Predicting Progression to Advanced Age-Related Macular Degeneration from Clinical, Genetic, and Lifestyle Factors Using Machine Learning

Intergrader Agreement in Grading Optical Coherence Tomography Morphologic Features in Eyes With Intermediate Nonexudative Age-Related Macular Degeneration

Purpose

To determine the reliability of a nine-point summary scale for grading intermediate age-related macular degeneration (AMD) image morphologic features based on the Early Treatment Diabetic Retinopathy Study (ETDRS) grid.

Methods

Two trained graders independently divided spectral domain-optical coherence tomography (SD-OCT) scans into nine subfields and then graded each subfield for the presence of intraretinal hyperreflective foci (HRF), reticular pseudodrusen (RPD), and incomplete or complete retinal pigment epithelium and outer retinal atrophy (iRORA or cRORA). Grading results were assessed by summing the subfield grades into a nine-point summary score and also by using an eye-level binary grade for presence of the finding in any subfield. Gwet's first-order agreement coefficient (AC1) was calculated to assess intergrader agreement.

Results

Images of 79 eyes from 52 patients were evaluated. Intergrader agreement was higher when the OCT grades were summarized with a nine-point summary score (Gwet's AC1 0.92, 0.89, 0.99, and 0.99 for HRF, RPD, iRORA, and cRORA, respectively) compared with the eye-level binary grade (Gwet's AC1 0.75, 0.76, 0.97, and 0.96 for HRF, RPD, iRORA, and cRORA, respectively), with significant differences detected for HRF and RPD.

Conclusions

The use of a nine-point summary score showed higher reliability in grading when compared to the binary subfield- and eye-level data, and thus may offer more precise estimation of AMD disease staging.

Translational Relevance

These findings suggest that a nine-point summary score could be a useful means of disease staging by using findings on OCT in clinical studies of AMD.

DeepAlienorNet: A deep learning model to extract clinical features from colour fundus photography in age-related macular degeneration

OBJECTIVE

This study aimed to develop a deep learning (DL) model, named 'DeepAlienorNet', to automatically extract clinical signs of age-related macular degeneration (AMD) from colour fundus photography (CFP).

METHODS AND ANALYSIS

The ALIENOR Study is a cohort of French individuals 77 years of age or older. A multi-label DL model was developed to grade the presence of 7 clinical signs: large soft drusen (>125 μm), intermediate soft (63-125 μm), large area of soft drusen (total area >500 μm), presence of central soft drusen (large or intermediate), hyperpigmentation, hypopigmentation, and advanced AMD (defined as neovascular or atrophic AMD). Prediction performances were evaluated using cross-validation and the expert human interpretation of the clinical signs as the ground truth.

RESULTS

A total of 1178 images were included in the study. Averaging the 7 clinical signs' detection performances, DeepAlienorNet achieved an overall sensitivity, specificity, and AUROC of 0.77, 0.83, and 0.87, respectively. The model demonstrated particularly strong performance in predicting advanced AMD and large areas of soft drusen. It can also generate heatmaps, highlighting the relevant image areas for interpretation.

CONCLUSION

DeepAlienorNet demonstrates promising performance in automatically identifying clinical signs of AMD from CFP, offering several notable advantages. Its high interpretability reduces the black box effect, addressing ethical concerns. Additionally, the model can be easily integrated to automate well-established and validated AMD progression scores, and the user-friendly interface further enhances its usability. The main value of DeepAlienorNet lies in its ability to assist in precise severity scoring for further adapted AMD management, all while preserving interpretability.

An Updated Simplified Severity Scale for Age-Related Macular Degeneration Incorporating Reticular Pseudodrusen: Age-Related Eye Disease Study Report Number 42

PURPOSE

To update the Age-Related Eye Disease Study (AREDS) simplified severity scale for risk of late age-related macular degeneration (AMD), including incorporation of reticular pseudodrusen (RPD), and to perform external validation on the Age-Related Eye Disease Study 2 (AREDS2).

DESIGN

Post hoc analysis of 2 clinical trial cohorts: AREDS and AREDS2.

PARTICIPANTS

Participants with no late AMD in either eye at baseline in AREDS (n = 2719) and AREDS2 (n = 1472).

METHODS

Five-year rates of progression to late AMD were calculated according to levels 0 to 4 on the simplified severity scale after 2 updates: (1) noncentral geographic atrophy (GA) considered part of the outcome, rather than a risk feature, and (2) scale separation according to RPD status (determined by validated deep learning grading of color fundus photographs).

MAIN OUTCOME MEASURES

Five-year rate of progression to late AMD (defined as neovascular AMD or any GA).

RESULTS

In the AREDS, after the first scale update, the 5-year rates of progression to late AMD for levels 0 to 4 were 0.3%, 4.5%, 12.9%, 32.2%, and 55.6%, respectively. As the final simplified severity scale, the 5-year progression rates for levels 0 to 4 were 0.3%, 4.3%, 11.6%, 26.7%, and 50.0%, respectively, for participants without RPD at baseline and 2.8%, 8.0%, 29.0%, 58.7%, and 72.2%, respectively, for participants with RPD at baseline. In external validation on the AREDS2, for levels 2 to 4, the progression rates were similar: 15.0%, 27.7%, and 45.7% (RPD absent) and 26.2%, 46.0%, and 73.0% (RPD present), respectively.

CONCLUSIONS

The AREDS AMD simplified severity scale has been modernized with 2 important updates. The new scale for individuals without RPD has 5-year progression rates of approximately 0.5%, 4%, 12%, 25%, and 50%, such that the rates on the original scale remain accurate. The new scale for individuals with RPD has 5-year progression rates of approximately 3%, 8%, 30%, 60%, and 70%, that is, approximately double for most levels. This scale fits updated definitions of late AMD, has increased prognostic accuracy, seems generalizable to similar populations, but remains simple for broad risk categorization.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Polygenic Risk Scores for Glaucoma Onset in the Ocular Hypertension Treatment Study

Importance

Primary open-angle glaucoma (POAG) is a highly heritable disease, with 127 identified risk loci to date. Polygenic risk score (PRS) may provide a clinically useful measure of aggregate genetic burden and improve patient risk stratification.

Objective

To assess whether a PRS improves prediction of POAG onset in patients with ocular hypertension.

Design, Setting, and Participants

This was a post hoc analysis of the Ocular Hypertension Treatment Study. Data were collected from 22 US sites with a mean (SD) follow-up of 14.0 (6.9) years. A total of 1636 participants were followed up from February 1994 to December 2008; 1077 participants were enrolled in an ancillary genetics study, of which 1009 met criteria for this analysis. PRS was calculated using summary statistics from the largest cross-ancestry POAG meta-analysis, with weights trained using 8 813 496 variants from 449 186 cross-ancestry participants in the UK Biobank. Data were analyzed from July 2022 to December 2023.

Exposures

From February 1994 to June 2002, participants were randomized to either topical intraocular pressure-lowering medication or close observation. After June 2002, both groups received medication.

Main Outcomes and Measures

Outcome measures were hazard ratios for POAG onset. Concordance index and time-dependent areas under the receiver operating characteristic curve were used to compare the predictive performance of multivariable Cox proportional hazards models.

Results

Of 1009 included participants, 562 (55.7%) were female, and the mean (SD) age was 55.9 (9.3) years. The mean (SD) PRS was significantly higher for 350 POAG converters (0.24 [0.95]) compared with 659 nonconverters (-0.12 [1.00]) (P < .001). POAG risk increased 1.36% (95% CI, 1.08-1.64) with each higher PRS decile, with conversion ranging from 9.52% (95% CI, 7.09-11.95) in the lowest PRS decile to 21.81% (95% CI, 19.37-24.25) in the highest decile. Comparison of low-risk and high-risk PRS tertiles showed a 2.0-fold increase in 20-year POAG risk for participants of European and African ancestries. In the subgroup randomized to delayed treatment, each increase in PRS decile was associated with a 0.52-year (95% CI, 0.01-1.03) decrease in age at diagnosis (P = .047). No significant linear association between PRS and age at POAG diagnosis was present in the early treatment group. Prediction models significantly improved with the addition of PRS as a covariate (C index = 0.77) compared with the Ocular Hypertension Treatment Study baseline model (C index = 0.75) (P < .001). Each 1-SD higher PRS conferred a mean hazard ratio of 1.25 (95% CI, 1.13-1.44) for POAG onset.

Conclusions and Relevance

Higher PRS was associated with increased risk for POAG in patients with ocular hypertension. The inclusion of a PRS improved the prediction of POAG onset.

Trial Registration

ClinicalTrials.gov Identifier: NCT00000125.

LIFETIME AMBIENT ULTRAVIOLET RADIATION EXPOSURE AND INCIDENCE OF AGE-RELATED MACULAR DEGENERATION

PURPOSE

To investigate the link between lifelong exposure to ultraviolet radiation (UVR) and the development of age-related macular degeneration (AMD).

METHODS

The Alienor study is a prospective population-based cohort involving 963 residents of Bordeaux, France, older than 73 years. A subset of 614 participants for advanced AMD and 422 participants for early AMD were included in the analysis. The participants' residential history combined with UVR estimates from the EuroSun satellite were used to estimate the amount of ambient UVR they have been exposed to over their lifetime. Age-related macular degeneration was classified from retinal fundus photographs and spectral domain optical coherence tomography at 2 to 3 years intervals over the 2006 to 2017 period. Associations between cumulative exposure to ultraviolet A, ultraviolet B, and total (total UV) and the incidence of early and advanced AMD were estimated using multivariate Cox models.

RESULTS

Intermediate quartiles of total UV, ultraviolet A, and ultraviolet B exposures were associated with a higher risk for incident early AMD (Hazard Ratio [HR] =2.01 [95% confidence interval [CI] = 1.27-3.13], HR = 2.20 [95% CI = 1.38-3.50], HR = 1.79 [95% CI = 1.13-2.80], respectively) as compared with the lower quartile. However, this risk did not further increase in the highest quartiles of exposure. None of the three types of UVR exposure was significantly associated with incident advanced AMD.

CONCLUSION

Despite an increased risk with intermediate compared with low UVR exposure, our study cannot confirm a dose-response relationship of UVR exposure with early AMD onset.

Preliminary analysis of predicting the first recurrence in patients with neovascular age-related macular degeneration using deep learning

BACKGROUND

To predict, using deep learning, the first recurrence in patients with neovascular age-related macular degeneration (nAMD) after three monthly loading injections of intravitreal anti-vascular endothelial growth factor (anti-VEGF).

METHODS

Optical coherence tomography (OCT) images were obtained at baseline and after the loading phase. The first recurrence was defined as the initial appearance of a new retinal hemorrhage or intra/subretinal fluid accumulation after the initial resolution of exudative changes after three loading injections. Standard U-Net architecture was used to identify the three retinal fluid compartments, which include pigment epithelial detachment, subretinal fluid, and intraretinal fluid. To predict the first recurrence of nAMD, classification learning was conducted to determine whether the first recurrence occurred within three months after the loading phase. The recurrence classification architecture was built using ResNet50. The model with retinal regions of interest of the entire region and fluid region on OCT at baseline and after the loading phase is presented.

RESULTS

A total of 1,444 eyes of 1,302 patients were included. The mean duration until the first recurrence after the loading phase was 8.20 ± 15.56 months. The recurrence classification system revealed that the model with the fluid region of OCT after the loading phase provided the highest classification performance, with an area under the receiver operating characteristic curve (AUC) of 0.725 ± 0.012. Heatmap analysis revealed that three pathological fluids, subsided choroidal neovascularization lesions, and hyperreflective foci were important areas for the first recurrence.

CONCLUSIONS

The deep learning algorithm allowed for the prediction of the first recurrence for three months after the loading phase with adequate feasibility. An automated prediction system may assist in establishing patient-specific treatment plans and the provision of individualized medical care for patients with nAMD.

Therapeutic targeting of the complement system in ocular disease

The complement system is involved in the pathogenesis of several ocular diseases, providing a rationale for the investigation of complement-targeting therapeutics for these conditions. Dry age-related macular degeneration, as characterised by geographic atrophy (GA), is currently the most active area of research for complement-targeting therapeutics, with a complement C3 inhibitor approved in the United States earlier this year marking the first approved therapy for GA. This review discusses the role of complement in ocular disease, provides an overview of the complement-targeting agents currently under development for ocular conditions, and reflects on the lessons that can be learned from the preclinical investigations and clinical trials conducted in this field to date.

Age-Related Macular Degeneration in an Ageing Society - Current Epidemiological Research

Epidemiological studies on age-related macular degeneration (AMD) provide crucial data on the frequency of early and late forms as well as associated risk factors. The increasing number of population-based cross-sectional and longitudinal cohort studies in Germany and Europe with published data is making prevalence and incidence estimators for AMD more robust, although they show mostly method-related fluctuations. This review article brings together the latest published epidemiological measures for AMD from Germany and Central as well as Western Europe. Based on this data and population figures for Germany and Europe, prevalence is projected, and future trends are forecasted. The epidemiological evidence for AMD-associated risk factors is also improving, especially through meta-analyses within large consortia with correspondingly high case numbers. This review article summarizes the latest findings and resulting recommendations for prevention approaches. Additionally, it discusses treatment options and future challenges.

Polygenic Risk Score Improves Prediction of Primary Open Angle Glaucoma Onset in the Ocular Hypertension Treatment Study

Objective or Purpose

Primary open-angle glaucoma (POAG) is a highly heritable disease with 127 identified risk loci. Polygenic risks score (PRS) offers a measure of aggregate genetic burden. In this study, we assess whether PRS improves risk stratification in patients with ocular hypertension.

Design

A post-hoc analysis of the Ocular Hypertension Treatment Study (OHTS) data.

Setting Participants and/or Controls

1636 participants were followed from 1994 to 2020 across 22 sites. The PRS was computed for 1009 OHTS participants using summary statistics from largest cross-ancestry POAG metanalysis with weights trained using 8,813,496 variants from 488,395 participants in the UK Biobank.

Methods Interventions or Testing

Survival regression analysis, with endpoint as development of POAG, predicted disease onset from PRS incorporating baseline covariates.

Main Outcomes and Measures

Outcome measures were hazard ratios for POAG onset. Concordance index and time-dependent AUC were used to compare the predictive performance of multivariable Cox-Proportional Hazards models.

Results

Mean PRS was significantly higher for POAG-converters (0.24 ± 0.95) than for non-converters (-0.12 ± 1.00) (p < 0.01). POAG risk increased 1.36% with each higher PRS decile, with conversion ranging from 9.5% in the lowest PRS decile to 21.8% in the highest decile. Comparison of low- and high-risk PRS tertiles showed a 1.8-fold increase in 20-year POAG risk for participants of European and African ancestries (p<0.01). In the subgroup randomized to delayed treatment, each increase in PRS decile was associated with a 0.52-year decrease in age at diagnosis, (p=0.05). No significant linear relationship between PRS and age at POAG diagnosis was present in the early treatment group. Prediction models significantly improved with the addition of PRS as a covariate (C-index = 0.77) compared to OHTS baseline model (C-index=0.75) (p<0.01). One standard deviation higher PRS conferred a mean hazard ratio of 1.25 (CI=[1.13, 1.44]) for POAG onset.

Conclusions

Higher PRS is associated with increased risk for, and earlier development of POAG in patients with ocular hypertension. Early treatment may mitigate the risk from high genetic burden, delaying clinically detectable disease by up to 5.2 years. The inclusion of a PRS improves the prediction of POAG onset.

Learn Single-horizon Disease Evolution for Predictive Generation of Post-therapeutic Neovascular Age-related Macular Degeneration

BACKGROUND AND OBJECTIVE

Most of the existing disease prediction methods in the field of medical image processing fall into two classes, namely image-to-category predictions and image-to-parameter predictions.Few works have focused on image-to-image predictions. Different from multi-horizon predictions in other fields, ophthalmologists prefer to show more confidence in single-horizon predictions due to the low tolerance of predictive risk.

METHODS

We propose a single-horizon disease evolution network (SHENet) to predictively generate post-therapeutic SD-OCT images by inputting pre-therapeutic SD-OCT images with neovascular age-related macular degeneration (nAMD). In SHENet, a feature encoder converts the input SD-OCT images to deep features, then a graph evolution module predicts the process of disease evolution in high-dimensional latent space and outputs the predicted deep features, and lastly, feature decoder recovers the predicted deep features to SD-OCT images. We further propose an evolution reinforcement module to ensure the effectiveness of disease evolution learning and obtain realistic SD-OCT images by adversarial training.

RESULTS

SHENet is validated on 383 SD-OCT cubes of 22 nAMD patients based on three well-designed schemes (P-0, P-1 and P-M) based on the quantitative and qualitative evaluations. Three metrics (PSNR, SSIM, 1-LPIPS) are used here for quantitative evaluations. Compared with other generative methods, the generative SD-OCT images of SHENet have the highest image quality (P-0: 23.659, P-1: 23.875, P-M: 24.198) by PSNR. Besides, SHENet achieves the best structure protection (P-0: 0.326, P-1: 0.337, P-M: 0.349) by SSIM and content prediction (P-0: 0.609, P-1: 0.626, P-M: 0.642) by 1-LPIPS. Qualitative evaluations also demonstrate that SHENet has a better visual effect than other methods.

CONCLUSIONS

SHENet can generate post-therapeutic SD-OCT images with both high prediction performance and good image quality, which has great potential to help ophthalmologists forecast the therapeutic effect of nAMD.

Latest Development on Genetics of Common Retinal Diseases

Many complex forms of retinal diseases are common and pan-ethnic in occurrence. Among them, neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, and central serous choroid retinopathy involve both choroidopathy and neovascularization with multifactorial etiology. They are sight-threatening and potentially blinding. Early treatment is crucial to prevent disease progression. To understand their genetic basis, candidate gene mutational and association analyses, linkage analysis, genome-wide association studies, transcriptome analysis, next-generation sequencing, which includes targeted deep sequencing, whole-exome sequencing, and whole genome sequencing have been conducted. Advanced genomic technologies have led to the identification of many associated genes. But their etiologies are attributed to complicated interactions of multiple genetic and environmental risk factors. Onset and progression of neovascular age-related macular degeneration and polypoidal choroidal vasculopathy are affected by aging, smoking, lifestyle, and variants in over 30 genes. Although some genetic associations have been confirmed and validated, individual genes or polygenic risk markers of clinical value have not been established. The genetic architectures of all these complex retinal diseases that involve sequence variant quantitative trait loci have not been fully delineated. Recently artificial intelligence is making an impact in the collection and advanced analysis of genetic, investigative, and lifestyle data for the establishment of predictive factors for the risk of disease onset, progression, and prognosis. This will contribute to individualized precision medicine for the management of complex retinal diseases.

Automation of Macular Degeneration Classification in the AREDS Dataset, Using a Novel Neural Network Design

Purpose

To create an ensemble of Convolutional Neural Networks (CNNs), capable of detecting and stratifying the risk of progressive age-related macular degeneration (AMD) from retinal photographs.

Design

Retrospective cohort study.

Methods

Three individual CNNs are trained to accurately detect 1) advanced AMD, 2) drusen size and 3) the presence or otherwise of pigmentary abnormalities, from macular centered retinal images were developed. The CNNs were then arranged in a "cascading" architecture to calculate the Age-related Eye Disease Study (AREDS) Simplified 5-level risk Severity score (Risk Score 0 - Risk Score 4), for test images. The process was repeated creating a simplified binary "low risk" (Scores 0-2) and "high risk" (Risk Score 3-4) classification.

Participants

There were a total of 188,006 images, of which 118,254 images were deemed gradable, representing 4591 patients, from the AREDS1 dataset. The gradable images were split into 50%/25%/25% ratios for training, validation and test purposes.

Main Outcome Measures

The ability of the ensemble of CNNs using retinal images to predict an individual's risk of experiencing progression of their AMD based on the AREDS 5-step Simplified Severity Scale.

Results

When assessed against the 5-step Simplified Severity Scale, the results generated by the ensemble of CNN's achieved an accuracy of 80.43% (quadratic kappa 0.870). When assessed against a simplified binary (Low Risk/High Risk) classification, an accuracy of 98.08%, sensitivity of ≥85% and specificity of ≥99% was achieved.

Conclusion

We have created an ensemble of neural networks, trained on the AREDS 1 dataset, that is able to accurately calculate an individual's score on the AREDS 5-step Simplified Severity Scale for AMD. If the results presented were replicated, then this ensemble of CNNs could be used as a screening tool that has the potential to significantly improve health outcomes by identifying asymptomatic individuals who would benefit from AREDS2 macular supplements.

The Need for Artificial Intelligence Based Risk Factor Analysis for Age-Related Macular Degeneration: A Review

In epidemiology, a risk factor is a variable associated with increased disease risk. Understanding the role of risk factors is significant for developing a strategy to improve global health. There is strong evidence that risk factors like smoking, alcohol consumption, previous cataract surgery, age, high-density lipoprotein (HDL) cholesterol, BMI, female gender, and focal hyper-pigmentation are independently associated with age-related macular degeneration (AMD). Currently, in the literature, statistical techniques like logistic regression, multivariable logistic regression, etc., are being used to identify AMD risk factors by employing numerical/categorical data. However, artificial intelligence (AI) techniques have not been used so far in the literature for identifying risk factors for AMD. On the other hand, artificial intelligence (AI) based tools can anticipate when a person is at risk of developing chronic diseases like cancer, dementia, asthma, etc., in providing personalized care. AI-based techniques can employ numerical/categorical and/or image data thus resulting in multimodal data analysis, which provides the need for AI-based tools to be used for risk factor analysis in ophthalmology. This review summarizes the statistical techniques used to identify various risk factors and the higher benefits that AI techniques provide for AMD-related disease prediction. Additional studies are required to review different techniques for risk factor identification for other ophthalmic diseases like glaucoma, diabetic macular edema, retinopathy of prematurity, cataract, and diabetic retinopathy.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Systems genomics in age-related macular degeneration

Genomic studies in age-related macular degeneration (AMD) have identified genetic variants that account for the majority of AMD risk. An important next step is to understand the functional consequences and downstream effects of the identified AMD-associated genetic variants. Instrumental for this next step are 'omics' technologies, which enable high-throughput characterization and quantification of biological molecules, and subsequent integration of genomics with these omics datasets, a field referred to as systems genomics. Single cell sequencing studies of the retina and choroid demonstrated that the majority of candidate AMD genes identified through genomic studies are expressed in non-neuronal cells, such as the retinal pigment epithelium (RPE), glia, myeloid and choroidal cells, highlighting that many different retinal and choroidal cell types contribute to the pathogenesis of AMD. Expression quantitative trait locus (eQTL) studies in retinal tissue have identified putative causal genes by demonstrating a genetic overlap between gene regulation and AMD risk. Linking genetic data to complement measurements in the systemic circulation has aided in understanding the effect of AMD-associated genetic variants in the complement system, and supports that protein QTL (pQTL) studies in plasma or serum samples may aid in understanding the effect of genetic variants and pinpointing causal genes in AMD. A recent epigenomic study fine-mapped AMD causal variants by determing regulatory regions in RPE cells differentiated from induced pluripotent stem cells (iPSC-RPE). Another approach that is being employed to pinpoint causal AMD genes is to produce synthetic DNA assemblons representing risk and protective haplotypes, which are then delivered to cellular or animal model systems. Pinpointing causal genes and understanding disease mechanisms is crucial for the next step towards clinical translation. Clinical trials targeting proteins encoded by the AMD-associated genomic loci C3, CFB, CFI, CFH, and ARMS2/HTRA1 are currently ongoing, and a phase III clinical trial for C3 inhibition recently showed a modest reduction of lesion growth in geographic atrophy. The EYERISK consortium recently developed a genetic test for AMD that allows genotyping of common and rare variants in AMD-associated genes. Polygenic risk scores (PRS) were applied to quantify AMD genetic risk, and may aid in predicting AMD progression. In conclusion, genomic studies represent a turning point in our exploration of AMD. The results of those studies now serve as a driving force for several clinical trials. Expanding to omics and systems genomics will further decipher function and causality from the associations that have been reported, and will enable the development of therapies that will lessen the burden of AMD.

Characterizing Early Residual Fluid in Neovascular Age-Related Macular Degeneration using Machine Learning in Routine Clinical Practice

PURPOSE

Neovascular age-related macular degeneration (nAMD) often requires intensive therapy with anti-VEGF injections. In prior post hoc studies, early residual fluid (ERF) after the loading phase was associated with poorer treatment outcomes. This retrospective study examined the impact of ERF on vision using machine learning (ML) methods in routine clinical practice.

DESIGN

Retrospective cohort.

PARTICIPANTS

This study included treatment-naïve patients with nAMD who were initiated on anti-VEGF between 2012 and 2018, with at least 1 year of follow-up.

METHODS

Overall, 286 patients with nAMD were included. An ML algorithm quantified intraretinal fluid (IRF), subretinal fluid (SRF), and total retinal fluid from OCTs. The ERF group included those with fluid at week 12 and was further stratified by fluid subtype. Paired t tests and analysis of variance compared best visual acuity (BVA) and fluid among subgroups, and a quartile analysis correlated fluid volumes to week 52 BVA. The risk of ERF was predicted from baseline factors using 3 ML methods: Ridge logistic regression, k nearest neighbors classification, and support vector classification.

MAIN OUTCOME MEASURES

Mean change in BVA from baseline to week 52 according to week 12 fluid status.

RESULTS

At week 12, 58.4% of patients had ERF. The breakdown of those in the ERF group included SRF-only (45.5%), IRF-only (21.6%), and IRF and SRF (32.9%). The ERF and ERF-free groups had similar BVA gains from baseline to week 52 (+5.7 ± 15.4 vs. +4.9 ± 18; P = 0.69). Examining specific ERF subgroups revealed no significant differences among the IRF-only (+4.6 ± 16.4), SRF-only (+5.6 ± 12.5), and IRF and SRF (+6.6 ± 18.5, P = 0.93) groups. Quartile analysis of week 12 fluid revealed no predictive pattern for BVA gains. Three ML methods were developed to predict those at risk for ERF achieved equivalent performance, with F1 score of 0.73 to 0.76.

CONCLUSIONS

These results diverge from prior post hoc studies, in that there was no significant difference in long-term BVA gains between ERF and ERF-free cohorts, as well as between the week 12 fluid subgroups.

Risk Association of Liver Cancer and Hepatitis B with Tree Ensemble and Lifestyle Features

The second-largest cause of death by cancer in Korea is liver cancer, which leads to acute morbidity and mortality. Hepatitis B is the most common cause of liver cancer. About 70% of liver cancer patients suffer from hepatitis B. Early risk association of liver cancer and hepatitis B can help prevent fatal conditions. We propose a risk association method for liver cancer and hepatitis B with only lifestyle features. The diagnostic features were excluded to reduce the cost of gathering medical data. The data source is the Korea National Health and Nutrition Examination Survey (KNHANES) from 2007 to 2019. We use 3872 and 4640 subjects for liver cancer and hepatitis B model, respectively. Random forest is employed to determine functional relationships between liver diseases and lifestyle features. The performance of our proposed method was compared with six machine learning methods. The results showed the proposed method outperformed the other methods in the area under the receiver operator characteristic curve of 0.8367. The promising results confirm the superior performance of the proposed method and show that the proposed method with only lifestyle features provides significant advantages, potentially reducing the cost of detecting patients who require liver health care in advance.

Molecular Genetic Mechanisms in Age-Related Macular Degeneration

Age-related macular degeneration (AMD) is among the leading causes of irreversible blindness worldwide. In addition to environmental risk factors, such as tobacco use and diet, genetic background has long been established as a major risk factor for the development of AMD. However, our ability to predict disease risk and personalize treatment remains limited by our nascent understanding of the molecular mechanisms underlying AMD pathogenesis. Research into the molecular genetics of AMD over the past two decades has uncovered 52 independent gene variants and 34 independent loci that are implicated in the development of AMD, accounting for over half of the genetic risk. This research has helped delineate at least five major pathways that may be disrupted in the pathogenesis of AMD: the complement system, extracellular matrix remodeling, lipid metabolism, angiogenesis, and oxidative stress response. This review surveys our current understanding of each of these disease mechanisms, in turn, along with their associated pathogenic gene variants. Continued research into the molecular genetics of AMD holds great promise for the development of precision-targeted, personalized therapies that bring us closer to a cure for this debilitating disease.

WARE: Wet AMD Risk-Evaluation Tool as a Clinical Decision-Support System Integrating Genetic and Non-Genetic Factors

Given the multifactorial features characterizing age-related macular degeneration (AMD), the availability of a tool able to provide the individual risk profile is extremely helpful for personalizing the follow-up and treatment protocols of patients. To this purpose, we developed an open-source computational tool named WARE (Wet AMD Risk Evaluation), able to assess the individual risk profile for wet AMD based on genetic and non-genetic factors. In particular, the tool uses genetic risk measures normalized for their relative frequencies in the general population and disease prevalence. WARE is characterized by a user-friendly web page interface that is intended to assist clinicians in reporting risk assessment upon patient evaluation. When using the tool, plots of population risk distribution highlight a “low-risk zone” and a “high-risk zone” into which subjects can fall depending on their risk-assessment result. WARE represents a reliable population-specific computational system for wet AMD risk evaluation that can be exploited to promote preventive actions and personalized medicine approach for affected patients or at-risk individuals. This tool can be suitable to compute the disease risk adjusted to different populations considering their specific genetic factors and related frequencies, non-genetic factors, and the disease prevalence.

A Screening Tool for Self-Evaluation of Risk for Age-Related Macular Degeneration: Validation in a Spanish Population

Purpose

The objectives of this study were the creation and validation of a screening tool for age-related macular degeneration (AMD) for routine assessment by primary care physicians, ophthalmologists, other healthcare professionals, and the general population.

Methods

A simple, self-administered questionnaire (Simplified Théa AMD Risk-Assessment Scale [STARS] version 4.0) which included well-established risk factors for AMD, such as family history, smoking, and dietary factors, was administered to patients during ophthalmology visits. A fundus examination was performed to determine presence of large soft drusen, pigmentary abnormalities, or late AMD. Based on data from the questionnaire and the clinical examination, predictive models were developed to estimate probability of the Age-Related Eye Disease Study (AREDS) score (categorized as low risk/high risk). The models were evaluated by area under the receiving operating characteristic curve analysis.

Results

A total of 3854 subjects completed the questionnaire and underwent a fundus examination. Early/intermediate and late AMD were detected in 15.9% and 23.8% of the patients, respectively. A predictive model was developed with training, validation, and test datasets. The model in the test set had an area under the curve of 0.745 (95% confidence interval [CI] = 0.705-0.784), a positive predictive value of 0.500 (95% CI = 0.449-0.557), and a negative predictive value of 0.810 (95% CI = 0.770-0.844).

Conclusions

The STARS questionnaire version 4.0 and the model identify patients at high risk of developing late AMD.

Translational Relevance

The screening instrument described could be useful to evaluate the risk of late AMD in patients >55 years without having an eye examination, which could lead to more timely referrals and encourage lifestyle changes.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology

PURPOSE OF REVIEW

The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each.

RECENT FINDINGS

Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks.

SUMMARY

AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

Incidence, progression and risk factors of age-related macular degeneration in 35-95-year-old individuals from three jointly designed German cohort studies

Objective

To estimate age-related macular degeneration (AMD) incidence/progression across a wide age range.

Methods and analysis

AMD at baseline and follow-up (colour fundus imaging, Three Continent AMD Consortium Severity Scale, 3CACSS, clinical classification, CC) was assessed for 1513 individuals aged 35–95 years at baseline from three jointly designed population-based cohorts in Germany: Kooperative Gesundheitsforschung in der Region Augsburg (KORA-Fit, KORA-FF4) and Altersbezogene Untersuchungen zur Gesundheit der Universität Regensburg (AugUR) with 18-year, 14-year or 3-year follow-up, respectively. Baseline assessment included lifestyle, metabolic and genetic markers. We derived cumulative estimates, rates and risk factor association for: (1) incident early AMD, (2) incident late AMD among no AMD at baseline (definition 1), (3) incident late AMD among no/early AMD at baseline (definition 2), (4) progression from early to late AMD.

Results

Incidence/progression increased by age, except progression in 70+-year old. We observed 35–55-year-old with 3CACSS-based early AMD who progressed to late AMD. Predominant risk factor for incident late AMD definition 2 was early AMD followed by genetics and smoking. When separating incident late AMD definition 1 from progression (instead of combined as incident late AMD definition 2), estimates help judge an individual’s risk based on age and (3CACSS) early AMD status: for example, for a 65-year old, 3-year late AMD risk with no or early AMD is 0.5% or 7%, 3-year early AMD risk is 3%; for an 85-year old, these numbers are 0.5%, 21%, 12%, respectively. For CC-based ‘early/intermediate’ AMD, incidence was higher, but progression was lower.

Conclusion

We provide a practical guide for AMD risk for ophthalmology practice and healthcare management and document a late AMD risk for individuals aged <55 years.

Epigenomic signatures in age-related macular degeneration: Focus on their role as disease modifiers and therapeutic targets

Epigenetics is characterized by molecular modifications able to shape gene expression profiles in response to inner and external stimuli. Therefore, epigenetic elements are able to provide intriguing and useful information for the comprehension and management of different human conditions, including aging process, and diseases. On this subject, Age-related Macular Degeneration (AMD) represents one of the most frequent age-related disorders, dramatically affecting the quality of life of older adults worldwide. The etiopathogenesis is characterized by an interplay among multiple genetic and non-genetic factors, which have been extensively studied. Nevertheless, a deeper dissection of molecular machinery associated with risk, onset, progression and effectiveness of therapies is still missing. In this regard, epigenetic signals may be further explored to disentangle disease etiopathogenesis, the possible therapeutic avenues and the differential response to AMD treatment. This review will discuss the epigenomic signatures mostly investigated in AMD, which could be applied to improve the knowledge of disease mechanisms and to set-up novel or modified treatment options.

Exploring Consensus on Preventive Measures and Identification of Patients at Risk of Age-Related Macular Degeneration Using the Delphi Process

Background: Early identification of AMD can lead to prompt and more effective treatment, better outcomes, and better final visual acuity; several risk scores have been devised to determine the individual level of risk for developing AMD. Herein, the Delphi method was used to provide recommendations for daily practice regarding preventive measures and follow-up required for subjects at low, moderate, and high risk of AMD evaluated with the Simplified Test AMD Risk-assessment Scale (STARS^®) questionnaire. Methods: A steering committee of three experts drafted and refined 25 statements on the approach to be recommended in different clinical situations [general recommendations (n = 2), use of evaluation tools (n = 4), general lifestyle advice (n = 3), and AREDS-based nutritional supplementation (n = 5)] with the help of a group of international experts, all co-authors of this paper. Thirty retinal specialists from Europe and the US were chosen based on relevant publications, clinical expertise, and experience in AMD, who then provided their level of agreement with the statements. Statements for which consensus was not reached were modified and voted upon again. Results: In the first round of voting, consensus was reached for 24 statements. After modification, consensus was then reached for the remaining statement. Conclusion: An interprofessional guideline to support preventive measures in patients at risk of AMD based on STARS^® scoring has been developed to aid clinicians in daily practice, which will help to optimize preventive care of patients at risk of AMD.

Artificial Intelligence, Heuristic Biases, and the Optimization of Health Outcomes: Cautionary Optimism

The use of artificial intelligence (AI) and machine learning (ML) in clinical care offers great promise to improve patient health outcomes and reduce health inequity across patient populations. However, inherent biases in these applications, and the subsequent potential risk of harm can limit current use. Multi-modal workflows designed to minimize these limitations in the development, implementation, and evaluation of ML systems in real-world settings are needed to improve efficacy while reducing bias and the risk of potential harms. Comprehensive consideration of rapidly evolving AI technologies and the inherent risks of bias, the expanding volume and nature of data sources, and the evolving regulatory landscapes, can contribute meaningfully to the development of AI-enhanced clinical decision making and the reduction in health inequity.

COVID-19 lockdown measures induced severe iron-deficiency anaemia resulting in central retinal vein occlusion and amenorrhea

During the COVID-19 pandemic, precautionary measures taken by various countries include individual movement restrictions causing significant lifestyle changes and affecting dietary patterns. A 23-year-old woman presented with reduced left eye vision over 1 week and amenorrhea for 4 months. She was diagnosed with severe iron-deficiency anaemia causing central retinal vein occlusion and amenorrhea. During the lockdown, there was a change in her diet with greatly reduced iron intake. Iron is an essential mineral for retina metabolism and function. Iron supplementation was done with improvement in her vision. This case demonstrates the potential impact of lockdown measures on nutrition and health. Education of the general population on maintaining appropriate nutrition during periods of movement restriction is important and that nutritional evaluation and supplementation should be considered in patients with drastic changes in dietary pattern.

CFH Loss in Human RPE Cells Leads to Inflammation and Complement System Dysregulation via the NF-κB Pathway

Age-related macular degeneration (AMD), the leading cause of vision loss in the elderly, is a degenerative disease of the macula, where retinal pigment epithelium (RPE) cells are damaged in the early stages of the disease, and chronic inflammatory processes may be involved. Besides aging and lifestyle factors as drivers of AMD, a strong genetic association to AMD is found in genes of the complement system, with a single polymorphism in the complement factor H gene (CFH), accounting for the majority of AMD risk. However, the exact mechanism of CFH dysregulation confers such a great risk for AMD and its role in RPE cell homeostasis is unclear. To explore the role of endogenous CFH locally in RPE cells, we silenced CFH in human hTERT-RPE1 cells. We demonstrate that endogenously expressed CFH in RPE cells modulates inflammatory cytokine production and complement regulation, independent of external complement sources, or stressors. We show that loss of the factor H protein (FH) results in increased levels of inflammatory mediators (e.g., IL-6, IL-8, GM-CSF) and altered levels of complement proteins (e.g., C3, CFB upregulation, and C5 downregulation) that are known to play a role in AMD. Moreover, our results identify the NF-κB pathway as the major pathway involved in regulating these inflammatory and complement factors. Our findings suggest that in RPE cells, FH and the NF-κB pathway work in synergy to maintain inflammatory and complement balance, and in case either one of them is dysregulated, the RPE microenvironment changes towards a proinflammatory AMD-like phenotype.

Risk Stratification and Clinical Utility of Polygenic Risk Scores in Ophthalmology

Translational Relevance

Common genetic variants can be used to effectively stratify the risk of disease development and progression and may be used to guide screening, triaging, monitoring, or treatment thresholds.

The complement system in age-related macular degeneration

Age-related macular degeneration (AMD) is a chronic and progressive degenerative disease of the retina, which culminates in blindness and affects mainly the elderly population. AMD pathogenesis and pathophysiology are incredibly complex due to the structural and cellular complexity of the retina, and the variety of risk factors and molecular mechanisms that contribute to disease onset and progression. AMD is driven by a combination of genetic predisposition, natural ageing changes and lifestyle factors, such as smoking or nutritional intake. The mechanism by which these risk factors interact and converge towards AMD are not fully understood and therefore drug discovery is challenging, where no therapeutic attempt has been fully effective thus far. Genetic and molecular studies have identified the complement system as an important player in AMD. Indeed, many of the genetic risk variants cluster in genes of the alternative pathway of the complement system and complement activation products are elevated in AMD patients. Nevertheless, attempts in treating AMD via complement regulators have not yet been successful, suggesting a level of complexity that could not be predicted only from a genetic point of view. In this review, we will explore the role of complement system in AMD development and in the main molecular and cellular features of AMD, including complement activation itself, inflammation, ECM stability, energy metabolism and oxidative stress.