Since the Artificial Intelligence Committee of the American Society of Retina Specialists developed the initial task force report in 2020, the artificial intelligence (AI) field has seen further adoption of US Food and Drug Administration–approved AI platforms and significant development of AI for various retinal conditions. With expansion of this technology comes further areas of challenges, including the data sources used in AI, the democracy of AI, commercialization, bias, and the need for provider education on the technology of AI. The overall focus of this committee report is to explore these recent issues as they relate to the continued development of AI and its integration into ophthalmology and retinal practice.
HeydonPEganCBolterL, et al. Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients. Br J Ophthalmol. 2021;105:723-728.
2.
FauwJDLedsamJRRomera-ParedesB, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med. 2018;24:1342-1350.
3.
AbràmoffMDLouYErginayA, et al. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophth Vis Sci. 2016;57:5200-5206.
4.
AbràmoffMDLavinPTBirchMShahNFolkJC.Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. Npj Digital Medicine. 2018;1:39.
5.
GulshanVPengLCoramM, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402-2410.
6.
TingDSWCheungCY-LLimG, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318:2211-2223.
7.
SchleglTWaldsteinSMBogunovicH, et al. Fully automated detection and quantification of macular fluid in OCT using deep learning. Ophthalmology. 2018;125:549-558.
8.
BurlinaPMJoshiNPekalaMPachecoKDFreundDEBresslerNM.Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 2017;135:1170.
9.
Schmidt-ErfurthUWaldsteinSMKlimschaS, et al. Prediction of individual disease conversion in early AMD using artificial intelligence. Invest Ophth Vis Sci. 2018; 59:3199-3208.
10.
PoplinRVaradarajanAVBlumerK, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng. 2018;2:158-164.
11.
KorotEPontikosNLiuX, et al. Predicting sex from retinal fundus photographs using automated deep learning. Sci Rep. 2021;11:10286.
12.
ArcaduFBenmansourFMaunzA, et al. Deep learning predicts OCT measures of diabetic macular thickening from color fundus photographs. Invest Ophthalmol Vis Sci. 2019;60:852-857.
13.
YangJZhangCWangEChenYYuW.Utility of a public-available artificial intelligence in diagnosis of polypoidal choroidal vasculopathy. Graefe’s Archive Clin Exp Ophthalmol. 2020;258:17-21.
14.
BurlinaPMJoshiNPachecoKDFreundDEKongJBresslerNM.Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration. JAMA Ophthalmol. 2018;136:1359.
15.
TalcottKEKimJEModiYMoshfeghiDMSinghRP.The American society of retina specialists artificial intelligence task force report. J Vitreoretin Dis. 2020;4:312-319.
DengJDongWSocherRLiL-JLiKFei-FeiL. ImageNet: a large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL. IEEE; 2009:248-255.
18.
LeeAYCampbellJPHwangTSLumFChewEY; American Academy of Ophthalmology. Recommendations for standardization of images in ophthalmology. Ophthalmology. 2021;128:969-970.
19.
LeeAYSaddaSLumF.Joint American Academy of Ophthalmology and Association for Research in Vision and Ophthalmology policy statement: the time for digital imaging standards implementation is now. Ophthalmology. 2022;129:1229-1231.
20.
TrivediARobinsonCBlazesM, et al. Deep learning models for COVID-19 chest x-ray classification: preventing shortcut learning using feature disentanglement. PLoS One. 2022;17:e0274098.
21.
CuadrosJBresnickG.EyePACS: an adaptable telemedicine system for diabetic retinopathy screening. J Diabetes Sci Technol. 2009;3:509-516.
22.
KermanyDSGoldbaumMCaiW, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 2018;172:1122-1131.e9.
23.
KhanSMLiuXNathS, et al. A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability. Lancet Digit Health. 2021;3:e51–e66.
24.
WuYOlvera-BarriosAYanagiharaR, et al. Training deep learning models to work on multiple devices by cross-domain learning with no additional annotations. Ophthalmology. 2023;130:213-222.
25.
CastelvecchiD.Is facial recognition too biased to be let loose?Nature. 2020;587:347-349.
26.
ObermeyerZPowersBVogeliCMullainathanS.Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366:447-453.
27.
BurlinaPJoshiNPaulWPachecoKDBresslerNM.Addressing artificial intelligence bias in retinal diagnostics. Transl Vis Sci Technol. 2021;10:13.
NorgeotBQuerGBeaulieu-JonesBK, et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat Med. 2020;26:1320-1324.
31.
IbrahimHLiuXDennistonAK.Reporting guidelines for artificial intelligence in healthcare research. Clin Exp Ophthalmol. 2021;49:470-476.
32.
MaslejNFattoriniLBrynjolfssonE, et al. The AI index report: measuring trends in artificial intelligence. 2023. Accessed January 25, 2023. https://aiindex.stanford.edu/report/
WhitfillJTKalpasEGarcia-FilionP.Reuniting long lost cousins: a novel curriculum in imaging informatics for clinical informatics fellows. J Digit Imaging. 2022;35:876-880.
40.
MakeevaVVeyBCookT, et al. Imaging informatics fellowship curriculum: a survey to identify core topics and potential inter-program areas of collaboration. J Digit Imaging. 2020;33:547-553.
HopkinsJJKeanePABalaskasK.Delivering personalized medicine in retinal care: from artificial intelligence algorithms to clinical application. Curr Opin Ophthalmol. 2020;31:329-336.
51.
NathSRahimyEKrasAKorotE.Toward safer ophthalmic artificial intelligence via distributed validation on real-world data. Curr Opin Ophthalmol. 2023;34:459-463.
52.
FaesLWagnerSKFuDJ, et al. Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility study. Lancet Digit Health. 2019;1:e232-e242.
53.
KorotEGuanZFerrazD, et al. Code-free deep learning for multi-modality medical image classification. Nat Mach Intell. 2021;3:288-298.
54.
AntakiFKahwatiGSebagJ, et al. Predictive modeling of proliferative vitreoretinopathy using automated machine learning by ophthalmologists without coding experience. Sci Rep. 2020;10:19528.
55.
LeeJ-HKimY-TLeeJ-BJeongS-N.A performance comparison between automated deep learning and dental professionals in classification of dental implant systems from dental imaging: a multi-center study. Diagnostics. 2020;10:910.
MahajanDGirshickRRamanathanV, et al. Exploring the limits of weakly supervised pretraining. Arxiv2018. doi:10.48550/arxiv.1805.00932
58.
KrauseJGulshanVRahimyE, et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology. 2017;125:1264-1272.
59.
XieQLuongM-THovyELeQV.Self-training with noisy student improves ImageNet classification. Arxiv2019. doi:10.48550/arxiv.1911.04252
60.
NguyenQValizadeganHHauskrechtM.Learning classification models with soft-label information. J Am Med Inform Assoc. 2014;21(3):501-508.
61.
KorotEWoodEWeinerASimDATreseM.A renaissance of teleophthalmology through artificial intelligence. Eye (Lond). 2018;33:861-863.
62.
BellemoVLimZWLimG, et al. Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study. Lancet Digit Health. 2019;1:e35-e44.
63.
MeyALoogM. A soft-labeled self-training approach. 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico. IEEE. 2016:2604-2609.
64.
TrigueroIGarcíaSHerreraF.Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. Knowl Inf Syst. 2015;42:245-284.
65.
ChenTKornblithSNorouziMHintonG.A simple framework for contrastive learning of visual representations. Arxiv2020. doi:10.48550/arxiv.2002.05709
66.
KorotEGonçalvesMBHuemerJ, et al. Clinician-driven AI: code-free self-training on public data for diabetic retinopathy referral. JAMA Ophthalmol. 2023;141:1029-1036.
67.
VithlaniJHawksworthCElvidgeJAyikuLDawoudD.Economic evaluations of artificial intelligence-based healthcare interventions: a systematic literature review of best practices in their conduct and reporting. Front Pharmacol. 2023;14:1220950.
68.
RajeshAEDavidsonOQLeeCSLeeAY.Artificial intelligence and diabetic retinopathy: AI framework, prospective studies, head-to-head validation, and cost-effectiveness. Diabetes Care. 2023;46:1728-1739.
69.
RuamviboonsukPRuamviboonsukVTiwariR.Recent evidence of economic evaluation of artificial intelligence in ophthalmology. Curr Opin Ophthalmol. 2023;34:449-458.
70.
MorrisonSLDukhovnyDChanRVPChiangMFCampbellJP.Cost-effectiveness of Artificial Intelligence–based retinopathy of prematurity screening. JAMA Ophthalmol. 2022;140:401-409.
71.
CampbellJPSinghPReddTK, et al. Applications of artificial intelligence for retinopathy of prematurity screening. Pediatrics. 2021;147:e2020016618.
72.
MoshfeghiDM.Systemic solutions in retinopathy of prematurity. Am J Ophthalmol. 2018;193:xiv-xviii.
73.
FiersonWMCaponeA; American Academy of Pediatrics Section on Ophthalmology, et al. Telemedicine for evaluation of retinopathy of prematurity. Pediatrics. 2015;135:e238-e254.
74.
Barrero-CastilleroACorwinBKVanderVeenDKWangJC.Workforce shortage for retinopathy of prematurity care and emerging role of telehealth and artificial intelligence. Pediatr Clin North Am. 2020;67:725-733.
