Complement inhibitors for the treatment of geographic atrophy

Artificial Intelligence to Facilitate Clinical Trial Recruitment in Age-Related Macular Degeneration

Objective

Recent developments in artificial intelligence (AI) have positioned it to transform several stages of the clinical trial process. In this study, we explore the role of AI in clinical trial recruitment of individuals with geographic atrophy (GA), an advanced stage of age-related macular degeneration, amidst numerous ongoing clinical trials for this condition.

Design

Cross-sectional study.

Subjects

Retrospective dataset from the INSIGHT Health Data Research Hub at Moorfields Eye Hospital in London, United Kingdom, including 306 651 patients (602 826 eyes) with suspected retinal disease who underwent OCT imaging between January 1, 2008 and April 10, 2023.

Methods

A deep learning model was trained on OCT scans to identify patients potentially eligible for GA trials, using AI-generated segmentations of retinal tissue. This method's efficacy was compared against a traditional keyword-based electronic health record (EHR) search. A clinical validation with fundus autofluorescence (FAF) images was performed to calculate the positive predictive value of this approach, by comparing AI predictions with expert assessments.

Main Outcome Measures

The primary outcomes included the positive predictive value of AI in identifying trial-eligible patients, and the secondary outcome was the intraclass correlation between GA areas segmented on FAF by experts and AI-segmented OCT scans.

Results

The AI system shortlisted a larger number of eligible patients with greater precision (1139, positive predictive value: 63%; 95% confidence interval [CI]: 54%-71%) compared with the EHR search (693, positive predictive value: 40%; 95% CI: 39%-42%). A combined AI-EHR approach identified 604 eligible patients with a positive predictive value of 86% (95% CI: 79%-92%). Intraclass correlation of GA area segmented on FAF versus AI-segmented area on OCT was 0.77 (95% CI: 0.68-0.84) for cases meeting trial criteria. The AI also adjusts to the distinct imaging criteria from several clinical trials, generating tailored shortlists ranging from 438 to 1817 patients.

Conclusions

This study demonstrates the potential for AI in facilitating automated prescreening for clinical trials in GA, enabling site feasibility assessments, data-driven protocol design, and cost reduction. Once treatments are available, similar AI systems could also be used to identify individuals who may benefit from treatment.

Financial Disclosures

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

Association of Lesion Location and Functional Parameters with Vision-Related Quality of Life in Geographic Atrophy Secondary to Age-related Macular Degeneration

OBJECTIVE

The primary goal of this study was to determine how structural and functional parameters influence the vision-related quality of life (VRQoL) in patients suffering from geographic atrophy (GA) secondary to age-related macular degeneration.

DESIGN

This study was designed as a prospective, noninterventional, natural-history study (Directional Spread in Geographic-Atrophy study, NCT02051998).

SUBJECTS

The research involved 82 patients with bilateral GA.

METHODS

The study examined parameters including GA location as assessed by the ETDRS grid, best-corrected visual acuity, low-luminance visual acuity (LLVA), reading acuity, and speed. These parameters were then correlated with VRQoL, which was gauged using the National Eye Institute Visual Function Questionnaire 25. The analysis method employed was the least absolute shrinkage and selection operator with linear mixed-effects models.

MAIN OUTCOME MEASURES

The central parameters measured in this study encompassed GA area, VRQoL scores associated with different GA subfields, and the significance of LLVA for foveal-sparing patients.

RESULTS

On average, patients showed a total GA area of 2.9 ± 1.2 mm2 in the better eye (BE) and 3.1 ± 1.3 mm2 in the worse eye. The most significant associations with VRQoL scores for distance and near activities were observed in the inner lower and inner left subfields of the BE, respectively. For patients with foveal-sparing GA, the LLVA of the BE stood out as the most influential variable across all VRQoL scales.

CONCLUSIONS

The study's findings point toward the pivotal role of GA location, especially the inner lower and inner left subfields of the BE, in relation to VRQoL in GA patients. The LLVA's importance becomes even more pronounced for foveal-sparing patients. These observations highlight the need for health care professionals to better understand the association between lesion location and patient-reported outcomes. This is critical for informing treatment decisions and refining the planning of interventional trials.

FINANCIAL DISCLOSURE(S)

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

CYTOR-NFAT1 feedback loop regulates epithelial-mesenchymal transition of retinal pigment epithelial cells

Epithelial mesenchymal transition (EMT) occurring in retinal pigment epithelial cells (RPE) is a crucial mechanism that contributes to the development of age-related macular degeneration (AMD), a pivotal factor leading to permanent vision impairment. Long non-coding RNAs (lncRNAs) have emerged as critical regulators orchestrating EMT in RPE cells. In this study, we explored the function of the lncRNA CYTOR (cytoskeleton regulator RNA) in EMT of RPE cells and its underlying mechanisms. Through weighted correlation network analysis, we identified CYTOR as an EMT-related lncRNA associated with AMD. Experimental validation revealed that CYTOR orchestrates TGF-β1-induced EMT, as well as proliferation and migration of ARPE-19 cells. Further investigation demonstrated the involvement of CYTOR in regulating the WNT5A/NFAT1 pathway and NFAT1 intranuclear translocation in the ARPE-19 cell EMT model. Mechanistically, CHIP, EMSA and dual luciferase reporter assays confirmed NFAT1's direct binding to CYTOR's promoter, promoting transcription. Reciprocally, CYTOR overexpression promoted NFAT1 expression, while NFAT1 overexpression increased CYTOR transcription. These findings highlight a mutual promotion between CYTOR and NFAT1, forming a positive feedback loop that triggers the EMT phenotype in ARPE-19 cells. These discoveries provide valuable insights into the molecular mechanisms of EMT and its association with AMD, offering potential avenues for targeted therapies in EMT-related conditions, including AMD.

Role of plasma fatty acid in age-related macular degeneration: insights from a mendelian randomization analysis

BACKGROUND

An imbalance in lipid metabolism has been linked to the development of AMD, but the causal relationship between AMD and plasma fatty acids (FAs) remains controversial. Using a two-sample Mendelian randomization (MR) approach, we sought to evaluate the impact of specific FA plasma levels on the risk of different AMD subtypes.

METHODS

We analysed genome-wide association data of circulating FAs from 115,006 European-descended individuals in the UK Biobank. These data were used in a two-sample MR framework to assess the potential role of circulating FAs in developing wet and dry AMD. Sensitivity analyses were conducted to ensure the robustness of our findings. Additional multivariable and locus-specific MR analyses were conducted to evaluate direct effects of FA on AMD subtypes, minimizing biases from lipoprotein-related traits and triglycerides.

RESULTS

Mendelian randomization revealed associations of omega-3 was associated with decreased wet (OR 0.78, 95%CI 0.66-0.92) and dry AMD (0.85, 0.74-0.97) risk, showed a protective effect on AMD. Notably, the omega-6 to omega-3 ratio showed potential causal effects on both wet (1.27, 1.03-1.56) and dry AMD (1.18, 1.02-1.37). Multivariable MR suggested that the causal relationship of omega-3, omega-6 to omega-3 ratio on wet AMD persists after conditioning on HDL, LDL and triglycerides, albeit with slightly diminished evidence strength. Locus-specific MR linked to omega-3(FADS1, 0.89, 0.82-0.98; FADS2, 0.88, 0.81-0.96) and omega-6 to omega-3 ratio (FADS1, 1.10, 1.02-1.20; FADS2, 1.11, 1.03-1.20) suggests causal effects of these factors on wet AMD.

CONCLUSIONS

The associations between plasma FA concentrations and AMD, suggest potential causal role of omega-3, and the omega-6 to omega-3 ratio in wet AMD. These results underscore the impact of an imbalanced circulating omega-3 and omega-6 FA ratio on AMD pathophysiology from MR perspective.

Decreased Macular Choriocapillaris Perfusion Correlates with Contrast Sensitivity Function in Dry Age-Related Macular Degeneration

PURPOSE

To investigate the relationships between contrast sensitivity (CS), choriocapillaris perfusion, and other structural OCT biomarkers in dry age-related macular degeneration (AMD).

DESIGN

Cross-sectional, observational study.

PARTICIPANTS

One hundred AMD eyes (22 early, 52 intermediate, and 26 late) from 74 patients and 45 control eyes from 37 age-similar subjects.

METHODS

All participants had visual acuity (VA) assessment, quantitative CS function (qCSF) testing, macular OCT, and 6 × 6-mm swept-source OCT angiography scans on the same day. OCT volumes were analyzed for subretinal drusenoid deposits and hyporeflective drusen cores, and to measure thickness of the outer nuclear layer. OCT angiography scans were utilized to calculate drusen volume and inner choroid flow deficit percentage (IC-FD%), and to measure the area of choroidal hypertransmission defects (HTDs). Inner choroid flow deficit percentage was measured from a 16-μm thick choriocapillaris slab after compensation and binarization with Phansalkar's method. Generalized linear mixed-effects models were used to evaluate the associations between functional and structural variables.

MAIN OUTCOME MEASURES

To explore the associations between qCSF-measured CS, IC-FD%, and various AMD imaging biomarkers.

RESULTS

Age-related macular degeneration exhibited significantly reduced qCSF metrics eyes across all stages compared with controls. Univariate analysis revealed significant associations between various imaging biomarkers, reduced qCSF metrics, and VA in both groups. Multivariate analysis confirmed that higher IC-FD% in the central 5 mm was significantly associated with decreases in all qCSF metrics in AMD eyes (β = -0.74 to -0.25, all P < 0.05), but not with VA (P > 0.05). Outer nuclear layer thickness in the central 3 mm correlated with both VA (β = 2.85, P < 0.001) and several qCSF metrics (β = 0.01-0.90, all P < 0.05), especially in AMD eyes. Further, larger HTD areas were associated with decreased VA (β = -0.89, P < 0.001) and reduced CS at low-intermediate frequencies across AMD stages (β = -0.30 to -0.29, P < 0.001).

CONCLUSIONS

The significant association between IC-FD% in the central 5 mm and qCSF-measured CS reinforces the hypothesis that decreased macular choriocapillaris perfusion contributes to visual function changes in AMD, which are more pronounced in CS than in VA.

FINANCIAL DISCLOSURE(S)

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

Human versus Artificial Intelligence: Validation of a Deep Learning Model for Retinal Layer and Fluid Segmentation in Optical Coherence Tomography Images from Patients with Age-Related Macular Degeneration

Artificial intelligence (AI) models have received considerable attention in recent years for their ability to identify optical coherence tomography (OCT) biomarkers with clinical diagnostic potential and predict disease progression. This study aims to externally validate a deep learning (DL) algorithm by comparing its segmentation of retinal layers and fluid with a gold-standard method for manually adjusting the automatic segmentation of the Heidelberg Spectralis HRA + OCT software Version 6.16.8.0. A total of sixty OCT images of healthy subjects and patients with intermediate and exudative age-related macular degeneration (AMD) were included. A quantitative analysis of the retinal thickness and fluid area was performed, and the discrepancy between these methods was investigated. The results showed a moderate-to-strong correlation between the metrics extracted by both software types, in all the groups, and an overall near-perfect area overlap was observed, except for in the inner segment ellipsoid (ISE) layer. The DL system detected a significant difference in the outer retinal thickness across disease stages and accurately identified fluid in exudative cases. In more diseased eyes, there was significantly more disagreement between these methods. This DL system appears to be a reliable method for accessing important OCT biomarkers in AMD. However, further accuracy testing should be conducted to confirm its validity in real-world settings to ultimately aid ophthalmologists in OCT imaging management and guide timely treatment approaches.

Age-Related Macular Degeneration: A Review

Importance

Age-related macular degeneration (AMD) affects approximately 20 million people in the US and 196 million people worldwide. AMD is a leading cause of severe vision impairment in older people and is expected to affect approximately 288 million people worldwide by 2040.

Observations

Older age, genetic factors, and environmental factors, such as cigarette smoking, are associated with development of AMD. AMD occurs when extracellular deposits accumulate in the outer retina, ultimately leading to photoreceptor degeneration and loss of central vision. The late stages of AMD are characterized by outer retinal atrophy, termed geographic atrophy, or neovascularization associated with subretinal and/or intraretinal exudation, termed exudative neovascular AMD. The annual incidence of AMD ranges from 0.3 per 1000 in people who are aged 55 to 59 years to 36.7 per 1000 in people aged 90 years or older. The estimated heritability of late-stage AMD is approximately 71% (95% CI, 18%-88%). Long-term prospective cohort studies show a significantly higher AMD incidence in people who smoke more than 20 cigarettes per day compared with people who never smoked. AMD is diagnosed primarily with clinical examination that includes a special lens that focuses light of the slit lamp through the pupil. Exudative neovascular AMD is best identified using angiography and by optical coherence tomography. Individuals with AMD who take nutritional supplements consisting of high-dose vitamin C, vitamin E, carotenoids, and zinc have a 20% probability to progress to late-stage AMD at 5 years vs a 28% probability for those taking a placebo. In exudative neovascular AMD, 94.6% of patients receiving monthly intravitreal anti-vascular endothelial growth factor (anti-VEGF) injections experience less than a 15-letter visual acuity loss after 12 months compared with 62.2% receiving sham treatment.

Conclusions and Relevance

The prevalence of AMD is anticipated to increase worldwide to 288 million individuals by 2040. Intravitreally administered anti-VEGF treatment is first-line therapy for exudative neovascular AMD.