scholarly journals Deep-learning-based Prediction of Late Age-Related Macular Degeneration Progression

2019 ◽  
Author(s):  
Qi Yan ◽  
Daniel E. Weeks ◽  
Hongyi Xin ◽  
Anand Swaroop ◽  
Emily Y. Chew ◽  
...  
Keyword(s):  
Macular Degeneration ◽  
Area Under The Curve ◽  
Image Data ◽  
Age Related Macular Degeneration ◽  
Individual Risk ◽  
Fundus Images ◽  
Age Related ◽  
Genetic And Environmental Factors ◽  
Disease Study ◽  
Individual Risk Assessment

ABSTRACTBoth genetic and environmental factors influence the etiology of age-related macular degeneration (AMD), a leading cause of blindness. AMD severity is primarily measured by fundus images and recently developed machine learning methods can successfully predict AMD progression using image data. However, none of these methods have utilized both genetic and image data for predicting AMD progression. Here we jointly used genotypes and fundus images to predict an eye as having progressed to late AMD with a modified deep convolutional neural network (CNN). In total, we used 31,262 fundus images and 52 AMD-associated genetic variants from 1,351 subjects from the Age-Related Eye Disease Study (AREDS) with disease severity phenotypes and fundus images available at baseline and follow-up visits over a period of 12 years. Our results showed that fundus images coupled with genotypes could predict late AMD progression with an averaged area under the curve (AUC) value of 0.85 (95%CI: 0.83-0.86). The results using fundus images alone showed an averaged AUC of 0.81 (95%CI: 0.80-0.83). We implemented our model in a cloud-based application for individual risk assessment.

Patient Use of Dietary Supplements, Home Monitoring, or Genetic Testing for Nonneovascular Age-Related Macular Degeneration

2021 ◽  
pp. 247412642198922
Author(s):  
Brittany C. Tsou ◽  
T.Y. Alvin Liu ◽  
Jun Kong ◽  
Susan B. Bressler ◽  
J. Fernando Arevalo ◽  
...  
Keyword(s):  
Genetic Testing ◽  
Macular Degeneration ◽  
Dietary Supplements ◽  
Home Monitoring ◽  
Cross Sectional Study ◽  
Age Related Macular Degeneration ◽  
Cross Sectional ◽  
Supplement Use ◽  
Age Related ◽  
Disease Study

Purpose: This work evaluated the use and type of dietary supplements and home monitoring for nonneovascular age-related macular degeneration (AMD), as well as the prevalence of genetic testing among patients with AMD. Methods: A cross-sectional study was conducted of 129 participants older than 50 years who completed self-administered questionnaires regarding usage and type of dietary supplements and home monitoring, as well as the participants’ use of genetic testing for AMD. Results: Of 91 participants with AMD, 83 (91.2%) took vitamins, including 55 (60.4%) who used an Age-Related Eye Disease Study (AREDS) or AREDS2 formulation. Of 38 without AMD, 31 (81.6%) took vitamins (difference from participants with AMD = 9.6% [95% CI, 0%-23.2%]), including 2 on an AREDS formulation. Among 82 participants with AMD who were AREDS candidates (intermediate or advanced AMD in 1 or both eyes), 51 (62.2%; 95% CI, 51.7%-72.7%) took an AREDS or AREDS2 formulation, and 31 (37.8%) did not (5 were unsure). Additionally, 50 (61.0%; 95% CI, 50.4%-71.6%) AREDS candidates did some type of home monitoring. Only 1 (1.2%; 95% CI, 0%-3.6%) underwent genetic testing for AMD. Among 9 with AMD who were not AREDS candidates, 4 (44.4%) used an AREDS formulation, 4 (44.4%) did not, and 1 (11.1%) was unsure; only 1 (11.1%) of these 9 performed home monitoring. Conclusions: Despite similar results from past surveys and AREDS2 data supporting supplement use in 2013 and home monitoring in 2014, these findings suggest about one-third of AREDS candidates do not do so, providing further support for improving education regarding appropriate supplement and home monitoring usage. Genetic testing for AMD also appears infrequent.

scholarly journals Automated diagnosis of Age-related Macular Degeneration using greyscale features from digital fundus images

2014 ◽  
Vol 53 ◽  
pp. 55-64 ◽  
Author(s):  
Muthu Rama Krishnan Mookiah ◽  
U. Rajendra Acharya ◽  
Joel E.W. Koh ◽  
Vinod Chandran ◽  
Chua Kuang Chua ◽  
...  
Keyword(s):  
Macular Degeneration ◽  
Age Related Macular Degeneration ◽  
Fundus Images ◽  
Automated Diagnosis ◽  
Age Related

GENETIC AND ENVIRONMENTAL FACTORS ASSOCIATED WITH RETICULAR PSEUDODRUSEN IN AGE-RELATED MACULAR DEGENERATION

Retina ◽  
2013 ◽  
Vol 33 (5) ◽  
pp. 998-1004 ◽  
Author(s):  
Nathalie Puche ◽  
Rocio Blanco-Garavito ◽  
Florence Richard ◽  
Nicolas Leveziel ◽  
Jennyfer Zerbib ◽  
...  
Keyword(s):  
Environmental Factors ◽  
Macular Degeneration ◽  
Age Related Macular Degeneration ◽  
Factors Associated ◽  
Reticular Pseudodrusen ◽  
Age Related ◽  
Genetic And Environmental Factors

Major Predictive Factors for Progression of Early to Late Age-Related Macular Degeneration

2020 ◽  
Vol 243 (6) ◽  
pp. 444-452 ◽  
Author(s):  
Vasilena Sitnilska ◽  
Eveline Kersten ◽  
Lebriz Altay ◽  
Tina Schick ◽  
Philip Enders ◽  
...  
Keyword(s):  
Prediction Model ◽  
Macular Degeneration ◽  
Area Under The Curve ◽  
Age Related Macular Degeneration ◽  
Advanced Age ◽  
Fundus Photography ◽  
Imaging Biomarkers ◽  
Nucleotide Polymorphisms ◽  
Phenotypic Profile ◽  
Age Related

<b><i>Introduction:</i></b> We present a prediction model for progression from early/intermediate to advanced age-related macular degeneration (AMD) within 5.9 years. <b><i>Objectives:</i></b> To evaluate the combined role of genetic, nongenetic, and phenotypic risk factors for conversion from early to late AMD over ≥5 years. <b><i>Methods:</i></b> Baseline phenotypic characteristics were evaluated based on color fundus photography, spectral-domain optical coherence tomography, and infrared images. Genotyping for 36 single-nucleotide polymorphisms as well as systemic lipid and complement measurements were performed. Multivariable backward logistic regression resulted in a final prediction model. <b><i>Results and Conclusions:</i></b> During a mean of 5.9 years of follow-up, 22.4% (<i>n</i> = 52) of the patients (<i>n</i> = 232) showed progression to late AMD. The multivariable prediction model included age, <i>CFH</i> variant rs1061170, pigment abnormalities, drusenoid pigment epithelial detachment (DPED), and hyperreflective foci (HRF). The model showed an area under the curve of 0.969 (95% confidence interval 0.948–0.990) and adequate calibration (Hosmer-Lemeshow test, <i>p</i> = 0.797). In addition to advanced age and carrying a <i>CFH</i> variant, pigment abnormalities, DPED, and HRF are relevant imaging biomarkers for conversion to late AMD. In clinical routine, an intensified monitoring of patients with a high-risk phenotypic profile may be suitable for the early detection of conversion to late AMD.

ADHERENCE TO RECOMMENDATIONS OF THE AGE-RELATED EYE DISEASE STUDY IN PATIENTS WITH AGE-RELATED MACULAR DEGENERATION

Retina ◽  
2010 ◽  
Vol 30 (8) ◽  
pp. 1166-1170 ◽  
Author(s):  
Bradley S Hochstetler ◽  
Ingrid U Scott ◽  
Allen R Kunselman ◽  
Kyle Thompson ◽  
Erica Zerfoss
Keyword(s):  
Macular Degeneration ◽  
Age Related Macular Degeneration ◽  
Eye Disease ◽  
Age Related ◽  
Disease Study

scholarly journals Development of a Deep-Learning-Based Artificial Intelligence Tool for Differential Diagnosis between Dry and Neovascular Age-Related Macular Degeneration

Diagnostics ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 261
Author(s):  
Tae-Young Heo ◽  
Kyoung Min Kim ◽  
Hyun Kyu Min ◽  
Sun Mi Gu ◽  
Jae Hyun Kim ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Differential Diagnosis ◽  
Deep Learning ◽  
Macular Degeneration ◽  
Data Augmentation ◽  
Treatment Strategies ◽  
Image Data ◽  
Age Related Macular Degeneration ◽  
Age Related ◽  
Leave One Out

The use of deep-learning-based artificial intelligence (AI) is emerging in ophthalmology, with AI-mediated differential diagnosis of neovascular age-related macular degeneration (AMD) and dry AMD a promising methodology for precise treatment strategies and prognosis. Here, we developed deep learning algorithms and predicted diseases using 399 images of fundus. Based on feature extraction and classification with fully connected layers, we applied the Visual Geometry Group with 16 layers (VGG16) model of convolutional neural networks to classify new images. Image-data augmentation in our model was performed using Keras ImageDataGenerator, and the leave-one-out procedure was used for model cross-validation. The prediction and validation results obtained using the AI AMD diagnosis model showed relevant performance and suitability as well as better diagnostic accuracy than manual review by first-year residents. These results suggest the efficacy of this tool for early differential diagnosis of AMD in situations involving shortages of ophthalmology specialists and other medical devices.

Sign in / Sign up

Export Citation Format

Share Document