Age-related Macular Degeneration Screening Research Articles

IDF23-0247 An AI-Assisted System for Early Screening of Age-Related Macular Degeneration (ARMD) from Real-World Fundus Images

IDF23-0247 An AI-Assisted System for Early Screening of Age-Related Macular Degeneration (ARMD) from Real-World Fundus Images

Using the Amsler Grid Test for Age-Related Macular Degeneration Screening.

To evaluate the use of the Amsler grid test (AGT) in screening for age-related macular degeneration (AMD), one of the most common causes of blindness, in primary healthcare settings. The AGT was applied to 700 eyes of 355 people aged 50 and over who applied to a family health center in Ankara and had no eye complaints. The test was considered positive if the lines on the AGT card were seen as broken or curved, there was a difference in shape or size between the squares, or a color change or blurring was described in any area. An ophthalmologist was consulted if the AGT was positive in one or both eyes. Patients considered suitable by ophthalmologists were evaluated with optical coherence tomography. AGT results were compared with ophthalmologist examination and tomography findings in terms of AMD detection. The AGT was positive in 97 (13.9%) and negative in 603 (86.1%) out of 700 eyes included in the study. A total of 184 eyes, 79 with a positive AGT and 105 eyes with a negative test, were evaluated by an ophthalmologist. As a result of examinations and tests performed by ophthalmologists, AMD was detected in a total of 67 eyes: 42 of 79 eyes with positive AGT and 25 of 105 eyes with negative AGT but referred to an ophthalmologist for different reasons. In our study, the AGT had 62.7% sensitivity and 68.4% specificity. The AGT is an inexpensive and easily applicable test. Although moderate sensitivity and specificity were found in our study; further studies are needed to evaluate the suitability of its use for AMD screening in primary care with limited facilities.

Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening

Age-related macular degeneration (AMD) is the leading cause of central vision impairment among the elderly. Effective and accurate AMD screening tools are urgently needed. Indocyanine green angiography (ICGA) is a well-established technique for detecting chorioretinal diseases, but its invasive nature and potential risks impede its routine clinical application. Here, we innovatively developed a deep-learning model capable of generating realistic ICGA images from color fundus photography (CF) using generative adversarial networks (GANs) and evaluated its performance in AMD classification. The model was developed with 99,002 CF-ICGA pairs from a tertiary center. The quality of the generated ICGA images underwent objective evaluation using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity measures (SSIM), etc., and subjective evaluation by two experienced ophthalmologists. The model generated realistic early, mid and late-phase ICGA images, with SSIM spanned from 0.57 to 0.65. The subjective quality scores ranged from 1.46 to 2.74 on the five-point scale (1 refers to the real ICGA image quality, Kappa 0.79–0.84). Moreover, we assessed the application of translated ICGA images in AMD screening on an external dataset (n = 13887) by calculating area under the ROC curve (AUC) in classifying AMD. Combining generated ICGA with real CF images improved the accuracy of AMD classification with AUC increased from 0.93 to 0.97 (P < 0.001). These results suggested that CF-to-ICGA translation can serve as a cross-modal data augmentation method to address the data hunger often encountered in deep-learning research, and as a promising add-on for population-based AMD screening. Real-world validation is warranted before clinical usage.

Clinical effectiveness of screening for age-related macular degeneration: A systematic review

Introduction Age-related macular degeneration (AMD) is an eye disease that occurs in patients over 50 years old. Early diagnosis enables timely treatment to stabilize disease progression. However, the fact that the disease is asymptomatic in its early stages can delay treatment until it progresses. As such, screening in specific contexts can be an early detection tool to reduce the clinical and social impact of the disease. Objective Assess the effectiveness of screening methods for early detection of AMD in adults aged 50 years or older. Methods A systematic review of comparative observational studies on AMD screening methods in those aged 50 years or older, compared with no screening or any other strategy. A literature search was conducted in the MEDLINE (via PubMed), Embase, Cochrane Library and Lilacs database. Results A total of 5,290 studies were identified, three of which met the inclusion criteria and were selected for the systematic review. A total of 8,733 individuals (16,780 eyes) were included in the analysis. The screening methods assessed were based on optical coherence tomography (OCT) compared with color fundus photography, and OCT and telemedicine testing compared to a standard eye exam. Conclusion The systematized data are limited and only suggest satisfactory performance in early screening of the population at risk of developing AMD. OCT and the telemedicine technique showed promising results in AMD screening. However, methodological problems were identified in the studies selected and the level of evidence was considered low.

A deep learning model for generating fundus autofluorescence images from color fundus photography

BackgroundFundus Autofluorescence (FAF) is a valuable imaging technique used to assess metabolic alterations in the retinal pigment epithelium (RPE) associated with various age-related and disease-related changes. The practical uses of FAF are ever-growing. This study aimed to evaluate the effectiveness of a generative deep learning (DL) model in translating color fundus (CF) images into synthetic FAF images and explore its potential for enhancing screening of age-related macular degeneration (AMD). MethodsA generative adversarial network (GAN) model was trained on pairs of CF and FAF images to generate synthetic FAF images. The quality of synthesized FAF images was assessed objectively by common generation metrics. Additionally, the clinical effectiveness of the generated FAF images in AMD classification was evaluated by measuring the area under the curve (AUC), using the LabelMe dataset. ResultsA total of 8410 FAF images from 2586 patients were analyzed. The synthesized FAF images exhibited an impressive objectively assessed quality, achieving a multi-scale structural similarity index (MS-SSIM) of 0.67. When evaluated on the LabelMe dataset, the combination of generated FAF images and CF images resulted in a noteworthy improvement in AMD classification accuracy, with the AUC increasing from 0.931 to 0.968. ConclusionsThis study presents the first attempt to use a generative deep learning model to create authentic and high-quality FAF images from CF images. The incorporation of the translated FAF images on top of CF images improved the accuracy of AMD classification. Overall, this study presents a promising approach to enhance large-scale AMD screening.

Synthetic artificial intelligence using generative adversarial network for retinal imaging in detection of age-related macular degeneration.

Age-related macular degeneration (AMD) is one of the leading causes of vision impairment globally and early detection is crucial to prevent vision loss. However, the screening of AMD is resource dependent and demands experienced healthcare providers. Recently, deep learning (DL) systems have shown the potential for effective detection of various eye diseases from retinal fundus images, but the development of such robust systems requires a large amount of datasets, which could be limited by prevalence of the disease and privacy of patient. As in the case of AMD, the advanced phenotype is often scarce for conducting DL analysis, which may be tackled via generating synthetic images using Generative Adversarial Networks (GANs). This study aims to develop GAN-synthesized fundus photos with AMD lesions, and to assess the realness of these images with an objective scale. To build our GAN models, a total of 125,012 fundus photos were used from a real-world non-AMD phenotypical dataset. StyleGAN2 and human-in-the-loop (HITL) method were then applied to synthesize fundus images with AMD features. To objectively assess the quality of the synthesized images, we proposed a novel realness scale based on the frequency of the broken vessels observed in the fundus photos. Four residents conducted two rounds of gradings on 300 images to distinguish real from synthetic images, based on their subjective impression and the objective scale respectively. The introduction of HITL training increased the percentage of synthetic images with AMD lesions, despite the limited number of AMD images in the initial training dataset. Qualitatively, the synthesized images have been proven to be robust in that our residents had limited ability to distinguish real from synthetic ones, as evidenced by an overall accuracy of 0.66 (95% CI: 0.61-0.66) and Cohen's kappa of 0.320. For the non-referable AMD classes (no or early AMD), the accuracy was only 0.51. With the objective scale, the overall accuracy improved to 0.72. In conclusion, GAN models built with HITL training are capable of producing realistic-looking fundus images that could fool human experts, while our objective realness scale based on broken vessels can help identifying the synthetic fundus photos.

Age-Related Macular Degeneration: An Exponentially Emerging Imminent Threat of Visual Impairment and Irreversible Blindness.

Age-related macular degeneration (AMD) is a significant cause of blindness globally. With the exponential rise in the aging population, AMD is the third leading cause of visual impairment worldwide. Neovascular AMD (nAMD; Wet AMD) and geographical atrophy (GA, late-stage dry AMD) are the advanced AMD accountable for substantial cases of visual deterioration among the elderly. Our review of the literature depicted that notable risk factors include cigarette smoking, nutritional elements, cardiovascular disorders, and genetic markers, including genes regulating complement, lipid, and angiogenic pathways. Some studies have suggested a relative decline in the proportion of AMD cases in the last two decades attributable to novel diagnostic and therapeutic modalities. Accurate diagnosis is the result of a combination of clinical examination and imaging techniques, including retinal photography, angiography, and optical coherence tomography. The incorporation of dietary antioxidant supplements, explicitly lutein, slows the progression of the disease in advanced stages. The induction of vascular endothelial growth factor (VEGF) inhibitors in the treatment of neovascular AMD, often combined with other modalities, has shown an immensely favorable prognosis. Research to integrate gene therapy and regenerative techniques using stem cells is underway to further mitigate AMD-associated morbidity. It is imperative to establish screening and therapeutic guidelines for AMD to curtail the future social and financial burden and improve the diminishing quality of life among the elderly.

Brain Activity in Age-Related Macular Degeneration Patients From the Perspective of Regional Homogeneity: A Resting-State Functional Magnetic Resonance Imaging Study.

ObjectiveIn this study, the regional homogeneity (ReHo) method was used to investigate levels of cerebral homogeneity in individuals with age-related macular degeneration (AMD), with the aim of exploring whether these measures are associated with clinical characteristics.Materials and MethodsPatients with AMD and healthy controls attending the First Affiliated Hospital of Nanchang University were invited to participate. Resting state functional magnetic resonance images were recorded in each participant and levels of synchronous neural activity were evaluated using ReHo. Receiver operating characteristic (ROC) curves were used to evaluate the sensitivity and specificity of this method.ResultsEighteen patients with AMD (9 males and 9 females) and 15 healthy controls (HCs) were recruited. The two groups were approximately matched in age, gender and weight. Compared with controls, the ReHo values were significantly higher in the AMD group at the limbic lobe and parahippocampal gyrus, and were significantly reduced at the cingulate gyrus, superior frontal gyrus, middle frontal gyrus, inferior parietal lobule, and precentral gyrus. Mean ReHo values at the cingulate gyrus and the superior frontal gyrus were negatively correlated with clinical symptoms.ConclusionBrain neural homogeneity dysfunction is a manifestation of visual pathways in AMD patients, and may be one of the pathological mechanisms of chronic vision loss, anxiety and depression in AMD patients. In addition, the ReHo data may be useful for early screening for AMD.

Digital health in medicine: Important considerations in evaluating health economic analysis

Digital health in medicine: Important considerations in evaluating health economic analysis

Cost-effectiveness and cost-utility of traditional and telemedicine combined population-based age-related macular degeneration and diabetic retinopathy screening in rural and urban China

SummaryBackgroundTo assess the cost-effectiveness and cost-utility of a population-level traditional and telemedicine combined age-related macular degeneration (AMD) and diabetic retinopathy (DR) screening program in rural and urban China.MethodsDecision-analytic Markov models were conducted to evaluate the costs and benefits of traditional and telemedicine combined AMD and DR screening from a societal perspective. A cohort of all participants aged 50 years old and above was followed through a total of 30 1-year Markov cycles. Separate analyses were performed for rural and urban settings. Relevant parameters such as the prevalence of AMD and DR, transition probability, compliance with screening and treatment, screening sensitivity, specificity, utility, and mortality were collected from published studies specific to China, other Asian counties' studies, or unpublished data sources such as the National Committee for the Prevention of Blindness. Costs of screening, full examination, and treatment come from the real medical environments and unified pricing of Beijing Municipal Medical Insurance Bureau. Primary outcomes were incremental cost-utility ratios (ICURs) using quality-adjusted life-years (QALYs) and incremental cost-effectiveness ratios (ICERs) using years of blindness avoided. One-way deterministic and simulated probabilistic sensitivity analyses were conducted to reflect uncertainty.FindingsUnder the status quo, the total expected medical costs for a 50-year-old patient with AMD or DR were $869·59 and $1,514·18 in rural and urban settings, respectively. Both traditional and telemedicine screening were highly cost-effective. In rural settings, ICURs were $191 (95% confidence interval [CI]: $66 to $239) and $199 (95% CI: $-12 to $217), and ICERs were $2,436 (95% CI: $1,089 to $3,254) and $2,441 (95% CI: $1,452 to $3,900) for traditional and telemedicine screening separately. Even more surprising, both screening strategies dominated no screening in urban settings. Our results were insensitive and robust to extensive sensitivity analyses. Among all acceptable screening intervals (from 1 to 5 years), annual screening could not only produce biggest benefits but also keep ICERs less than three times and one time the per capita gross domestic product (GDP) in rural and urban settings separately. When compared with traditional screening, ICERs of telescreening were less than three times the per capita GDP in rural settings ($2,559 to $8,809) and less than one time the per capita GDP in urban settings (less than $5,564), annual telescreening produced the biggest benefits, it could avert 119 and 270 years of blindness in rural and urban areas separately when 100,000 people were screened.InterpretationWe performed decision-analytic Markov models for combined AMD and DR screening in rural and urban China, and the results showed that population-level combined screening for AMD and DR is likely to be highly cost-effective in both rural and urban China for people over 50 years old. Optimal screening may have an interval of every year based on teleophthalmology platforms. In the future, China should pay more attention to chronic eye diseases and the government should establish a sound chronic disease management system and make every patient enjoy equal medical services.FundingNational Natural Science Foundation of China, NSFC (82171051); the Major Innovation Platform of Public Health & Disease Control and Prevention, Renmin University of China and Beijing Nova program (Z191100001119072).

Image enhancement of color fundus photographs for age-related macular degeneration: the Shanghai Changfeng Study.

To develop and evaluate a new fundus image optimization software based on red, green, blue channels (RGB) for the evaluation of age-related macular degeneration (AMD) in the Chinese population. Fundus images that were diagnosed as AMD from the Shanghai Changfeng Study database were analyzed to develop a standardized optimization procedure. Image brightness, contrast, and color balance were measured. Differences between central lesion area and normal retinal area under different image brightness, contrast, and color balance were observed. The optimal optimization parameters were determined based on the visual system to avoid image distortion. A paired-sample diagnostic test was used to evaluate the enhancement software. Fundus optical coherence tomography (OCT) was used as the gold standard. Diagnostic performances were compared between original images and optimized images using McNemar's test. A fundus image optimization procedure was developed using 86 fundus images of 74 subjects diagnosed with AMD. By observing gray-scale images, choroid can be best displayed in red channel and retina in green channel was found. There was limited information in blue channel. Totally 104 participants were included in the paired sample diagnostic test to assess the performance of the optimization software. After the image enhancement, sensitivity increased from 74% to 88% (P=0.008), specificity decreased slightly from 88% to 84% (P=0.500), and Youden index increased by 0.11. The standardized image optimization software increases diagnostic sensitivity and may help ophthalmologists in AMD diagnosis and screening.

Diagnostic accuracy of teleretinal screening for detection of diabetic retinopathy and age-related macular degeneration: a systematic review and meta-analysis

ObjectiveTo evaluate the diagnostic accuracy of teleretinal screening compared with face-to-face examination for detection of diabetic retinopathy (DR) and age-related macular degeneration (AMD).Methods and analysisThis study adhered to the Preferred...

Real-world effectiveness of screening programs for age-related macular degeneration: amended Japanese specific health checkups and augmented screening programs with OCT or AI.

To investigate the effectiveness of screening and subsequent intervention for age-related macular degeneration (AMD) in Japan. Best-case-scenario analysis using a Markov model. The clinical effectiveness and cost-effectiveness of screening for AMD were assessed by calculating the reduction proportion of blindness and the incremental cost-effectiveness ratio (ICER). The Markov model simulation began at screening at the age of 40years and ended at screening at the age of 90years. The first-eye and second-eye combined model assumed annual state-transition probabilities in the development and treatment of AMD. Data on prevalence, morbidity, transition probability, utility value, and treatment costs were obtained from previously published reports. Sensitivity analysis was performed to assess the influence of the parameters. In the base-case analysis, screening for AMD every 5years, beginning at age 40years and ending at age 74years (reflecting the screening ages of the current Japanese legal "Specific Health Checkups") showed a decrease of 40.7% in the total number of blind patients. The screening program reduced the number of blind people more than did the additional AREDS/AREDS2 formula supplement intake. However, the ICER of screening versus no screening was ¥9,846,411/QALY, which was beyond what people were willing to pay (WTP) in Japan. Sensitivity analysis revealed that neither OCT nor AI improved the ICER, but the scenario in which the prevalence of smoking decreased by 30% improved the ICER (¥4,655,601/QALY) to the level under the WTP. Ophthalmologic screening for AMD is highly effective in reducing blindness but is not cost-effective, as demonstrated by a Markov model based on real-world evidence from Japan.

Enhance Contrast and Balance Color of Retinal Image

This paper proposes a simple and effective retinal fundus image simulation modeling to enhance contrast and adjust the color balance for symmetric information in biomedicine. The aim of the study is for reliable diagnosis of AMD (age-related macular degeneration) screening. The method consists of a few simple steps. Firstly, local image contrast is refined with the CLAHE (Contrast Limited Adaptive Histogram Equalization) technique by operating CIE L*a*b* color space. Then, the contrast-enhanced image is stretched and rescaled by a histogram scaling equation to adjust the overall brightness offsets of the image and standardize it to Hubbard’s retinal image brightness range. The proposed method was assessed with retinal images from the DiaretDB0 and STARE datasets. The findings in the experimentation section indicate that the proposed method results in delightful color naturalness along with a standard color of retinal lesions.

Combined automated screening for age-related macular degeneration and diabetic retinopathy in primary care settings.

Background:Age-related macular degeneration (AMD) and diabetic retinopathy (DR) are among the leading causes of blindness in the United States and other developed countries. Early detection is the key to prevention and effective treatment. We have built an artificial intelligence-based screening system which utilizes a cloud-based platform for combined large scale screening through primary care settings for early diagnosis of these diseases.Methods:iHealthScreen Inc., an independent medical software company, has developed automated AMD and DR screening systems utilizing a telemedicine platform based on deep machine learning techniques. For both diseases, we prospectively imaged both eyes of 340 unselected non-dilated subjects over 50 years of age. For DR specifically, 152 diabetic patients at New York Eye and Ear faculty retina practices, ophthalmic and primary care clinics in New York city with color fundus cameras. Following the initial review of the images, 308 images with other confounding conditions like high myopia and vascular occlusion, and poor quality were excluded, leaving 676 eligible images for AMD and DR evaluation. Three ophthalmologists evaluated each of the images, and after adjudication, the patients were determined referrable or non-referable for AMD DR. Concerning AMD, 172 were labeled referable (intermediate or late), and 504 were non-referable (no or early). Concurrently, regarding DR, 33 were referable (moderate or worse), and 643 were non-referable (none or mild). All images were uploaded to iHealthScreen’s telemedicine platform and analyzed by the automated systems for both diseases. The system performances are tested on per eye basis with sensitivity, specificity, accuracy, and kappa scores with respect to the professional graders.Results:In identifying referable DR, the system achieved a sensitivity of 97.0% and a specificity of 96.3%, and a kappa score of 0.70 on this prospective dataset. For AMD, the sensitivity was 86.6%, the specificity of 92.1%, and a kappa score of 0.76.Conclusions:The AMD and DR screening tools achieved excellent performance operating together to identify two retinal diseases prospectively in mixed datasets, demonstrating the feasibility of such tools in the early diagnosis of eye diseases. These early screening tools will help create an even more comprehensive system capable of being trained on other retinal pathologies, a goal within reach for public health deployment.

Diagnostic accuracy of current machine learning classifiers for age-related macular degeneration: a systematic review and meta-analysis.

The objective of this study was to systematically review and meta-analyze the diagnostic accuracy of current machine learning classifiers for age-related macular degeneration (AMD). Artificial intelligence diagnostic algorithms can automatically detect and diagnose AMD through training data from large sets of fundus or OCT images. The use of AI algorithms is a powerful tool, and it is a method of obtaining a cost-effective, simple, and fast diagnosis of AMD. MEDLINE, EMBASE, CINAHL, and ProQuest Dissertations and Theses were searched systematically and thoroughly. Conferences held through Association for Research in Vision and Ophthalmology, American Academy of Ophthalmology, and Canadian Society of Ophthalmology were searched. Studies were screened using Covidence software and data on sensitivity, specificity and area under curve were extracted from the included studies. STATA 15.0 was used to conduct the meta-analysis. Our search strategy identified 307 records from online databases and 174 records from gray literature. Total of 13 records, 64,798 subjects (and 612,429 images), were used for the quantitative analysis. The pooled estimate for sensitivity was 0.918 [95% CI: 0.678, 0.98] and specificity was 0.888 [95% CI: 0.578, 0.98] for AMD screening using machine learning classifiers. The relative odds of a positive screen test in AMD cases were 89.74 [95% CI: 3.05-2641.59] times more likely than a negative screen test in non-AMD cases. The positive likelihood ratio was 8.22 [95% CI: 1.52-44.48] and the negative likelihood ratio was 0.09 [95% CI: 0.02-0.52]. The included studies show promising results for the diagnostic accuracy of the machine learning classifiers for AMD and its implementation in clinical settings.

The Relationship between Age-Related Macular Degeneration and Cardiovascular Disease: A Meta-Analysis.

Background:Age-related macular degeneration (AMD) and cardiovascular disease (CVD) share pathogenic mechanisms, and their lead-lag relationship remains unclear. We performed a meta-analysis of data from longitudinal studies to evaluate the interactive association between age-related macular degeneration (AMD) and cardiovascular disease (CVD).Methods:A literature search was performed in PubMed, Embase, and Cochrane Library up to Feb 2019. Estimates were pooled by study quality and type of AMD and CVD. Publication bias was assessed by Begg’s test.Results:We identified nine studies for the risk of AMD in CVD and ten studies for the risk of CVD in AMD. Overall, evidence for the risk of CVD in AMD patients was most robust. Both early and late AMD preceded CVD, but more solid significance existed in late AMD. Among the types of CVD, stroke was more tightly associated with AMD than coronary heart disease. Publication bias was not significant in either direction.Conclusion:AMD is a risk factor for CVD, which is primarily driven by the increased risk of stroke in patients with late AMD. Moreover, these results suggested that AMD treatment and screening for CVD in AMD patients may have unexplored clinical benefits.

Digital Technology for AMD Management in the Post-COVID-19 New Normal.

The COVID-19 pandemic has put strain on healthcare systems and the availability and allocation of healthcare manpower, resources and infrastructure. With immediate priorities to protect the health and safety of both patients and healthcare service providers, ophthalmologists globally were advised to defer nonurgent cases, while at the same time managing sight-threatening conditions such as neovascular Age-related Macular Degeneration (AMD). The management of AMD patients both from a monitoring and treatment perspective presents a particular challenge for ophthalmologists. This review looks at how these pressures have encouraged the acceptance and speed of adoption of digitalization. A literature review was conducted on the use of digital technology during COVID-19 pandemic, and on the transformation of medicine, ophthalmology and AMD screening through digitalization. In the management of AMD, the implementation of artificial intelligence and "virtual clinics" have provided assistance in screening, diagnosis, monitoring of the progression and the treatment of AMD. In addition, hardware and software developments in home monitoring devices has assisted in self-monitoring approaches. Digitalization strategies and developments are currently ongoing and underway to ensure early detection, stability and visual improvement in patients suffering from AMD in this COVID-19 era. This may set a precedence for the post COVID-19 new normal where digital platforms may be routine, standard and expected in healthcare delivery.

Data Mining for AMD Screening: A Classification Based Approach

© 2014, UK Simulation Society. All rights reserved. This paper investigates the use of three alternative approaches to classifying retinal images. The novelty of these approaches is that they are not founded on individual lesion segmentation for feature generation, instead use encodings focused on the entire image. Three different mechanisms for encoding retinal image data were considered: (i) time series, (ii) tabular and (iii) tree based representations. For the evaluation two publically available, retinal fundus image data sets were used. The evaluation was conducted in the context of Age-related Macular Degeneration (AMD) screening and according to statistical significance tests. Excellent results were produced: Sensitivity, specificity and accuracy rates of 99% and over were recorded, while the tree based approach has the best performance with a sensitivity of 99.5%. Further evaluation indicated that the results were statistically significant. The excellent results indicated that these classification systems are ideally suited to large scale AMD screening processes.

Artificial Intelligence to Stratify Severity of Age-Related Macular Degeneration (AMD) and Predict Risk of Progression to Late AMD.

PurposeTo build and validate artificial intelligence (AI)-based models for AMD screening and for predicting late dry and wet AMD progression within 1 and 2 years.MethodsThe dataset of the Age-related Eye Disease Study (AREDS) was used to train and validate our prediction model. External validation was performed on the Nutritional AMD Treatment-2 (NAT-2) study.First StepAn ensemble of deep learning screening methods was trained and validated on 116,875 color fundus photos from 4139 participants in the AREDS study to classify them as no, early, intermediate, or advanced AMD and further stratified them along the AREDS 12 level severity scale. Second step: the resulting AMD scores were combined with sociodemographic clinical data and other automatically extracted imaging data by a logistic model tree machine learning technique to predict risk for progression to late AMD within 1 or 2 years, with training and validation performed on 923 AREDS participants who progressed within 2 years, 901 who progressed within 1 year, and 2840 who did not progress within 2 years. For those found at risk of progression to late AMD, we further predicted the type (dry or wet) of the progression of late AMD.ResultsFor identification of early/none vs. intermediate/late (i.e., referral level) AMD, we achieved 99.2% accuracy. The prediction model for a 2-year incident late AMD (any) achieved 86.36% accuracy, with 66.88% for late dry and 67.15% for late wet AMD. For the NAT-2 dataset, the 2-year late AMD prediction accuracy was 84%.ConclusionsValidated color fundus photo-based models for AMD screening and risk prediction for late AMD are now ready for clinical testing and potential telemedical deployment.Translational RelevanceNoninvasive, highly accurate, and fast AI methods to screen for referral level AMD and to predict late AMD progression offer significant potential improvements in our care of this prevalent blinding disease.