identification
Copyright
User license
Creative Commons Attribution (CC BY 4.0) |
Permitted
- Read, print & download
- Redistribute or republish the final article
- Text & data mine
- Translate the article
- Reuse portions or extracts from the article in other works
- Sell or re-use for commercial purposes
Elsevier's open access license policy