Artificial Intelligence (AI) Applications for Age-Related Macular Degeneration (AMD) and Other Retinal Dystrophies

Opportunity to Use Artificial Intelligence in Medicine

Over the past period different reports related to the artificial intelligence (AI) and machine learning used in everyday life have been growing intensely. However, the AI in our country is still very limited, especially in the field of medicine. The aim of this article is to give some review about AI in medicine and the related fields based on published articles in PubMed and Psych Net. A research showed more than 9 thousand articles available at the mentioned databases. After providing some historical data, different AI applications in different fields of medicine are discussed. Finally, some limitations and ethical implications are discussed.

Technological Perception with Rural and Urban Differentiation and Its Influence on the Quality of Life of Older People with Age-Related Macular Degeneration

The past decade has seen a global increase in population age, especially in developed countries, where aging involves visual diseases such as age-related macular degeneration (AMD), which severely affect quality of life (QoL) and mental health, as well as increase isolation and care costs. This study investigated how persons with AMD perceive the impact of technology use on their QoL, focusing on potential disparities between urban and rural contexts in Spain. Using a cross-sectional observational design, data from the 2020 National Statistics Institute's Disability, Personal Autonomy, and Dependency Situations Survey were analyzed, focusing on QoL aspects based on the WHO items of the WHOQOL-100 scale. The results revealed a generally positive perception of technology among participants, with urban residents perceiving technology's positive impact more favorably. Sex discrepancies in technology perception were also observed, as women exhibited a more positive outlook on technology's influence on QoL. The analysis of QoL aspects, such as 'Visibility', 'Learning', 'Mobility', and 'Domestic life', highlighted distinct challenges faced by rural and urban populations, underscoring the importance of context-specific approaches in technology interventions. However, these perceptions were intertwined with comorbidities, which can exacerbate AMD-related issues. Furthermore, this study explored the role of technology in enhancing QoL among older adults with AMD, examining how it influences daily activities and independence, particularly in the context of AMD management. This study concluded that developing more-inclusive policies tailored to the specific needs of persons with AMD, with special attention to environmental and sex differences, is imperative to enhance the positive impact of technology on their QoL.

Research on an artificial intelligence-based myopic maculopathy grading method using EfficientNet

PURPOSE

We aimed to develop an artificial intelligence-based myopic maculopathy grading method using EfficientNet to overcome the delayed grading and diagnosis of different myopic maculopathy degrees.

METHODS

The cooperative hospital provided 4642 healthy and myopic maculopathy color fundus photographs, comprising the four degrees of myopic maculopathy and healthy fundi. The myopic maculopathy grading models were trained using EfficientNet-B0 to EfficientNet-B7 models. The diagnostic results were compared with those of the VGG16 and ResNet50 classification models. The leading evaluation indicators were sensitivity, specificity, F1 score, area under the receiver operating characteristic (ROC) curve area under curve (AUC), 95% confidence interval, kappa value, and accuracy. The ROC curves of the ten grading models were also compared.

RESULTS

We used 1199 color fundus photographs to evaluate the myopic maculopathy grading models. The size of the EfficientNet-B0 myopic maculopathy grading model was 15.6 MB, and it had the highest kappa value (88.32%) and accuracy (83.58%). The model's sensitivities to diagnose tessellated fundus (TF), diffuse chorioretinal atrophy (DCA), patchy chorioretinal atrophy (PCA), and macular atrophy (MA) were 96.86%, 75.98%, 64.67%, and 88.75%, respectively. The specificity was above 93%, and the AUCs were 0.992, 0.960, 0.964, and 0.989, respectively.

CONCLUSION

The EfficientNet models were used to design grading diagnostic models for myopic maculopathy. Based on the collected fundus images, the models could diagnose a healthy fundus and four types of myopic maculopathy. The models might help ophthalmologists to make preliminary diagnoses of different degrees of myopic maculopathy.

Uncertainty-inspired open set learning for retinal anomaly identification

Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies. We establish an uncertainty-inspired open set (UIOS) model, which is trained with fundus images of 9 retinal conditions. Besides assessing the probability of each category, UIOS also calculates an uncertainty score to express its confidence. Our UIOS model with thresholding strategy achieves an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set, external target categories (TC)-JSIEC dataset and TC-unseen testing set, respectively, compared to the F1 score of 92.20%, 80.69% and 64.74% by the standard AI model. Furthermore, UIOS correctly predicts high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images. UIOS provides a robust method for real-world screening of retinal anomalies.

Age-related macular degeneration

Age-related macular degeneration is an increasingly important public health issue due to ageing populations and increased longevity. Age-related macular degeneration affects individuals older than 55 years and threatens high-acuity central vision required for important tasks such as reading, driving, and recognising faces. Advances in retinal imaging have identified biomarkers of progression to late age-related macular degeneration. New treatments for neovascular age-related macular degeneration offer potentially longer-lasting effects, and progress is being made towards a treatment for atrophic late age-related macular degeneration. An effective intervention to slow progression in the earlier stages of disease, or to prevent late age-related macular degeneration development remains elusive, and our understanding of underlying mechanistic pathways continues to evolve.

Implementation science: A critical but undervalued part of the healthcare innovation ecosystem

Healthcare systems face many competing demands and insufficient resources. Service innovations to improve efficiency are important to address this challenge. Innovations can range from new pharmaceuticals, alternate models of care, novel devices, and the use other technologies. Suboptimal implementation can mean lost benefits. This review article aims to highlight the role of implementation science, summarize how settings have leveraged this methodology to promote translation of innovation into practice, and describe our own experience of embedding implementation science into an academic medical center in Singapore. Implementation science offers a range of methods to promote systematic uptake of research findings about innovations and is gaining recognition worldwide as an important discipline for health services researchers. Health systems around the world have tried to promote implementation research in their settings by establishing (1) dedicated centers/programs, (2) offering funding, and (3) building knowledge and capacity among staff. Implementation science is a critical piece in the translational pathway of "evidence to innovation." The three efforts we describe should be strengthened to integrate implementation science into the innovation ecosystem around the world.

Long-term persistence with aflibercept therapy among treatment-naïve patients with exudative age-related macular degeneration in a universal health care system: a retrospective study

Background

This study  aimed to analyse the persistence rates of treatment-naïve patients with neovascular age-related macular degeneration (nAMD) who received intravitreal aflibercept therapy in a universal health care system.

Methods

In this single-centre retrospective cohort study, we audited data of 918 treatment-naïve patients who received exclusively intravitreal aflibercept therapy for nAMD between September 2015 and May 2021. The primary outcome measures were the rates of treatment nonpersistence (gap in ophthalmological care > 6 months) and long-term nonpersistence (> 12 months).

Results

The rates of nonpersistence and long-term nonpersistence were 12.3% and 3.4% after one year; 22.4% and 9.5% after two years; and 38.3% and 19.3% after five years, respectively. Logistic regression analysis revealed that older age (p = 0.045), male sex (p = 0.039), requirement for caretakers or ambulance (p = 0.001), and low visual acuity of the study eye (p = 0.010) or fellow eye (p = 0.029) were independent risk factors for long-term nonpersistence. Patients aged > 80 and > 85 years (p = 0.013 and p = 0.022, respectively) had more than twice the risk for being nonpersistent to therapy within two years of follow-up compared with younger patients. Male patients (p = 0.033), patients requiring a caretaker (p = 0.038), and patients living > 60 km from the clinic (p = 0.029) had a 2 × higher risk of being persistently nonpersistent to therapy.

Conclusions

Patients with nAMD who were treated with aflibercept had lower nonpersistence rates than those reported in current literature. Multiple independent risk factors were correlated with long-term nonpersistence, early nonpersistence, or complete loss to follow-up. Considering the possible consequences of reduced compliance, further strategies are urgently needed for patients at risk of nonpersistence to therapy.

Artificial Intelligence Analysis of Biofluid Markers in Age-Related Macular Degeneration: A Systematic Review

This systematic review explores the use of artificial intelligence (AI) in the analysis of biofluid markers in age-related macular degeneration (AMD). We detail the accuracy and validity of AI in diagnostic and prognostic models and biofluid markers that provide insight into AMD pathogenesis and progression. This review was conducted in accordance with the Preferred Reporting Items for a Systematic Review and Meta-analysis guidelines. A comprehensive search was conducted across 5 electronic databases including Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, EMBASE, Medline, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics in AMD were included. Identified studies were assessed for risk of bias and critically appraised using the Joanna Briggs Institute Critical Appraisal tools. A total of 10,264 articles were retrieved from all databases and 37 studies met the inclusion criteria, including 15 cross-sectional studies, 15 prospective cohort studies, five retrospective cohort studies, one randomized controlled trial, and one case–control study. The majority of studies had a general focus on AMD (58%), while neovascular AMD (nAMD) was the focus in 11 studies (30%), and geographic atrophy (GA) was highlighted by three studies. Fifteen studies examined disease characteristics, 15 studied risk factors, and seven guided treatment decisions. Altered lipid metabolism (HDL-cholesterol, total serum triglycerides), inflammation (c-reactive protein), oxidative stress, and protein digestion were implicated in AMD development and progression. AI tools were able to both accurately differentiate controls and AMD patients with accuracies as high as 87% and predict responsiveness to anti-VEGF therapy in nAMD patients. Use of AI models such as discriminant analysis could inform prognostic and diagnostic decision-making in a clinical setting. The identified pathways provide opportunity for future studies of AMD development and could be valuable in the advancement of novel treatments.

Intravitreal Aflibercept Therapy and Treatment Outcomes of Eyes with Neovascular Age-Related Macular Degeneration in a Real-Life Setting: A Five-Year Follow-Up Investigation

Introduction

We aimed to evaluate visual and anatomical outcomes among eyes with neovascular age-related macular degeneration (nAMD) that were persistent to intravitreal aflibercept therapy compared to those that were nonpersistent to therapy.

Methods

We audited 648 treatment-naïve eyes of 559 patients regarding visual acuity (VA) given as the logarithm of the minimum angle of resolution (logMAR) and anatomic outcomes at baseline and at each subsequent follow-up visit for up to 5 years. Nonpersistence was defined as a visit-free interval of > 6 months.

Results

Among the enrolled eyes, 405 were persistent to the therapy and 243 (37%) were nonpersistent, of which 161 (66%) eyes returned for further therapy after a gap of clinical care. In the nonpersistent group, we observed a decline from 0.58 ± 0.35 to 0.92 ± 0.57 logMAR (p = 0.01) after 60 months. Compared with the persistent group, the nonpersistent group had worse visual outcomes at their 33-month (p = 0.03), 42-month (p = 0.01), 51-month (p = 0.001) and 60-month (p = 0.01) visits. Additionally, 5/405 (1.2%) eyes in the persistent group and 8/161 (5.0%) eyes in the nonpersistent group developed an end-stage disease with a subfoveal fibrosis during the observational period (p = 0.013).

Conclusion

We found that eyes with nAMD that were nonpersistent to intravitreal aflibercept therapy experienced statistically significantly worse VA compared to eyes persistent to therapy within 3 years. Moreover, eyes in the nonpersistent group had a four-fold higher risk of developing a fovea-involving fibrosis. Considering the potential irreversible deterioration with respect to best-corrected VA within nAMD, strategies need to be developed for patients at risk of nonpersistence to therapy.

Clinical Wide-Field Retinal Image Deep Learning Classification of Exudative and Non-Exudative Age-Related Macular Degeneration

Background: Age-related macular degeneration (AMD) is a disease that currently affects approximately 196 million individuals and is projected to affect 288 million in 2040. As a result, better and earlier detection methods for this disease are needed in an effort to provide a higher quality of care. One way to achieve this is through the utilization of machine learning. A deep neural network, specifically a convoluted neural network (CNN) can be trained to differentiate between different types of AMD images given the proper training data.

Methods: In this study, a CNN was trained on 420 Optos wide-field retinal images for 70 epochs in order to classify between exudative and non-exudative AMD. These images were obtained and labeled by ophthalmologists from the Martel Eye Clinic in Rancho Cordova, CA. 

Results: After completing the study, a model was created with 88% accuracy. Both the training and validation loss started above 1 and ended below 0.2. Despite only analyzing a single image at a time, the model was still able to accurately identify if the individual had AMD in both eyes or one eye only. The model had the most trouble with bilateral non-exudative AMD. Overall the model was fairly accurate in the other categories. It was noted that the neural network was able to further differentiate from a single image if the disease is present in left, right, or both eyes. This is a point of contention for further investigation as it is impossible for the artificial intelligence (AI) to extrapolate the condition of both eyes from only one image.

Conclusion: This research fostered the development of a CNN that was able to differentiate between exudative and non-exudative AMD. As well as determine if the disease is present in the right, left, or both eyes with a relatively high degree of accuracy. The model was trained on clinical data and can theoretically be used to classify other clinical images it has never encountered before.