Next Article in Journal
An Efficient Deep Learning Method for Detection of COVID-19 Infection Using Chest X-ray Images
Next Article in Special Issue
Natural Language Processing Applications for Computer-Aided Diagnosis in Oncology
Previous Article in Journal
Clinical Applications of Quantitative Perfusion Imaging with a C-Arm Flat-Panel Detector—A Systematic Review
Previous Article in Special Issue
Automated Identification of Multiple Findings on Brain MRI for Improving Scan Acquisition and Interpretation Workflows: A Systematic Review
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Diagnostics
Volume 13
Issue 1
10.3390/diagnostics13010130
diagnostics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

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

by
Abhishek Vyas
1,
Sundaresan Raman
1,
Janani Surya
2,
Sagnik Sen
3,4 and
Rajiv Raman
2,*
1
Birla Institute of Technology & Science, Pilani 333031, India
2
Sankara Nethralaya Medical Research Foundation, Chennai 600006, India
3
Moorfields Eye Hospital, London EC1V 2PD, UK
4
Aravind Eye Hospital, Madurai 625020, India
*
Author to whom correspondence should be addressed.
Diagnostics 2023, 13(1), 130; https://doi.org/10.3390/diagnostics13010130
Submission received: 24 October 2022 / Revised: 16 December 2022 / Accepted: 22 December 2022 / Published: 30 December 2022
(This article belongs to the Collection Reviews on Artificial Intelligence and Natural Language Processing in Medical Diagnostics)
Browse Figures
Review Reports Versions Notes

Abstract

:
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.

1. Introduction

Diabetes has become the fifth leading cause of blindness across the globe, due to which ophthalmic diseases are a global concern. Retinal disorders can cause blindness, but early diagnosis and timely treatment can prevent vision loss. Therefore, there is a dire need for automated diagnosis systems to assist in the early diagnosis of ophthalmic disease. There exist many retinal diseases. Cataract refers to the clouding of the lens, and in glaucoma the optic nerve of the eye that provides information to the brain is damaged, which can lead to gradual vision loss when left untreated and in diabetic retinopathy, where the blood vessels of the eye are damaged owing to the complication of diabetes. Researchers developed automatic detection systems to detect cataract [1,2,3,4], glaucoma [5], and diabetic retinopathy [6,7].
Age-related macular degeneration is also a leading cause of visual impairment and severe vision loss and is the most common form of maculopathy leading to vision loss in people [8,9]. AMD affects individuals over the age of 55 years. According to the world report on vision, of the estimated 196 million people suffering globally from age-related macular degeneration, 10.4 million (5.3%) have moderate or severe distance vision impairment or blindness from more severe forms of the condition [10].
A meta-analysis [11] suggested that the number of people in Europe affected by any AMD is expected to increase by 15% by 2050. AMD can be divided into subgroups according to the presence/absence of neo-vascularization–dry/non-neo-vascular and wet/neovascular AMD (nAMD). Several risk factors of AMD have been identified: age; gender; race; obesity; hypertension; smoking; sunlight; diet; phenotypic; demographic; environmental; genetic; alcohol consumption; and molecular risk factors; etc. [12,13,14,15,16,17,18,19,20,21,22,23,24,25]. Therefore, using risk factors as biomarkers for predicting AMD and AMD progression is a significant area of research
Artificial intelligence (AI) in diagnosis and prognosis represents a paradigm shift in healthcare. Artificial intelligence (AI) has already demonstrated proof-of-concept in medical fields such as radiology, pathology, and dermatology, which are similar to ophthalmology as they are deeply rooted in diagnostic imaging, which is the most prominent application of AI in healthcare. AI in medicine has overwhelming advantages: it can detect and learn features from large volumes of imaging data using efficient algorithms, assisting clinical practice. It can foster personalized medicine and help reduce diagnostic and therapeutic errors. In addition, AI can correlate novel features and recognize disease-specific patterns to gain innovative scientific insight. AI aims to contribute to better care outcomes and improve the productivity and efficiency of care delivery.
Many statistical methods have been designed to identify important risk factors from clinical data in the context of risk factors. However, an AI-based risk identification tool is needed to identify risk factors for ophthalmic diseases. This will nullify practitioner-dependent biases seen commonly in assessments of patients and hence the conventional methods of identifying risk factors. Novel treatments are being widely investigated in several clinical trials for both forms of AMD [26,27]. A meta-analysis has shown promising results for the diagnostic accuracy of the machine learning classifiers for AMD and its implementation in clinical settings [28]. Hence, using AI with deep learning tools has excellent potential in AMD, for diagnostic purposes–while allowing for a more efficient and accurate approach–to prognostication of affected individuals and perhaps to directly determine the efficacy of investigational medical products.
This review aims to summarize the literature related to techniques used to study risk factors of AMD and investigate AI-based options available for the same.
The paper is organized as follows: Section 2 presents the methods used in this research. Section 3 reviews statistical techniques used to identify risk factors for AMD. Section 4 provides a review of artificial intelligence techniques used in AMD diagnosis. Section 5 discusses the significance of AI over traditional statistical methods. Section 6 includes the discussion, and Section 7 lists the conclusion.

2. Methods

2.1. Study Selection

Search Terms

We used PubMed as our primary electronic search engine for looking into published articles related to AMD from 1991 to 2019. The search terms used were “age-related macular degeneration,” “risk factors,” “prevalence,” and “incidence.” The search strategy used both text word searches and subject headings. Additionally, initial search terms were updated after searching the reference lists of relevant articles. The articles were restricted to only the English language.

2.2. Inclusion and Exclusion Criteria

After preliminary searches, criteria were developed in an iterative process. We included studies on AMD, which identified risk factors using different statistical techniques. All risk factors studied, from clinical variables to genes, were considered for inclusion. Studies that did not mention statistical techniques to identify the risk factors were excluded.

2.3. Selecting Studies

A total of 118 articles were retrieved from PubMed after the initial search, of which 34 articles met this study’s objective and were selected for review. The flow diagram describing the study selection is depicted in Figure 1. The year-wise classification of included articles is shown in Figure 2.

3. Statistical Techniques for Risk Factor Identification

In medical research, statistical analyses are an essential component that can further the understanding of risk factors, treatment effects, and other aspects of the disease when appropriately applied. Statistics has become an integral part of research in ophthalmology, and its use to evaluate experimental data in ophthalmology has increased. Figure 3 depicts the various application of statistical methods from a clinician’s perspective.
Table 1 illustrates the studies included in this review, the overview of the risk factors identified, and the statistical tools used to identify them. The commonly identified risk factors identified may be divided into ocular-based factors (focal hyperpigmentation, drusen, slow choroidal filling, cataract, hyperopia), susceptibility-based risk factors (age, gender, race, hypertension, cardiovascular status, body mass index, obesity, and cholesterol), exposure-related risk factors (smoking, alcohol, physical activity) and genetics (Table 1). Figure 4 depicts the classification by percentage of techniques used in included articles in Table 1.
The review identified 34 prospective studies investigating risk factors for AMD. There was good evidence that risk factors like smoking, alcohol consumption, previous cataract surgery, age, high-density lipoprotein (HDL) cholesterol, BMI, female gender, and focal hyper-pigmentation were more often associated with being independent risk factors for AMD. One study showed a significant association between cardiovascular disease and the risk factors associated with AMD. In contrast, two studies showed no significant association between cardiovascular disease and its risk factors with AMD. Therefore, more investigation is needed to identify the association of cardiovascular disease and its risk factors with AMD.

4. Artificial Intelligence in AMD

In AMD pathogenesis, genetics plays a critical role. Many variants associated with AMD have been identified by sequencing studies and genome-wide association studies [63]. Figure 5 depicts the various applications of artificial intelligence from a clinician’s perspective. The input to AI can be data of the following types: numerical/categorical, fundus images, and optical coherence tomography (OCT) volumes. The most common imaging modalities in AI for AMD are OCT, color fundus image, and fundus autofluorescence (FAF).
Based on the input to the AI techniques, the application of AI can be divided into the following categories:

4.1. Lesion Detection, Quantification, and Extraction

A European study was done by Grinsven et al. [64] to detect and quantify drusen on color fundus photographs in 407 eyes without AMD or with early to moderate AMD. This study demonstrated that for detecting the presence of drusen and estimating the area, it achieved an intraclass correlation coefficient (ICC) larger than 0.85 and was in keeping with experienced human observers. Consequently, another algorithm was explored for the automatic detection of reticular pseudo-drusen (RPD) [65]. Automated RPD quantification achieved an ICC of 0.7, similar to the observers. Consequently, Liefers et al. [66] used a deep learning model to segment and quantify retinal features in individuals with atrophic AMD and nAMD. The mean ICC obtained was 0.66 ± 0.22 and 0.62 ± 0.21 for the model and observers, respectively.

4.2. Automated Image Segmentation

Schmidt-Erfuth et al. [67] analyzed OCT volume scans features–intraretinal cystoid fluid (IR), subretinal fluid (SRF), and pigment epithelial detachments (PED) to evaluate the predictive potential of machine learning in terms of best-corrected visual acuity (BCVA). A modest correlation was found between BCVA and OCT at baseline (R2 = 0.21). Subsequently, the same group used a deep learning method and a convolutional neural network (CNN) to accurately measure fluid response to anti-vascular endothelial growth factor (VEGF) treatment in neovascular AMD [68] in the HARBOR study. For this purpose, the group used automatic volumetric quantification data of fluid volumes in the OCT. Subsequently, the authors also validated the retinal fluid volumes (intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED)) as important biomarkers in neovascular AMD [69]. Lee et al. [70] utilized a deep learning framework to perform automated diagnosis and segmentation of retinal diseases. They created a key OCT image segmentation model. The authors applied this methodology in 14,884 clinically heterogenous scans.

4.3. AMD Classification

Yim et al. [71] combined 3D OCT images and automatic tissue maps in individuals with nAMD in one eye to predict progression in the contralateral eye to nAMD. This system outperformed five out of six experts and achieved a sensitivity of 80% at 55% specificity and 34% specificity at 90% sensitivity. Yan et al. [72] used data of disease severity phenotypes and fundus images available at baseline and follow-up visits over 12 years from AREDS to predict late AMD progression. They achieved an average AUC value of 0.85 when fundus images were coupled with genotypes to predict late AMD progression. Only fundus images showed a middle area under the ROC curve value of 0.81. Peng et al. [73] combined deep learning (DL) and survival analysis to develop, train, and validate a framework for predicting individual risk of late AMD. The model achieved a 5-year C-statistic of 86.4 when validated against an independent test data set of 601 participants, which substantially exceeded that of retinal specialists using two existing clinical standards of 81.3 and 82.0, respectively. Ajana et al. [74] used genotypic, lifestyle, and phenotypic factors to develop a prediction model for advanced AMD. The training data set included Rotterdam Study I [75] (RS-I) enrolled participants. The validation dataset included antioxidants, lipides essentiels, nutrition et maladies oculaires [76] (ALIENOR) study enrolled participants. The cross-validated AUC estimation in RS-I was 0.92 at five years, 0.92 at ten years, and 0.91 at 15 years. In ALIENOR, the AUC reached 0.92 at five years. Seddon et al. [77] calculated the AMD progression risk score to discriminate progressors from nonprogressors to advanced AMD based on demographic, ocular, behavioral, treatment, and genetic factors. They obtained a C-statistic score of 0.83, compared to C statistics for coronary heart disease (CHD), 0.79 for white men, and 0.83 for white women in the Framingham study cohort, and somewhat lower in several replication samples [78].
Seddon et al. [79] included time-varying progression rates up to 12 years, macular drusen size in both eyes at baseline, AMD status at baseline, six genetic variants, and environmental and demographic factors to build a model for AMD progression. The model’s AUC for progression at ten years with drusen size, environmental covariates, and genetic factors was 0.915 in the total sample. Klein et al. [80] constructed a risk assessment model to develop advanced AMD incorporating phenotypic, demographic, environmental, and genetic risk factors. The model did well on performance measures, with excellent discrimination (C statistic = 0.872) and excellent calibration and overall performance (Brier score at five years = 0.08). Seddon et al. [81] developed an online application and a predictive model. The online application assists in clinical decision-making and is available at www.seddonamdriskscore.org. The model included age, ten genetic loci, sex, BMI, education, baseline AMD status, and smoking, and the AUC for progression to advanced AMD over ten years was 91.1%. Spencer et al. [82] combined the results from the grammatical evolution of neural networks (GENN) and logistic regression models using a consensus approach to build an algorithm using a constellation of environmental risk factors and knowledge of each individual’s particular genetic profile, which was successful in differentiating between low and high-risk groups for AMD with a sensitivity of 77.0% and specificity of 74.1%.
Fraccaro et al. [83] used black-box methods, such as random forests, AdaBoost, and SVM, as well as white-box techniques, including decision trees and logistic regression, to develop models to diagnose AMD, including demographics, depigmentation area, and, for each eye, presence/absence of significant AMD-related clinical signs (retinal pigment epithelium, soft drusen, defects/pigment mottling, subretinal fluid, subretinal hemorrhage, macula thickness, subretinal fibrosis, macular scar). The model’s logistic regression, AdaBoost, and random forests achieved an AUC of 0.92, followed by decision trees and SVM with an AUC of 0.90. Shin et al. [84] used ocular and systemic factors to develop a risk prediction model for the progression of AMD in Koreans. The model achieved a C statistic of 0.84, indicating excellent predictive power. The fundus images were used for AMD grading; they can also be used with genotypes to predict the probability of late AMD progression. Such predictions can slow the disease progression by urging the patients to start preventative care beforehand since late AMD is irreversible.
The review of AI techniques for AMD as described in Section 4.1, Section 4.2 and Section 4.3 is summarized in Table 2.

5. Significance of AI over Traditional Statistical Methods

Open Problems

Statistical methods can work only with numerical or categorical data. In contrast, artificial intelligence (AI) can detect AMD automatically. AI techniques can assist in extracting the vascular skeleton and thus compute features like tortuosity, fractal index, thickness, and vessel density of blood vessels in a fundus image. AI can also detect and quantify drusen present in a fundus image. Moreover, automatic image segmentation can also be performed using AI.
Traditional statistical methods rely on strong assumptions, such as the additivity of the parameters within the linear predictor, the type of error distribution, and proportional hazards. These assumptions are often overlooked in the scientific literature and are not met in clinical practice. For instance, when studying survival in gastric cancer patients, the assumption of proportional hazards has been violated, as nodal status and the prognostic significance of the depth of tumor invasion tend to decrease with increasing follow-up. At the same time, the loss of the TP53 gene and the histology acquire prognostic importance after at least two years of follow-up [85]. On the other hand, machine learning (ML) techniques in AI have considerable flexibility and are free from a priori assumptions.
Traditional statistical approaches often fail because they make an a priori selection of the variables to be considered. For instance, a Cochrane review in gastric cancer surgery dealing with the extension of lymphadenectomy was later withdrawn and criticized because it failed to assess the quality of surgical procedures under comparison [86]. Whereas in ML any number of features can be chosen based on all the available information.
Traditional regression models show several limitations in choosing the most important risk factors when there are many predictors and few observations, such as in transcriptomics, genomics, metabolomics, and proteomics [87]. In contrast, ML is particularly suited for such situations. Therefore, it is possible to use numerous approaches to apply small datasets in building ML predictive models.
Traditional statistical methods can only address interactions between single potential confounders and the primary determinant. For instance, in gastric cancer patients, the effect of the surgical approach on survival is modulated by histology and tumor stage [88]. However, within a Cox model, it is not easy to highlight this second-order interaction [89], as the interaction between lymphadenectomy and histology becomes apparent after the first two years of follow-up. ML can also efficiently address such interactions. Furthermore, ML algorithms can analyze various data types (imaging data, laboratory findings, and demographic data) and integrate them into predictions for illness risk, prognosis, diagnosis, and appropriate treatments [90].

6. Discussion

Out of the included studies, the review found that for identifying risk factors, 32.35% used logistic regression, 8.82% of each used univariate & multivariate analyses, multivariable logistic regression, multivariate stepwise logistic regression, generalized estimating equation logistic regressions, 5.88% used polychotomous logistic regression and 2.94% of each used Poisson regression, unconditional logistic analysis, standard bivariate, and multivariate analyses, multivariate Cox regression, logistic regression, and Mantel-Haenszel analysis, survival analysis and Cox proportional hazards regression. The classification by number and percentage of techniques used in included articles is depicted in Figure 3.
AI techniques often used are logistic regression and deep learning for predicting AMD. The metrics evaluated by the AI techniques are not comparable due to the different datasets used in these studies. The prediction of AMD can be done by acquiring dataset of OCT volumes, color fundus images, and clinical data of risk factors. However, there is a tradeoff between the cost of obtaining the dataset and the metrics (accuracy, AUC, etc.) of the AI models received to predict AMD. In this context, the cost of obtaining OCT volumes is higher than obtaining color fundus images which is higher than obtaining clinical risk factor data. In this context, Yim et al. [71] demonstrated that an AI system using deep learning which combined 3D OCT images and automatic tissue maps in individuals with nAMD in one eye to predict progression in the contralateral eye to nAMD. This system outperformed five out of six experts and achieved a sensitivity of 80% at 55% specificity and 34% specificity at 90% sensitivity. Grinsven et al. [64] developed a supervised learning algorithm to detect and quantify drusen on color fundus photographs without AMD or with early to moderate AMD. The system achieved areas under the receiver operating characteristic (ROC) curve of 0.948 and 0.954 for automatic AMD risk assessment, which was similar in performance compared to human observers. Moreover, Ajana et al. [74] used genotypic, lifestyle, and phenotypic factors to develop a prediction model for advanced AMD and achieved an AUC achieved of 0.92. Therefore, using OCT volumes, fundus images, and clinical data result in similar performance if the metrics are compared to predict presence of AMD. If a method performs only moderately better using OCT volumes of data as compared to using fundus or clinical data, then the method may not prove economical. Therefore, there is always a tradeoff between the cost of obtaining the data and the metrics achieved by the AI models to predict AMD.
AI-based methods can be vital in identifying potential biomarkers for guiding targeted therapy in ophthalmology. Many risk factors are embedded in the high dimensional data produced by various imaging modalities. AI can process this high-dimensional data to find some risk factors for AMD, whereas statistical methods do not have high-dimensional data as input. Saha et al. [91] used deep learning for the automated identification of these OCT-based AMD biomarkers.
Despite the AI-based models showing a high level of accuracy in many of the diseases in ophthalmology, there are still many technical and clinical challenges for real-time deployment and clinical implementation of these models in clinical practice. These challenges could arise in both the research and clinical settings. Many studies’ training datasets are from relatively homogeneous populations [92,93,94]. AI training and testing using retinal images are subject to numerous variabilities, including the field of view, the width of the field, image quality, image magnification, and participant ethnicities. Diversifying the data set regarding image-capture hardware and races could help address this challenge [95].
The limited availability of large amounts of data is another challenge in developing AI models in ophthalmology. The software will likely produce inaccurate outcomes if the training set of images given to the AI tool is too small or not representative of natural patient populations. In addition, more evidence on obtaining high-quality ground-truth labels is required for different imaging tools.
Many DL systems in AI have reported a robust diagnostic performance, although some papers did not show how the power calculation was performed for the independent data sets. A power calculation should consider the following: the prevalence of the disease, type 1 and 2 errors, CIs (confidence intervals), and desired precision. The desired operating threshold should be first preset on the training set, followed by an analysis of performance metrics such as sensitivity and specificity on the test set to assess the calibration of the algorithm.
AI is adopted in healthcare, but it is still not on the horizon as clinicians and patients are concerned about AI and DL being ‘black boxes.’ It is not only the quantitative algorithmic performance in healthcare but the underlying features essential to improve physicians’ acceptance through which the algorithm classifies the disease. Generating heat maps highlighting the regions of influence on the image which contributed to the algorithmic conclusion may be the first step, although such maps are often challenging to interpret [96]. Explainable artificial intelligence (XAI) can also be used, a set of methods and processes that allows human users to comprehend and trust the results and output created by machine learning algorithms.
There are some limitations to the review. First, the review is limited to a certain number of studies and the associated risk factors. Second, the review is limited to only AMD. It can be further extended to other ophthalmic diseases like glaucoma, retinopathy of prematurity, cataract, diabetic retinopathy, etc.

7. Conclusions

To the best of our knowledge, this review is the first of its kind which analyzes the techniques for identifying the risk factors and predicting the disease using risk factor datasets in ophthalmology. Other reviews in the literature find modifiable and non-modifiable risk factors related to AMD. However, such a review of techniques to identify risk factors for AMD is so far not looked upon. In the study, logistic regression was found as the most used technique to identify risk factors for AMD. This review has highlighted that ML techniques can also be used for similar purposes. The study has demonstrated that statistical methods were used to determine the risk factors for AMD to a large extent. AI-based tools have already started managing epidemics and discovering potential drugs. Therefore, AI technology is more suitable to play a significant role in identifying risk factors in ophthalmology. To a reasonable extent, AI techniques play an essential role in predicting AMD. They have great potential to be used for personalized care in diagnosing, prognosis, and treating diseases in ophthalmology. Future studies can focus on novel analysis methods and biomarkers diagnosing AMD. For example, many patients with diabetic retinopathy do not respond well to current therapeutics. Therefore, new analytical techniques related to molecular biomarkers should accelerate progress in recent research [97]. In this context, erythrocyte membrane fluidity has been found as a biomarker for diabetic retinopathy [98]. Novel segmentation methods should be developed to unveil metabolic features as future work in this research [99,100].

Author Contributions

Conceptualization, R.R., S.R. and A.V.; methodology, A.V., J.S.; software, A.V.; validation, S.R. and R.R.; formal analysis, A.V.; investigation, R.R.; resources, S.S.; data curation, A.V. and J.S.; writing—original draft preparation, A.V.; writing—review and editing, A.V., S.R., S.S. and R.R.; visualization, S.R. and A.V.; supervision, S.R. and R.R.; project administration, R.R. and S.R.; All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Institutional Review Board Statement

Not Applicable.

Informed Consent Statement

Not Applicable.

Data Availability Statement

Datasets available on request form corresponding author only as the data are sensitive and participants may be potentially identifiable.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Imran, A.; Li, J.; Pei, Y.; Akhtar, F.; Mahmood, T.; Li, Z. Fundus image-based cataract classification using a hybrid convolutional and recurrent neural network. Vis. Comput. 2021, 37, 2407–2417. [Google Scholar] [CrossRef]
  2. Imran, A.; Li, J.; Pei, Y.; Akhtar, F.; Yang, J.J.; Dang, Y. Automated identification of cataract severity using retinal fundus images. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 2020, 8, 691–698. [Google Scholar] [CrossRef]
  3. Imran, A.; Li, J.; Pei, Y.; Akhtar, F.; Yang, J.J.; Wang, Q. Cataract detection and grading with retinal images using SOM-RBF neural network. In Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China, 6–9 December 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 2626–2632. [Google Scholar]
  4. Imran, A.; Li, J.; Pei, Y.; Mokbal, F.M.; Yang, J.J.; Wang, Q. Enhanced intelligence using collective data augmentation for CNN based cataract detection. In International Conference on Frontier Computing; Springer: Singapore, 2019; pp. 148–160. [Google Scholar]
  5. Latif, J.; Tu, S.; Xiao, C.; Ur Rehman, S.; Imran, A.; Latif, Y. ODGNet: A deep learning model for automated optic disc localization and glaucoma classification using fundus images. SN Appl. Sci. 2022, 4, 98. [Google Scholar] [CrossRef]
  6. Bilal, A.; Sun, G.; Mazhar, S.; Imran, A.; Latif, J. A Transfer Learning and U-Net-based automatic detection of diabetic retinopathy from fundus images. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 2022, 10, 663–674. [Google Scholar] [CrossRef]
  7. Bilal, A.; Sun, G.; Mazhar, S.; Imran, A. Improved Grey Wolf Optimization-Based Feature Selection and Classification Using CNN for Diabetic Retinopathy Detection. In Evolutionary Computing and Mobile Sustainable Networks; Springer: Singapore, 2022; pp. 1–14. [Google Scholar]
  8. Mitchell, P.; Liew, G.; Gopinath, B.; Wong, T.Y. Age-related macular degeneration. The Lancet 2018, 392, 1147–1159. [Google Scholar] [CrossRef] [PubMed]
  9. Ammar, M.J.; Hsu, J.; Chiang, A.; Ho, A.C.; Regillo, C.D. Age-related macular degeneration therapy: A review. Curr. Opin. Ophthalmol. 2020, 31, 215–221. [Google Scholar] [CrossRef]
  10. World Report on Vision; World Health Organization: Geneva, Switzerland, 2019.
  11. Li, J.Q.; Welchowski, T.; Schmid, M.; Mauschitz, M.M.; Holz, F.G.; Finger, R.P. Prevalence and incidence of age-related macular degeneration in Europe: A systematic review and meta-analysis. Br. J. Ophthalmol. 2020, 104, 1077–1084. [Google Scholar] [CrossRef]
  12. Pujol-Lereis, L.M.; Liebisch, G.; Schick, T.; Lin, Y.; Grassmann, F.; Uchida, K.; Zipfel, P.F.; Fauser, S.; Skerka, C.; Weber, B.H. Evaluation of serum sphingolipids and the influence of genetic risk factors in age-related macular degeneration. PLoS ONE 2018, 13, e0200739. [Google Scholar] [CrossRef] [Green Version]
  13. Bhuachalla, B.N.; McGarrigle, C.A.; O’Leary, N.; Akuffo, K.O.; Peto, T.; Beatty, S.; Kenny, R.A. Orthostatic hypertension as a risk factor for age-related macular degeneration: Evidence from the Irish longitudinal study on ageing. Exp. Gerontol. 2018, 106, 80–87. [Google Scholar] [CrossRef]
  14. Seddon, J.M.; Widjajahakim, R.; Rosner, B. Rare and common genetic variants, smoking, and body mass index: Progression and earlier age of developing advanced age-related macular degeneration. Investig. Ophthalmol. Vis. Sci. 2020, 61, 32. [Google Scholar] [CrossRef]
  15. Jaisankar, D.; Swaminathan, G.; Roy, R.; Kulothungan, V.; Sharma, T.; Raman, R. Association of obesity and age-related macular degeneration in Indian population. Indian J. Ophthalmol. 2018, 66, 976. [Google Scholar]
  16. Roddy, G.W.; Rosa, R.H.; Viker, K.B.; Holman, B.H.; Hann, C.R.; Krishnan, A.; Gores, G.J.; Bakri, S.J.; Fautsch, M.P. Diet mimicking “fast food” causes structural changes to the retina relevant to age-related macular degeneration. Curr. Eye Res. 2020, 45, 726–732. [Google Scholar] [CrossRef] [PubMed]
  17. Patel, S.N.; Wu, C.; Obeid, A.; Sivalingam, M.; Gervasio, K.; Wibbelsman, T.D.; Levin, H.; Xu, D.; Regillo, C.D.; Hsu, J.; et al. Sociodemographic factors in neovascular age-related macular degeneration. Ophthalmology 2020, 127, 280–282. [Google Scholar] [CrossRef] [PubMed]
  18. Mahr, M.A.; Hodge, D.O.; Erie, J.C. Racial differences in age-related macular degeneration and associated anti–Vascular Endothelial Growth Factor Intravitreal injections among Medicare beneficiaries. Ophthalmol. Retin. 2018, 2, 1188–1195. [Google Scholar] [CrossRef] [PubMed]
  19. Sasaki, M.; Harada, S.; Kawasaki, Y.; Watanabe, M.; Ito, H.; Tanaka, H.; Takeuchi, A.; Tsubota, K.; Takebayashi, T.; Nishiwaki, Y.; et al. Gender-specific association of early age-related macular degeneration with systemic and genetic factors in a Japanese population. Sci. Rep. 2018, 8, 785. [Google Scholar] [CrossRef] [Green Version]
  20. Van Asten, F.; Simmons, M.; Singhal, A.; Keenan, T.D.; Ratnapriya, R.; Agrón, E.; Clemons, T.E.; Swaroop, A.; Lu, Z.; Chew, E.Y.; et al. A deep phenotype association study reveals specific phenotype associations with genetic variants in age-. Theycular degeneration: Age-Related Eye Disease Study 2 (AREDS2) report no. 14. Ophthalmology 2018, 125, 559–568. [Google Scholar] [CrossRef]
  21. Warwick, A.; Lottery, A. Genetics and genetic testing for age-related macular degeneration. Eye 2018, 32, 849–857. [Google Scholar] [CrossRef]
  22. Lorés-Motta, L.; de Jong, E.K.; den Hollander, A.I. Exploring the use of molecular biomarkers for precision medicine in age-related macular degeneration. Mol. Diagn. Ther. 2018, 22, 315–343. [Google Scholar] [CrossRef] [Green Version]
  23. Desmettre, T.J. Epigenetics in age-related macular degeneration (AMD). J. Français D’ophtalmologie 2018, 41, e407–e415. [Google Scholar] [CrossRef]
  24. Zhou, H.; Zhang, H.; Yu, A.; Xie, J. Association between sunlight exposure and risk of age-related macular degeneration: A meta-analysis. BMC Ophthalmol. 2018, 18, 331. [Google Scholar] [CrossRef] [Green Version]
  25. Dinu, M.; Pagliai, G.; Casini, A.; Sofi, F. Food groups and risk of age-related macular degeneration: A systematic review with meta-analysis. Eur. J. Nutr. 2019, 58, 2123–2143. [Google Scholar] [CrossRef] [PubMed]
  26. De Guimaraes, T.A.C.; Georgiou, M.; Bainbridge, J.W.B.; Michaelides, M. Gene therapy for neovascular age-related macular degeneration: Rationale, clinical trials and future directions. Br. J. Ophthalmol. 2021, 105, 151–157. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  27. De Guimaraes, T.A.C.; Varela, M.D.; Georgiou, M.; Michaelides, M. Treatments for dry age-related macular degeneration: Therapeutic avenues, clinical trials and future directions. Br. J. Ophthalmol. 2022, 106, 297–304. [Google Scholar] [CrossRef] [PubMed]
  28. Cheung, R.; Chun, J.; Sheidow, T.; Motolko, M.; Malvankar-Mehta, M.S. Diagnostic accuracy of current machine learning classifiers for age-related macular degeneration: A systematic review and meta-analysis. Eye 2022, 36, 994–1004. [Google Scholar] [CrossRef] [PubMed]
  29. Holz, F.G.; Wolfensberger, T.J.; Piguet, B.; Gross-Jendroska, M.; Wells, J.A.; Minassian, D.C.; Chisholm, I.H.; Bird, A.C. Bilateral macular drusen in age-related macular degeneration. Prognosis and risk factors. Ophthalmology 1994, 101, 8090455. [Google Scholar] [CrossRef] [PubMed]
  30. Tamakoshi, A.; Yuzawa, M.; Matsui, M.; Uyama, M.; Fujiwara, N.K.; Ohno, Y. Smoking and neovascular form of age-related macular degeneration in late middle-aged males: Findings from a case-control study in Japan. Research Committee on Chorioretinal Degenerations. Br. J. Ophthalmol. 1997, 81, 1722029. [Google Scholar] [CrossRef] [Green Version]
  31. Klein, R.; Klein, B.E.; Jensen, S.C. The relation of cardiovascular disease and its risk factors to the 5-year incidence of age-related maculopathy: The Beaver Dam Eye Study. Ophthalmology 1997, 104, 1804–1812. [Google Scholar] [CrossRef]
  32. Buch, H.; Vinding, T.; La Cour, M.; Jensen, G.B.; Prause, J.U.; Nielsen, N.V. Risk factors for age-related maculopathy in a 14-year follow-up study: The Copenhagen City Eye Study. Acta Ophthalmol. Scand. 2005, 83, 409–427. [Google Scholar] [CrossRef]
  33. Klein, R.; Deng, Y.; Klein, B.E.; Hyman, L.; Seddon, J.; Frank, R.N.; Wallace, R.B.; Hendrix, S.L.; Kuppermann, B.D.; Langer, R.D.; et al. Cardiovascular disease, its risk factors and treatment, and age-related macular degeneration: Women’s Health Initiative Sight Exam ancillary study. Am. J. Ophthalmol. 2007, 143, 2812860. [Google Scholar] [CrossRef] [Green Version]
  34. Chaine, G.; Hullo, A.; Sahel, J.; Soubrane, G.; Espinasse-Berrod, M.A.; Schutz, D.; Bourguignon, C.; Harpey, C.; Brault, Y.; Coste, M.; et al. Case-control study of the risk factors for age-related macular degeneration. France-DMLA Study Group. Br. J. Ophthalmol. 1998, 82, 1722735. [Google Scholar] [CrossRef] [Green Version]
  35. Delcourt, C.; Michel, F.; Colvez, A.; Lacroux, A.; Delage, M.; Vernet, M.H. Pola Study Vernet, and Group. Associations of cardiovascular disease and its risk factors with age-related macular degeneration: The POLA study. Ophthalmic Epidemiol. 2001, 8, 237–286. [Google Scholar] [CrossRef] [PubMed]
  36. Vine, A.K.; Stader, J.; Branham, K.; Musch, D.C.; Swaroop, A. Biomarkers of cardiovascular disease as risk factors for age-related macular degeneration. Ophthalmology 2005, 112, 16225921. [Google Scholar] [CrossRef] [PubMed]
  37. Clemons, T.E.; Milton, R.C.; Klein, R.; Seddon, J.M.; Ferris, F.L., 3rd. Age-Related Eye Disease Study Research Group. Risk factors for the incidence of Advanced Age-Related Macular Degeneration in the Age-Related Eye Disease Study (AREDS) AREDS report no. 19. Ophthalmology 2005, 112, 1513667. [Google Scholar]
  38. Fraser-Bell, S.; Wu, J.; Klein, R.; Azen, S.P.; Varma, R. Smoking, alcohol intake, estrogen use, and age-related macular degeneration in Latinos: The Los Angeles Latino Eye Study. Am. J. Ophthalmol. 2006, 141, 79–87. [Google Scholar] [CrossRef] [PubMed]
  39. Cheung, C.M.G.; Li, X.; Cheng, C.Y.; Zheng, Y.; Mitchell, P.; Wang, J.J.; Jonas, J.B.; Nangia, V.; Wong, T.Y. Prevalence and risk factors for age-related macular degeneration in Indians: A comparative study in Singapore and India. Am. J. Ophthalmol. 2012, 155, 23246273. [Google Scholar]
  40. Yip, J.L.; Khawaja, A.P.; Chan, M.P.; Broadway, D.C.; Peto, T.; Tufail, A.; Luben, R.; Hayat, S.; Bhaniani, A.; Wareham, N.J.; et al. Cross-Sectional and Longitudinal Associations between Cardiovascular Risk Factors and Age-Related Macular Degeneration in the EPIC-Norfolk Eye Study. PLoS ONE 2015, 10, e0132565. [Google Scholar] [CrossRef] [Green Version]
  41. Raman, R.; Pal, S.S.; Ganesan, S.; Gella, L.; Vaitheeswaran, K.; Sharma, T. The prevalence and risk factors for age-related macular degeneration in rural-urban India, Sankara Nethralaya Rural-Urban Age-related Macular degeneration study, Report No. 1. Eye 2016, 30, 688–697. [Google Scholar] [CrossRef] [Green Version]
  42. McGuinness, M.B.; Karahalios, A.; Kasza, J.; Guymer, R.H.; Finger, R.P.; Simpson, J.A. Survival Bias When Assessing Risk Factors for Age-Related Macular Degeneration: A Tutorial with Application to the Exposure of Smoking. Ophthalmic Epidemiol. 2017, 24, 229–238. [Google Scholar] [CrossRef]
  43. Connolly, E.; Rhatigan, M.; O’Halloran, A.M.; Muldrew, K.A.; Chakravarthy, U.; Cahill, M.; Kenny, R.A.; Doyle, S.L. Prevalence of age-related macular degeneration associated genetic risk factors and 4-year progression data in the Irish population. Br. J. Ophthalmol. 2018, 102, 1691–1695. [Google Scholar] [CrossRef]
  44. Butt, A.L.; Lee, E.T.; Klein, R.; Russell, D.; Ogola, G.; Warn, A.; Kingsley, R.M.; Yeh, J. Prevalence and risks factors of age-related macular degeneration in Oklahoma Indians: The Vision Keepers Study. Ophthalmology 2011, 118, 1380–1385. [Google Scholar] [CrossRef] [Green Version]
  45. Hyman, L.; Schachat, A.P.; He, Q.; Leske, M.C. Hypertension, cardiovascular disease, and age-related macular degeneration. Arch. Ophthalmol. 2000, 118, 351–359. [Google Scholar] [CrossRef] [Green Version]
  46. Age-Related Eye Disease Study Research Group. Risk factors associated with age-related macular degeneration. A case-control study in the age-related eye disease study: Age-Related Eye Disease Study Report Number 3. Ophthalmology 2000, 107, 2224–2232. [Google Scholar]
  47. Klein, R.; Cruickshanks, K.J.; Nash, S.D.; Krantz, E.M.; Nieto, F.J.; Huang, G.H.; Pankow, J.S.; Klein, B.E. The prevalence of age-related macular degeneration and associated risk factors. Arch Ophthalmol. 2010, 128, 750–758. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  48. Shim, S.H.; Kim, S.G.; Bae, J.H.; Yu, H.G.; Song, S.J. Risk Factors for Progression of Early Age-Related Macular Degeneration in Koreans. Ophthalmic Epidemiol. 2016, 23, 80–87. [Google Scholar] [CrossRef] [PubMed]
  49. Erke, M.G.; Bertelsen, G.; Peto, T.; Sjølie, A.K.; Lindekleiv, H.; Njølstad, I. Cardiovascular risk factors associated with age-related macular degeneration: The Tromsø Study. Acta Ophthalmol. 2014, 92, 662–669. [Google Scholar] [CrossRef]
  50. Krishnaiah, S.; Das, T.; Nirmalan, P.K.; Nutheti, R.; Shamanna, B.R.; Rao, G.N.; Thomas, R. Risk factors for age-related macular degeneration: Findings from the Andhra Pradesh eye disease study in South India. Investig. Ophthalmol. Vis. Sci. 2005, 46, 4442–4451. [Google Scholar] [CrossRef] [Green Version]
  51. Choudhury, F.; Varma, R.; McKean-Cowdin, R.; Klein, R.; Azen, S.P. Risk factors for four-year incidence and progression of age-related macular degeneration: The Los Angeles Latino eye study. Am. J. Ophthalmol. 2011, 152, 385–395. [Google Scholar] [CrossRef] [Green Version]
  52. Jonasson, F.; Fisher, D.E.; Eiriksdottir, G.; Sigurdsson, S.; Klein, R.; Launer, L.J.; Harris, T.; Gud-nason, V.; Cotch, M.F. Five-year incidence, progression, and risk factors for age-related macular degeneration: The age, gene/environment susceptibility study. Ophthalmology 2014, 121, 1766–1772. [Google Scholar] [CrossRef] [Green Version]
  53. Saunier, V.; Merle, B.M.; Delyfer, M.N.; Cougnard-Grégoire, A.; Rougier, M.B.; Amouyel, P.; Lambert, J.C.; Dartigues, J.F.; Korobelnik, J.F.; Delcourt, C. Incidence of and Risk Factors Associated With Age-Related Macular Degeneration: Four-Year Follow-up From the ALIENOR Study. JAMA Ophthalmol. 2018, 136, 473–481. [Google Scholar] [CrossRef]
  54. Lechanteur, Y.T.; van de Ven, J.P.; Smailhodzic, D.; Boon, C.J.; Klevering, B.J.; Fauser, S.; Groenewoud, J.M.; Van Der Wilt, G.J.; Hollander, A.I.; Hoyng, C.B. Genetic, behavioural, and sociodemographic risk factors for second eye progression in age-related macular degeneration. Investig. Ophthalmol. Vis. Sci. 2012, 53, 5846–5852. [Google Scholar] [CrossRef] [Green Version]
  55. Cougnard-Gregoire, A.; Delyfer, M.N.; Korobelnik, J.F.; Rougier, M.B.; Le Goff, M.; Dartigues, J.F.; Barberger-Gateau, P.; Delcourt, C. Elevated high-density lipoprotein cholesterol and age-related macular degeneration: The Alienor study. PLoS ONE 2014, 9, e90973. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  56. Foo, V.H.X.; Yanagi, Y.; Nguyen, Q.D.; Sabanayagam, C.; Lim, S.H.; Neelam, K.; Wang, J.J.; Mitchell, P.; Cheng, C.Y.; Wong, T.Y.; et al. Six-Year Incidence and Risk Factors of Age-Related Macular Degeneration in Singaporean Indians: The Singapore Indian Eye Study. Sci. Rep. 2018, 8, 8868. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  57. Wang, J.J.; Foran, S.; Smith, W.; Mitchell, P. Risk of age-related macular degeneration in eyes with macular drusen or hyperpigmentation: The Blue Mountains Eye Study cohort. Arch Ophthalmol. 2003, 121, 658–663. [Google Scholar] [CrossRef] [Green Version]
  58. Aoki, A.; Tan, X.; Yamagishi, R.; Shinkai, S.; Obata, R.; Miyaji, T.; Yamaguchi, T.; Numaga, J.; Ito, H.; Yanagi, Y. Risk Factors for Age-Related Macular Degeneration in an Elderly Japanese Population: The Hatoyama Study. Investig. Ophthalmol. Vis. Sci. 2015, 56, 2580–2585. [Google Scholar] [CrossRef] [PubMed]
  59. Hallak, J.A.; de Sisternes, L.; Osborne, A.; Yaspan, B.; Rubin, D.L.; Leng, T. Imaging, Genetic, and Demographic Factors Associated With Conversion to Neovascular Age-Related Macular Degeneration: Secondary Analysis of a Randomized Clinical Trial. JAMA Ophthalmol. 2019, 137, 738–744. [Google Scholar] [CrossRef] [PubMed]
  60. Hammond, B.R., Jr.; Wooten, B.R.; Snodderly, D.M. Cigarette smoking and retinal carotenoids: Implications for age-related macular degeneration. Vision Res. 1996, 36, 3003–3009. [Google Scholar] [CrossRef] [Green Version]
  61. Abalain, J.H.; Carre, J.L.; Leglise, D.; Robinet, A.; Legall, F.; Meskar, A.; Floch, H.H.; Colin, J. Is age-related macular degeneration associated with serum lipoprotein and lipoparticle levels? Clin. Chim. Acta 2002, 326, 97–104. [Google Scholar] [CrossRef]
  62. Tomany, S.C.; Wang, J.J.; Van Leeuwen, R.; Klein, R.; Mitchell, P.; Vingerling, J.R.; Klein, B.E.; Smith, W.; De Jong, P.T. Risk factors for incident age-related macular degeneration: Pooled findings from 3 continents. Ophthalmology 2004, 111, 1280–1287. [Google Scholar] [CrossRef]
  63. Yan, Q. Genome-wide analysis of disease progression in age-related macular degeneration. Hum. Mol. Genet. 2018, 27, 929–940. [Google Scholar] [CrossRef] [Green Version]
  64. van Grinsven, M.J.; Lechanteur, Y.T.; van de Ven, J.P.; van Ginneken, B.; Hoyng, C.B.; Theelen, T.; Sánchez, C.I. Automatic drusen quantification and risk assessment of age-related macular degeneration on colour fundus images. Investig. Ophthalmol. Vis. Sci. 2013, 54, 3019–3027. [Google Scholar] [CrossRef] [Green Version]
  65. Van Grinsven, M.J.; Buitendijk, G.H.; Brussee, C.; van Ginneken, B.; Hoyng, C.B.; Theelen, T.; Klaver, C.C.W. Automatic identification of reticular pseudodrusen using multimodal retinal image analysis. Investig. Ophthalmol. Vis. Sci. 2015, 56, 633–639. [Google Scholar] [CrossRef] [PubMed]
  66. Liefers, B.; Taylor, P.; Alsaedi, A.; Bailey, C.; Balaskas, K.; Dhingra, N.; Egan, C.A.; Rodrigues, F.G.; Gonzalo, C.G.; Heeren, T.F.; et al. Quantification of key retinal features in early and late age-related macular degeneration using deep learning. Am. J. Ophthalmol. 2021, 226, 1–12. [Google Scholar] [CrossRef] [PubMed]
  67. Schmidt-Erfurth, U.; Bogunovic, H.; Sadeghipour, A.; Clare, B.; Konstantinos, B.; Narendra, D.; Osborne, A.; Waldstein, S.M. Machine learning to analyze the prognostic value of current imaging biomarkers in neovascular age-related macular degeneration. Ophthalmol. Retin. 2018, 2, 24–30. [Google Scholar] [CrossRef] [PubMed]
  68. Schmidt-Erfurth, U.; Vogl, W.D.; Jampol, L.M.; Bogunović, H. Application of automated quantification of fluid volumes to anti–VEGF therapy of neovascular age-related macular degeneration. Ophthalmology 2020, 127, 1211–1219. [Google Scholar] [CrossRef]
  69. Keenan, T.D.L.; Chakravarthy, U.; Loewenstein, A.; Chew, E.Y.; Schmidt-Erfurth, U. Automated quantitative assessment of retinal fluid volumes as important biomarkers in neovascular age-related macular degeneration. Am. J. Ophthalmol. 2021, 224, 267–281. [Google Scholar] [CrossRef]
  70. Lee, H.; Kang, K.E.; Chung, H.; Kim, H.C. Automated segmentation of lesions, including subretinal hyperreflective material in neovascular age-related macular degeneration. Am. J. Ophthalmol. 2018, 191, 64–75. [Google Scholar] [CrossRef]
  71. Yim, J.; Chopra, R.; Spitz, T.; Winkens, J.; Obika, A.; Kelly, C.; Askham, H.; Lukic, M.; Huemer, J.; Fasler, K.; et al. Predicting conversion to wet age-related macular degeneration using deep learning. Nat. Med. 2020, 26, 892–899. [Google Scholar] [CrossRef]
  72. Yan, Q.; Weeks, D.E.; Xin, H.; Swaroop, A.; Chew, E.Y.; Huang, H.; Ding, Y.; Chen, W. Deep-learning-based prediction of late age-related macular degeneration progression. Nat. Mach. Intell. 2020, 2, 141–150. [Google Scholar] [CrossRef]
  73. Peng, Y.; Keenan, T.D.; Chen, Q.; Agrón, E.; Allot, A.; Wong, W.T.; Chew, E.Y.; Lu, Z. Predicting risk of late age-related macular degeneration using deep learning. NPJ Digit. Med. 2020, 3, 111. [Google Scholar] [CrossRef]
  74. Ajana, S.; Cougnard-Grégoire, A.; Colijn, J.M.; Merle, B.M.; Verzijden, T.; de Jong, P.T.; Hofman, A.; Vingerling, J.R.; Hejblum, B.P.; Korobelnik, J.-F.; et al. Predicting progression to advanced age-related macular degeneration from clinical, genetic and lifestyle factors using machine learning. Ophthalmology 2020, 128, 587–597. [Google Scholar] [CrossRef]
  75. Ikram, M.A.; Brusselle, G.G.; Murad, S.D.; van Duijn, C.M.; Franco, O.H.; Goedegebure; Klaver, C.C.W.; Nijsten, T.E.C.; Peeters, R.P.; Stricker, B.H.; et al. The Rotterdam Study: 2018 update on objectives, design and main results. Eur. J. Epidemiol. 2017, 32, 807–850. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  76. Delcourt, C.; Korobelnik, J.F.; Barberger-Gateau, P.; Delyfer, M.N.; Rougier, M.B.; Le Goff, M.; Malet, F.; Colin, J.; Dartigues, J.F. Nutrition and Age-Related Eye Dis- eases: The ALIENOR (Antioxydants, Lipides Essentiels, Nutrition et Maladies Oculaires) Study. J. Nutr. Health Aging 2010, 14, 854–861. [Google Scholar] [CrossRef] [PubMed]
  77. Seddon, J.M.; Reynolds, R.; Maller, J.; Fagerness, J.A.; Daly, M.J.; Rosner, B. Prediction model for prevalence and incidence of advanced age-related macular degeneration based on genetic, demographic, and environmental variables. Investig. Ophthalmol. Vis. Sci. 2008, 50, 2044–2053. [Google Scholar] [CrossRef] [PubMed]
  78. D’Agostino, R.B.; Grundy, S.; Sullivan, L.M.; Wilson, P.; CHD Risk Prediction Group. Validation of the Framingham coronary heart disease prediction scores: Results of a multiple ethnic groups investigation. JAMA 2001, 286, 180–187. [Google Scholar] [CrossRef] [Green Version]
  79. Seddon, J.M.; Reynolds, R.; Yu, Y.; Daly, M.J.; Rosner, B. Risk models for progression to advanced age-related macular degeneration using demographic, environmental, genetic, and ocular factors. Ophthalmology 2011, 118, 2203–2211. [Google Scholar] [CrossRef] [Green Version]
  80. Klein, M.L.; Francis, P.J.; Ferris, F.L.; Hamon, S.C.; Clemons, T.E. Risk assessment model for the development of advanced age-related macular degeneration. Arch. Ophthalmol. 2011, 129, 1543–1550. [Google Scholar] [CrossRef]
  81. Seddon, J.M.; Silver, R.E.; Kwong, M.; Rosner, B. Risk Prediction for Progression of Macular Degeneration: 10 Common and Rare Genetic Variants, Demographic, Environmental, and Macular Covariates. Investig. Ophthalmol. Vis. Sci. 2015, 56, 2192–2202. [Google Scholar] [CrossRef]
  82. Spencer, K.L.; Olson, L.M.; Schnetz-Boutaud, N.; Gallins, P.; Agarwal, A.; Iannaccone, A.; Kritchevsky, S.B.; Garcia, M.; Nalls, M.A.; Newman, A.B.; et al. Using genetic variation and environmental risk factor data to identify individuals at high risk for age-related macular degeneration. PLoS ONE 2011, 6, e17784. [Google Scholar] [CrossRef] [Green Version]
  83. Fraccaro, P.; Nicolo, M.; Bonetto, M.; Giacomini, M.; Weller, P.; Traverso, C.E.; Prosperi, M. Combining macula clinical signs and patient characteristics for age-related macular degeneration diagnosis: A machine learning approach. BMC Ophthalmol. 2015, 15, 10. [Google Scholar] [CrossRef] [Green Version]
  84. Shin, K.U.; Song, S.J.; Bae, J.H.; Lee, M.Y. Risk Prediction Model for Progression of Age-Related Macular Degeneration. Ophthalmic. Res. 2017, 57, 32–36. [Google Scholar] [CrossRef]
  85. Verlato, G.; Marrelli, D.; Accordini, S.; Bencivenga, M.; Di Leo, A.; Marchet, A.; Petrioli, R.; Zoppini, G.; Muggeo, M.; Roviello, F.; et al. Short-term and long-term risk factors in gastric cancer. World J. Gastroenterol. 2015, 21, 6434–6443. [Google Scholar] [CrossRef] [PubMed]
  86. Verlato, G.; Giacopuzzi, S.; Bencivenga, M.; Morgagni, P.; De Manzoni, G. Problems faced by evidence-based medicine in evaluating lymphadenectomy for gastric cancer. World J. Gastroenterol. 2014, 20, 12883–12891. [Google Scholar] [CrossRef]
  87. Fabris, A.; Bruschi, M.; Santucci, L.; Candiano, G.; Granata, S.; Dalla Gassa, A.; Antonucci, N.; Petretto, A.; Ghiggeri, G.M.; Gambaro, G.; et al. Proteomic-based research strategy identified laminin subunit alpha 2 as a potential urinary-specific biomarker for the medullary sponge kidney disease. Kidney Int. 2017, 91, 459–468. [Google Scholar] [CrossRef] [PubMed]
  88. De Manzoni, G.; Marrelli, D.; Verlato, G.; Morgagni, P.; Roviello, F. Western perspective and epidemiology of gastric cancer. In Gastric Cancer: Principles and Practice; Springer International Publishing: Cham, Switzerland, 2015; pp. 111–123. ISBN 9783319158266. [Google Scholar]
  89. Bencivenga, M.; Verlato, G.; Mengardo, V.; Scorsone, L.; Sacco, M.; Torroni, L.; Giacopuzzi, S.; de Manzoni, G. Is There Any Role for Super-Extended Limphadenectomy in Advanced Gastric Cancer? Results of an Observational Study from a Western High Volume Center. J. Clin. Med. 2019, 8, 1799. [Google Scholar] [CrossRef]
  90. Ngiam, K.Y.; Khor, I.W. Big data and machine learning algorithms for healthcare delivery. Lancet Oncol. 2019, 20, e262–e273. [Google Scholar] [CrossRef] [PubMed]
  91. Saha, S.; Nassisi, M.; Wang, M.; Lindenberg, S.; Sadda, S.; Hu, Z.J. Automated detection and classification of early AMD biomarkers using deep learning. Sci. Rep. 2019, 9, 10990. [Google Scholar] [CrossRef] [Green Version]
  92. Gulshan, V.; Peng, L.; Coram, M.; Stumpe, M.C.; Wu, D.; Narayanaswamy, A.; Venugopalan, S.; Widner, K.; Madams, T.; Cuadros, J.; et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016, 316, 2402–2410. [Google Scholar] [CrossRef]
  93. Abràmoff, M.D.; Lou, Y.; Erginay, A.; Clarida, W.; Amelon, R.; Folk, J.C.; Niemeijer, M. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Investig. Ophthalmol. Vis. Sci. 2016, 57, 5200–5206. [Google Scholar] [CrossRef] [Green Version]
  94. Garcia, R.; Leng, T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology 2017, 124, 962–969. [Google Scholar] [CrossRef]
  95. Ting, D.S.W.; Cheung, C.Y.L.; Lim, G.; Tan, G.S.W.; Quang, N.D.; Gan, A.; Hamzah, H.; Garcia-Franco, R.; Yeo, I.Y.S.; Lee, S.Y.; et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 2017, 318, 2211–2223. [Google Scholar] [CrossRef]
  96. Ramanishka, V.; Das, A.; Zhang, J. Top-down visual saliency guided by captions. arXiv 2016, arXiv:1612.07360. [Google Scholar]
  97. Jenkins, A.J.; Joglekar, M.V.; Hardikar, A.A.; Keech, A.C.; O’Neal, D.N.; Januszewski, A.S. Biomarkers in diabetic retinopathy. Rev. Diabet. Stud. RDS 2015, 12, 159. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  98. Bianchetti, G.; Viti, L.; Scupola, A.; Di Leo, M.; Tartaglione, L.; Flex, A.; De Spirito, M.; Pitocco, D.; Maulucci, G. Erythrocyte membrane fluidity as a marker of diabetic retinopathy in type 1 diabetes mellitus. Eur. J. Clin. Investig. 2021, 51, e13455. [Google Scholar] [CrossRef]
  99. Bianchetti, G.; Ciccarone, F.; Ciriolo, M.R.; De Spirito, M.; Pani, G.; Maulucci, G. Label-free metabolic clustering through unsupervised pixel classification of multiparametric fluorescent images. Anal. Chim. Acta 2021, 1148, 238173. [Google Scholar] [CrossRef]
  100. Loo, J.; Kriegel, M.F.; Tuohy, M.M.; Kim, K.H.; Prajna, V.; Woodward, M.A.; Farsiu, S. Open-source automatic segmentation of ocular structures and biomarkers of microbial keratitis on slit-lamp photography images using deep learning. IEEE J. Biomed. Health Inform. 2020, 25, 88–99. [Google Scholar] [CrossRef]
Diagnostics 13 00130 g001 550
Figure 1. Flow diagram describing study selection.
Figure 1. Flow diagram describing study selection.
Diagnostics 13 00130 g001
Diagnostics 13 00130 g002 550
Figure 2. Year-wise classification of included articles.
Figure 2. Year-wise classification of included articles.
Diagnostics 13 00130 g002
Diagnostics 13 00130 g003 550
Figure 3. Application of statistical methods concerning the perspective of a clinician.
Figure 3. Application of statistical methods concerning the perspective of a clinician.
Diagnostics 13 00130 g003
Diagnostics 13 00130 g004 550
Figure 4. The classification by percentage of techniques used in included articles.
Figure 4. The classification by percentage of techniques used in included articles.
Diagnostics 13 00130 g004
Diagnostics 13 00130 g005 550
Figure 5. Applications of artificial intelligence from the perspective of a clinician.
Figure 5. Applications of artificial intelligence from the perspective of a clinician.
Diagnostics 13 00130 g005
Table
Table 1. The summarized review of statistical techniques for AMD.
Table 1. The summarized review of statistical techniques for AMD.
TechniqueSourceStudy TypeCountrySex (%male)Age Range
(Years)		AMD TypeClassification CriteriaAdjustmentRisk Factors
Identified
Poisson Regression Analysis Holz et al. [29]ProspectiveLondon46.8Older than 50 years of ageAMDStandardized grading schemeAge, sex
and smoking		Focal hyperpigmentation, slow choroidal filling
and degree of confluence of drusen
Unconditional logistic analysis Tamakoshi et al. [30] Case-controlJapan100Aged 50 to 69 yearsNeovascular AMDNRAge, sexCigarette smoking
Univariate and
multivariate analyses		Klein et al. [31] Population-basedUnited StatesNR43–86 years of age ARMWARMGSAge and gender(No strong relation between cardiovascular disease and most of its risk factors with the incidence of lesions associated with age-related maculopathy)
Buch et al. [32]Population-based
cohort		Denmark36.2Between 60 and 80 yearsARMModification of WARMGSAge and genderAge, cataract, family history,
alcohol consumption,
the apolipoproteins A1 and B
Women’s Health Initiative Sight
Exam ancillary study [33]		AncillaryUnited States063 years and older.Late AMDWARMGSAgeSmoking, use of calcium
channel blockers, diabetes, and obesity
Logistic Regression Chaine et al. [34]Case-controlFrance3150–85 yearsAMDNRNRArterial hypertension, coronary disease,
hyperopia, light-coloured irises,
lens opacities and previous cataract surgery
POLA study [35]ProspectiveFrance43.860 years or overAMDInternational classification *Age and gender(No significant association of late AMD with a history of cardiovascular disease, diabetes, and hypertension)
Vine et al. [36]Case-controlUnited States41.8≥65
Year old		AMDNRAge, CRP,
and homocysteine level		CRP
and homocysteine level
AREDS study [37]Clinic-based
prospective cohort		NRNR55 to 80 years Neovascular AMDNRAge, gender, and
AREDS treatment		Smoking, race, and BMI
Fraser-Bell et al. [38]Population-based,
cross-sectional		United States4240 years oldEarly and
advanced AMD		Modified WARMGSAge, sex and
smoking status 		Smoking and heavy alcohol consumption
Gemmy et al. [39] Population-based, cross-sectional Singapore and India50.2 (Singapore) &
47.3 (India)		40–83 yearsEarly AMDInternational classification of
the Wisconsin age-related maculopathy 		Age, BMI, sex, cholesterol, myocardial infarction, hypertension, central corneal thickness
axial length, and
IOP. 		Shorter axial length
higher BMI, previous cataract surgery,
lower cholesterol and hypertension.
Yip et al. [40]Prospective cohortUnited Kingdom43.144–91 yearsAMDModified Wisconsin protocol *Sex, education, smoking,
and SBP. 		Older age,
baseline CRP, and a higher baseline
and follow-up levels of HDL.
Raman et al. [41]Population-based cross-sectionalIndiaNR≥60 yearsEarly and
late AMD		International ARM
epidemiological
study group		Age and genderAge per year increase,
middle socioeconomic status,
and smokeless tobacco
Myra et al. [42]ObservationalAustralia4047–85 yearsLate AMDNRSex, age at fundus photography,
index of relative socioeconomic
disadvantage,
and the Mediterranean diet score 		Current smokers
Connolly et al. [43]CohortIreland44≥50 yearsAMD A modified version of the
international classification
and grading system for AMD		Age, sex, education
and CFH		Older age, the presence of ARMS2 and CFH
risk alleles
Butt et al. [44] Cross-sectional United StatesNR45 to 74 years Early and
late AMD 		University of Wisconsin
ocular
epidemiology reading center		NRAge and
HDL cholesterol
Polychotomous logistic
regression analyses		Hyman et al. [45]Case-control United States40Between the age
of 50 and 79 years		Neovascular AMDIndependent graders at the reading centerAge, sex,
and energy intake. 		Moderate to severe hypertension
AREDS study [46]Case-control United States44.2Aged 60 to 80 yearsAMD The Wisconsin age-related
maculopathy grading system #		Age and genderSmoking, hypertension,
lens opacities, hyperopia,
female gender, less education, white race, and increased BMI
Multivariable logistic
regression models		Klein et al. [47] CohortUnited States45.6Aged 21 to 84 yearsAMD WARMGSAge and sexSmoking and
serum HDL cholesterol
Shim et al. [48]Prospective cohortSouth Korea60.5Older than 50 yearsEarly AMD
progression		International age-related maculopathy (ARM)
epidemiological study group and WARMGS		Age,
alcohol consumption, smoking status,
BMI, BP, HDL cholesterol, and total cholesterol		An increasing number of drusen,
central drusen location, hypertension,
and current smoking.
Erke et al. [49] Population-based,
cross-sectional		Norway4365–87 years AMD and
late AMD		International classification system *Age, sex, smoking
and SBP		Smoking, higher SBP,
physical inactivity,
overweight and obesity in women
Standard Bivariate and
Multivariate Analyses		Krishnaiah et al. [50]Population-based,
cross-sectional		India47Aged 40 to 102 yearsAMDInternational classification
and grading system		Age, area
and gender 		Ageing, smoking, prior cataract surgery, and presence of cortical cataract.
Multivariate stepwise
logistic regression		Choudhury et al. [51] Population-based
prospective cohort		United States39.1Aged 40 or olderAny AMD and
progression of AMD		Modified WARMGSAgeOlder age, current smoking
and higher pulse pressure
Jonasson et al. [52]Population-based
prospective cohort		Iceland42.4Aged 67 years and older AMDModification of WARMGSAge and sexAge, smoking,
plasma HDL cholesterol,
BMI and female sex
Saunier et al. [53]Population-based
cohort		France37.373 years or older Early to
advanced AMD		International classification *
and to a modification of the grading scheme
used in the multi-ethnic study of atherosclerosis @		Age and sexFellow eye, smoking,
plasma HDL cholesterol concentration,
and CFH Y402H genotype
Multivariate Cox
regression survival analysis		Lechanteur et al. [54]RetrospectiveNetherlands34.354.3–93.4 years.End-stage AMDNRAge, education, sex,
baseline AMD grade, smoking,
BMI,
six genetic variants and associated genotypes, and treatment groups		Sex, smoking status, age,
to a lesser extent BMI,
CFI (rs10033900) and LPL (rs12678919)
Generalized estimating
equation logistic regressions		Cougnard et al. [55]Population-based France38.165 years and olderEarly and
any AMD		International classification *@Age, educational level, sex,
BMI, smoking, lipid-lowering medication use for all relevant genetic polymorphisms, cardiovascular disease and diabetes,		HDL,
TC, LDL,
higher HDL,
and TG
Foo et al. [56]Population-based
cohort		Singapore49.7NREarly AMD WARMGSAge, gender, hypertension, total cholesterol,
cardiovascular disease, BMI categories,
smoking status, alcohol consumption frequency,
serum CRP
and ARMS2 genetic loci.
Heavy alcohol drinking, underweight BMI, ARMS2 rs3750847 homozygous genetic loci carrier, and cardiovascular disease history.
Wang et al. [57]Population-based
cohort		Australia39.249 years or older AMDWARMGSAge, sex, smoking status
and the correlation between eyes		Eyes with indistinct soft drusen, large drusen, hyperpigmentation or
a large area of the macula
covered by drusen.
Logistic regression analyses
and Mantel-Haenszel analysis		Aoki et al. [58]Cross-sectional Japan6065–74 years and 75–84 yearsAMDSimplified severity scale for AMD
from the AREDS		AgeCFH I62V and
ARMS2 A69S variant
Survival analysis and
Cox proportional hazards regression		Hallak et al. [59]Retrospective,
post hoc
secondary analysis		United States40.850 years or olderNeovascular AMDNRNRMean drusen
reflectivity, the total en-face area of the drusen
restricted to a circular area of 3 mm
from the fovea and one genetic variant (rs61941274)
OthersHammond et al. [60]Case-control United States47NRNeovascular AMD NRNRSmokers
Alain et al. [61]Case-control France22.6Mean age 77 yearsAMDWARMGSNRPerturbations of HDL metabolism
Tomany et al. [62]Population-based
cohort 		Australia,
Netherlands,
and the United States		4343–95 yearsAMDWisconsin and international
age-related maculopathy grading systems		Age, gender (when appropriate),
data source, and follow-up time		Smoking
AMD, age-related macular degeneration; ARM, age-related maculopathy; WARMGS, the Wiscon-sin age-related maculopathy grading system; CRP, C-reactive protein; BMI, body mass index; POLA, Pathologies Oculaires Liées à I’Age; AREDS, Age-Related Eye Disease Study; IOP, intraocular pressure; SBP, systolic blood pressure; HDL, high-density lipoprotein; CFH, complement factor H; ARMS2, age-related maculopathy susceptibility 2; BP, blood pressure; SBP, systolic blood pressure; LPL, lipoprotein lipase; CFI, complement factor I; LDL, low-density lipoprotein; TC, total cholesterol; TG, triglycerides. *: Bird AC, Bressler NM, Bressler SB, Chisholm IH, Coscas G, Davis MD, et al. An international classification and grading system for age-related maculopathy and age-related macular degeneration. The international ARM epidemiological study group. Surv Ophthalmol. 1995;39:367–74. #: Klein R, Davis MD, Magli YL, et al. The Wisconsin age-related maculopathy grading system. Ophthalmology 1991;98:1128–34. @: Klein R, Klein BE, Knudtson MD, et al. Prevalence of age-related macular degeneration in 4 racial/ethnic groups in the Multi-Ethnic Study of Atherosclerosis. Ophthalmology. 2006;113(3): 373–380.
Table
Table 2. The summarized review of AI techniques for AMD.
Table 2. The summarized review of AI techniques for AMD.
SourceTechniqueDatasetMetricsDisease
Grinsven et al. [64]Supervised machine learning algorithmA total of 407 images of different eyes with nonadvanced stages of AMD (i.e., stages 1, 2, and 3 according to the criteria shown in Table 1), with sufficient grading quality for human graders, were selected consecutively from the European genetic database (EUGENDA), a large multicenter database for clinical and molecular analysis of AMD.AUROC values of 0.948 and 0.954AMD risk assessment
Grinsven et al. [65]Machine learning algorithmA set of subjects with and without RPD were selected from the Rotterdam Study. A prospective cohort study aimed to investigate risk factors for chronic diseases in the elderly.AUROC value of 0.941Reticular pseudo drusen (RPD) detection
Liefers et al. [66]Deep learning modelThis study’s imaging data (OCT B scans) were obtained from 30,337 patients at five centres in the UK (NRES Committee London, City Road and Hampstead, London).On 11 of 13 features, the model obtained a mean Dice score of 0.63 ± 0.15, compared with 0.61 ± 0.17 for the observers. ICC was 0.66 ± 0.22, compared with 0.62 ± 0.21 for the observers Feature segmentation associated with neovascular and atrophic AMD
Schmidt-Erfuth et al. [67]Random forest regression algorithmData (spectral-domain (SD) OCT volume scans) of 614 evaluable patients receiving intravitreal ranibizumab monthly or pro re nata according to protocol-specified criteria in the HARBOR trial were studied.At baseline, OCT features and BCVA were correlated with R2 = 0.21.Predict best-corrected visual acuity (BCVA) outcomes
Schmidt-Erfuth et al. [68]Deep learning method (convolutional neural network (CNN))SD-OCT scans of 1095 patients enrolled in the HARBOR trialNRMeasure fluid response to anti-vascular endothelial growth factor (VEGF) treatment in neovascular AMD
Keenan et al. [69]Artificial Intelligence AlgorithmsData from (a) the HARBOR trial, (b) a tertiary referral retinal centre in the United Kingdom, (c) a tertiary referral retinal centre in Israel, and (d) the AREDS2 10-year follow-up. were studied,Large ranges that differed by population were observed at the treatment-naive stage: 0–3435 nL (IRF), 0–5018 nL (SRF), and 0–10,022 nL (PED).Validation of retinal fluid volumes (IRF, SRF and PED)
Lee et al. [70] Automated segmentation algorithm with a CNNA dataset including 930 B-scans from 93 eyes of 93 patients with nAMD.Dice coefficients for segmentation of IRF, SRF, SHRM, and PED were 0.78, 0.82, 0.75, and 0.80To quantify and detect intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM) with nAMD
Yim et al. [71]Artificial intelligence systemA cohort of 2,795 patients (OCT scans) across seven different sites who were first diagnosed with nAMD between June 2012 and June 2017Sensitivity of 80% at 55% specificity and 34% specificity at 90% sensitivityProgression to exudative wet AMD
Yan et al. [72]Modified deep
convolutional neural network		The data consisted of 52 AMD-associated genetic variants and 31,262 fundus images from 1,351 subjects from the age-related eye disease study (AREDS) fundus images coupled with genotypes.AUC value of 0.85AMD progression
Peng et al. [73]Deep learning (DL)
and survival analysis		AREDS and AREDS25-year C-statistic 86.4Late AMD
Ajana et al. [74]Prediction model used
bootstrap lasso for survival analysis		The training data set included Rotterdam study I (RS-I) enrolled participants.AUC estimation in RS-I
was 0.92 at five years,
0.92 at ten years and 0.91 at 15 years		Advanced AMD
Seddon et al. [77]Predictive modelThe data was from 1446 individuals who
participated in the multicenter AREDS, of which 279 progressed to advanced AMD and 1167 did not progress during 6.3 years of follow-up		C statistic score of 0.83Prevalence and
incidence of AMD
Seddon et al. [79] Model of AMD progressionData consisted of 2937 individuals in the
AREDS		AUC 0.915 in the total sampleAMD Progression
Klein et al. [80] Risk assessment model Longitudinal data from 2846 participants
in the AREDS		C statistic = 0.872.
Brier score at 5 years = 0.08		Advanced AMD
Seddon et al. [81]Predictive model
and online application		Data from the AREDS for Caucasian participants were used for this analysisAUC- 91.1Progression to
advanced AMD
Spencer et al. [82]Logistic regression and
grammatical evolution of
neural networks (GENN) models		A VM family dataset, the population-based age-related maculopathy ancillary (ARMA) study cohort, and Vanderbilt-Miami (VM) clinic-based case-control dataset. Sensitivity of 77.0%
and specificity of 74.1%		High- and low-risk
groups for AMD
Fraccaro et al. [83]Random forests,
AdaBoost and SVM, as well as white-box methods, including decision trees and logistic regression		Data on healthy subjects, study participants, and patients with macular diseases were collected from March 2013 to January 2014 during routine clinical practice at the Medical Retina Center of the University Eye Clinic of Genoa (Italy).Logistic Regression, AdaBoost, and random forests achieved a mean AUC of 0.92, followed by decision trees and SVM with a mean AUC of 0.90.Diagnose AMD
Shin et al. [84] Risk prediction modelThe study sample included 50 years of age or older individuals counting 10,890; 318 (2.92%) presented with early AMD findings in baseline examinations.C statistic-0.84Progression of AMD
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Vyas, A.; Raman, S.; Surya, J.; Sen, S.; Raman, R. The Need for Artificial Intelligence Based Risk Factor Analysis for Age-Related Macular Degeneration: A Review. Diagnostics 2023, 13, 130. https://doi.org/10.3390/diagnostics13010130

AMA Style

Vyas A, Raman S, Surya J, Sen S, Raman R. The Need for Artificial Intelligence Based Risk Factor Analysis for Age-Related Macular Degeneration: A Review. Diagnostics. 2023; 13(1):130. https://doi.org/10.3390/diagnostics13010130

Chicago/Turabian Style

Vyas, Abhishek, Sundaresan Raman, Janani Surya, Sagnik Sen, and Rajiv Raman. 2023. "The Need for Artificial Intelligence Based Risk Factor Analysis for Age-Related Macular Degeneration: A Review" Diagnostics 13, no. 1: 130. https://doi.org/10.3390/diagnostics13010130

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop