Detection of Longitudinal Visual Field Progression in Glaucoma Using Machine Learning

Identifying Factors Associated With Fast Visual Field Progression in Patients With Ocular Hypertension Based on Unsupervised Machine Learning

PRCIS

We developed unsupervised machine learning models to identify different subtypes of patients with ocular hypertension in terms of visual field (VF) progression and discovered 4 subtypes with different trends of VF worsening. We then identified factors associated with fast VF progression.

PURPOSE

To identify ocular hypertension (OHT) subtypes with different trends of visual field (VF) progression based on unsupervised machine learning and to discover factors associated with fast VF progression.

DESIGN

Cross-sectional and longitudinal study.

PARTICIPANTS

A total of 3133 eyes of 1568 ocular hypertension treatment study (OHTS) participants with at least 5 follow-up VF tests were included in the study.

METHODS

We used a latent class mixed model (LCMM) to identify OHT subtypes using standard automated perimetry (SAP) mean deviation (MD) trajectories. We characterized the subtypes based on demographic, clinical, ocular, and VF factors at the baseline. We then identified factors driving fast VF progression using generalized estimating equation (GEE) and justified findings qualitatively and quantitatively.

MAIN OUTCOME MEASURE

Rates of SAP mean deviation (MD) change.

RESULTS

The LCMM model discovered four clusters (subtypes) of eyes with different trajectories of MD worsening. The number of eyes in clusters were 794 (25%), 1675 (54%), 531 (17%), and 133 (4%). We labeled the clusters as improvers (cluster 1), stables (cluster 2), slow progressors (cluster 3), and fast progressors (cluster 4) based on their mean of MD decline rate, which were 0.08, -0.06, -0.21, and -0.45 dB/year, respectively. Eyes with fast VF progression had higher baseline age, intraocular pressure (IOP), pattern standard deviation (PSD) and refractive error (RE), but lower central corneal thickness (CCT). Fast progression was associated with being male, heart disease history, diabetes history, African American race, and stroke history.

CONCLUSIONS

Unsupervised clustering can objectively identify OHT subtypes including those with fast VF worsening without human expert intervention. Fast VF progression was associated with higher history of stroke, heart disease and diabetes. Fast progressors were more from African American race, males, and had higher incidence of glaucoma conversion. Subtyping can provide guidance for adjusting treatment plans to slow vision loss and improve quality of life of patients with a faster progression course.

The use of artificial neural networks in studying the progression of glaucoma

In ophthalmology, artificial intelligence methods show great promise due to their potential to enhance clinical observations with predictive capabilities and support physicians in diagnosing and treating patients. This paper focuses on modelling glaucoma evolution because it requires early diagnosis, individualized treatment, and lifelong monitoring. Glaucoma is a chronic, progressive, irreversible, multifactorial optic neuropathy that primarily affects elderly individuals. It is important to emphasize that the processed data are taken from medical records, unlike other studies in the literature that rely on image acquisition and processing. Although more challenging to handle, this approach has the advantage of including a wide range of parameters in large numbers, which can highlight their potential influence. Artificial neural networks are used to study glaucoma progression, designed through successive trials for near-optimal configurations using the NeuroSolutions and PyTorch frameworks. Furthermore, different problems are formulated to demonstrate the influence of various structural and functional parameters on the study of glaucoma progression. Optimal neural networks were obtained using a program written in Python using the PyTorch deep learning framework. For various tasks, very small errors in training and validation, under 5%, were obtained. It has been demonstrated that very good results can be achieved, making them credible and useful for medical practice.

Application of artificial intelligence in glaucoma care: An updated review

The application of artificial intelligence (AI) in ophthalmology has been increasingly explored in the past decade. Numerous studies have shown promising results supporting the utility of AI to improve the management of ophthalmic diseases, and glaucoma is of no exception. Glaucoma is an irreversible vision condition with insidious onset, complex pathophysiology, and chronic treatment. Since there remain various challenges in the clinical management of glaucoma, the potential role of AI in facilitating glaucoma care has garnered significant attention. In this study, we reviewed the relevant literature published in recent years that investigated the application of AI in glaucoma management. The main aspects of AI applications that will be discussed include glaucoma risk prediction, glaucoma detection and diagnosis, visual field estimation and pattern analysis, glaucoma progression detection, and other applications.

Integrating Deep Learning with Electronic Health Records for Early Glaucoma Detection: A Multi-Dimensional Machine Learning Approach

BACKGROUND

Recent advancements in deep learning have significantly impacted ophthalmology, especially in glaucoma, a leading cause of irreversible blindness worldwide. In this study, we developed a reliable predictive model for glaucoma detection using deep learning models based on clinical data, social and behavior risk factor, and demographic data from 1652 participants, split evenly between 826 control subjects and 826 glaucoma patients.

METHODS

We extracted structural data from control and glaucoma patients' electronic health records (EHR). Three distinct machine learning classifiers, the Random Forest and Gradient Boosting algorithms, as well as the Sequential model from the Keras library of TensorFlow, were employed to conduct predictive analyses across our dataset. Key performance metrics such as accuracy, F1 score, precision, recall, and the area under the receiver operating characteristics curve (AUC) were computed to both train and optimize these models.

RESULTS

The Random Forest model achieved an accuracy of 67.5%, with a ROC AUC of 0.67, outperforming the Gradient Boosting and Sequential models, which registered accuracies of 66.3% and 64.5%, respectively. Our results highlighted key predictive factors such as intraocular pressure, family history, and body mass index, substantiating their roles in glaucoma risk assessment.

CONCLUSIONS

This study demonstrates the potential of utilizing readily available clinical, lifestyle, and demographic data from EHRs for glaucoma detection through deep learning models. While our model, using EHR data alone, has a lower accuracy compared to those incorporating imaging data, it still offers a promising avenue for early glaucoma risk assessment in primary care settings. The observed disparities in model performance and feature significance show the importance of tailoring detection strategies to individual patient characteristics, potentially leading to more effective and personalized glaucoma screening and intervention.

Prediction of Visual Field Progression with Baseline and Longitudinal Structural Measurements Using Deep Learning

PURPOSE

Identifying glaucoma patients at high risk of progression based on widely available structural data is an unmet task in clinical practice. We test the hypothesis that baseline or serial structural measures can predict visual field (VF) progression with deep learning (DL).

DESIGN

Development of a DL algorithm to predict VF progression.

METHODS

3,079 eyes (1,765 patients) with various types of glaucoma and ≥5 VFs, and ≥3 years of follow-up from a tertiary academic center were included. Serial VF mean deviation (MD) rates of change were estimated with linear-regression. VF progression was defined as negative MD slope with p<0.05. A Siamese Neural Network with ResNet-152 backbone pre-trained on ImageNet was designed to predict VF progression using serial optic-disc photographs (ODP), and baseline retinal nerve fiber layer (RNFL) thickness. We tested the model on a separate dataset (427 eyes) with RNFL data from different OCT. The Main Outcome Measure was Area under ROC curve (AUC).

RESULTS

Baseline average (SD) MD was 3.4 (4.9)dB. VF progression was detected in 900 eyes (29%). AUC (95% CI) for model incorporating baseline ODP and RNFL thickness was 0.813 (0.757-0.869). After adding the second and third ODPs, AUC increased to 0.860 and 0.894, respectively (p<0.027). This model also had highest AUC (0.911) for predicting fast progression (MD rate <1.0 dB/year). Model's performance was similar when applied to second dataset using RNFL data from another OCT device (AUC=0.893; 0.837-0.948).

CONCLUSIONS

DL model predicted VF progression with clinically relevant accuracy using baseline RNFL thickness and serial ODPs and can be implemented as a clinical tool after further validation.

Efficacy of Smoothing Algorithms to Enhance Detection of Visual Field Progression in Glaucoma

Purpose

To evaluate and compare the effectiveness of nearest neighbor (NN)- and variational autoencoder (VAE)-smoothing algorithms to reduce variability and enhance the performance of glaucoma visual field (VF) progression models.

Design

Longitudinal cohort study.

Subjects

7150 eyes (4232 patients), with ≥ 5 years of follow-up and ≥ 6 visits.

Methods

Vsual field thresholds were smoothed with the NN and VAE algorithms. The mean total deviation (mTD) and VF index rates, pointwise linear regression (PLR), permutation of PLR (PoPLR), and the glaucoma rate index were applied to the unsmoothed and smoothed data.

Main Outcome Measures

The proportion of progressing eyes and the conversion to progression were compared between the smoothed and unsmoothed data. A simulation series of noiseless VFs with various patterns of glaucoma damage was used to evaluate the specificity of the smoothing models.

Results

The mean values of age and follow-up time were 62.8 (standard deviation: 12.6) years and 10.4 (standard deviation: 4.7) years, respectively. The proportion of progression was significantly higher for the NN and VAE smoothed data compared with the unsmoothed data. VF progression occurred significantly earlier with both smoothed data compared with unsmoothed data based on mTD rates, PLR, and PoPLR methods. The ability to detect the progressing eyes was similar for the unsmoothed and smoothed data in the simulation data.

Conclusions

Smoothing VF data with NN and VAE algorithms improves the signal-to-noise ratio for detection of change, results in earlier detection of VF progression, and could help monitor glaucoma progression more effectively in the clinical setting.

Financial Disclosures

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

Artificial intelligence in glaucoma: opportunities, challenges, and future directions

Artificial intelligence (AI) has shown excellent diagnostic performance in detecting various complex problems related to many areas of healthcare including ophthalmology. AI diagnostic systems developed from fundus images have become state-of-the-art tools in diagnosing retinal conditions and glaucoma as well as other ocular diseases. However, designing and implementing AI models using large imaging data is challenging. In this study, we review different machine learning (ML) and deep learning (DL) techniques applied to multiple modalities of retinal data, such as fundus images and visual fields for glaucoma detection, progression assessment, staging and so on. We summarize findings and provide several taxonomies to help the reader understand the evolution of conventional and emerging AI models in glaucoma. We discuss opportunities and challenges facing AI application in glaucoma and highlight some key themes from the existing literature that may help to explore future studies. Our goal in this systematic review is to help readers and researchers to understand critical aspects of AI related to glaucoma as well as determine the necessary steps and requirements for the successful development of AI models in glaucoma.

Identifying, Understanding, and Addressing Disparities in Glaucoma Care in the United States

Glaucoma is the leading cause of irreversible blindness worldwide, currently affecting around 80 million people. Glaucoma prevalence is rapidly rising in the United States due to an aging population. Despite recent advances in the diagnosis and treatment of glaucoma, significant disparities persist in disease detection, management, and outcomes among the diverse patient populations of the United States. Research on disparities is critical to identifying, understanding, and addressing societal and healthcare inequalities. Disparities research is especially important and impactful in the context of irreversible diseases such as glaucoma, where earlier detection and intervention are the primary approach to improving patient outcomes. In this article, we first review recent studies identifying disparities in glaucoma care that affect patient populations based on race, age, and gender. We then review studies elucidating and furthering our understanding of modifiable factors that contribute to these inequities, including socioeconomic status (particularly age and education), insurance product, and geographic region. Finally, we present work proposing potential strategies addressing disparities in glaucoma care, including teleophthalmology and artificial intelligence. We also discuss the presence of non-modifiable factors that contribute to differences in glaucoma burden and can confound the detection of glaucoma disparities.

Translational Relevance

By recognizing underlying causes and proposing potential solutions, healthcare providers, policymakers, and other stakeholders can work collaboratively to reduce the burden of glaucoma and improve visual health and clinical outcomes in vulnerable patient populations.

OCT-based deep-learning models for the identification of retinal key signs

A new system based on binary Deep Learning (DL) convolutional neural networks has been developed to recognize specific retinal abnormality signs on Optical Coherence Tomography (OCT) images useful for clinical practice. Images from the local hospital database were retrospectively selected from 2017 to 2022. Images were labeled by two retinal specialists and included central fovea cross-section OCTs. Nine models were developed using the Visual Geometry Group 16 architecture to distinguish healthy versus abnormal retinas and to identify eight different retinal abnormality signs. A total of 21,500 OCT images were screened, and 10,770 central fovea cross-section OCTs were included in the study. The system achieved high accuracy in identifying healthy retinas and specific pathological signs, ranging from 93 to 99%. Accurately detecting abnormal retinal signs from OCT images is crucial for patient care. This study aimed to identify specific signs related to retinal pathologies, aiding ophthalmologists in diagnosis. The high-accuracy system identified healthy retinas and pathological signs, making it a useful diagnostic aid. Labelled OCT images remain a challenge, but our approach reduces dataset creation time and shows DL models' potential to improve ocular pathology diagnosis and clinical decision-making.

Forecasting Risk of Future Rapid Glaucoma Worsening Using Early Visual Field, OCT, and Clinical Data

PURPOSE

To assess whether we can forecast future rapid visual field (VF) worsening using deep learning models (DLMs) trained on early VF, OCT, and clinical data.

DESIGN

A retrospective cohort study.

SUBJECTS

In total, 4536 eyes from 2962 patients. Overall, 263 (5.80%) eyes underwent rapid VF worsening (mean deviation slope less than -1 dB/year across all VFs).

METHODS

We included eyes that met the following criteria: (1) followed for glaucoma or suspect status; (2) had at least 5 longitudinal reliable VFs (VF1, VF2, VF3, VF4, and VF5); and (3) had 1 reliable baseline OCT scan (OCT1) and 1 set of baseline clinical measurements (clinical1) at the time of VF1. We designed a DLM to forecast future rapid VF worsening. The input consisted of spatially oriented total deviation values from VF1 (including or not including VF2 and VF3 in some models) and retinal nerve fiber layer thickness values from the baseline OCT. We passed this VF/OCT stack into a vision transformer feature extractor, the output of which was concatenated with baseline clinical data before putting it through a linear classifier to predict the eye's risk of rapid VF worsening across the 5 VFs. We compared the performance of models with differing inputs by computing area under the curve (AUC) in the test set. Specifically, we trained models with the following inputs: (1) model V: VF1; (2) VC: VF1+ Clinical1; (3) VO: VF1+ OCT1; (4) VOC: VF1+ Clinical1+ OCT1; (5) V2: VF1 + VF2; (6) V2OC: VF1 + VF2 + Clinical1 + OCT1; (7) V3: VF1 + VF2 + VF3; and (8) V3OC: VF1 + VF2 + VF3 + Clinical1 + OCT1.

MAIN OUTCOME MEASURES

The AUC of DLMs when forecasting rapidly worsening eyes.

RESULTS

Model V3OC best forecasted rapid worsening with an AUC (95% confidence interval [CI]) of 0.87 (0.77-0.97). Remaining models in descending order of performance and their respective AUC (95% CI) were as follows: (1) model V3 (0.84 [0.74-0.95]), (2) model V2OC (0.81 [0.70-0.92]), (3) model V2 (0.81 [0.70-0.82]), (4) model VOC (0.77 [0.65-0.88]), (5) model VO (0.75 [0.64-0.88]), (6) model VC (0.75 [0.63-0.87]), and (7) model V (0.74 [0.62-0.86]).

CONCLUSIONS

Deep learning models can forecast future rapid glaucoma worsening with modest to high performance when trained using data from early in the disease course. Including baseline data from multiple modalities and subsequent visits improves performance beyond using VF data alone.

FINANCIAL DISCLOSURE(S)

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

Visual field prediction using a deep bidirectional gated recurrent unit network model

Although deep learning architecture has been used to process sequential data, only a few studies have explored the usefulness of deep learning algorithms to detect glaucoma progression. Here, we proposed a bidirectional gated recurrent unit (Bi-GRU) algorithm to predict visual field loss. In total, 5413 eyes from 3321 patients were included in the training set, whereas 1272 eyes from 1272 patients were included in the test set. Data from five consecutive visual field examinations were used as input; the sixth visual field examinations were compared with predictions by the Bi-GRU. The performance of Bi-GRU was compared with the performances of conventional linear regression (LR) and long short-term memory (LSTM) algorithms. Overall prediction error was significantly lower for Bi-GRU than for LR and LSTM algorithms. In pointwise prediction, Bi-GRU showed the lowest prediction error among the three models in most test locations. Furthermore, Bi-GRU was the least affected model in terms of worsening reliability indices and glaucoma severity. Accurate prediction of visual field loss using the Bi-GRU algorithm may facilitate decision-making regarding the treatment of patients with glaucoma.

Artificial intelligence in ophthalmology: The path to the real-world clinic

Artificial intelligence (AI) has great potential to transform healthcare by enhancing the workflow and productivity of clinicians, enabling existing staff to serve more patients, improving patient outcomes, and reducing health disparities. In the field of ophthalmology, AI systems have shown performance comparable with or even better than experienced ophthalmologists in tasks such as diabetic retinopathy detection and grading. However, despite these quite good results, very few AI systems have been deployed in real-world clinical settings, challenging the true value of these systems. This review provides an overview of the current main AI applications in ophthalmology, describes the challenges that need to be overcome prior to clinical implementation of the AI systems, and discusses the strategies that may pave the way to the clinical translation of these systems.

Data Preprocessing and Augmentation Improved Visual Field Prediction of Recurrent Neural Network with Multi-Central Datasets

INTRODUCTION

The purpose of this study was to determine whether data preprocessing and augmentation could improve visual field (VF) prediction of recurrent neural network (RNN) with multi-central datasets.

METHODS

This retrospective study collected data from five glaucoma services between June 2004 and January 2021. From an initial dataset of 331,691 VFs, we considered reliable VF tests with fixed intervals. Since the VF monitoring interval is very variable, we applied data augmentation using multiple sets of data for patients with more than eight VFs. We obtained 5,430 VFs from 463 patients and 13,747 VFs from 1,076 patients by setting the fixed test interval to 365 ± 60 days (D = 365) and 180 ± 60 days (D = 180), respectively. Five consecutive VFs were provided to the constructed RNN as input and the 6th VF was compared with the output of the RNN. The performance of the periodic RNN (D = 365) was compared to that of an aperiodic RNN. The performance of the RNN with 6 long- and short-term memory (LSTM) cells (D = 180) was compared with that of the RNN with 5-LSTM cells. To compare the prediction performance, the root mean square error (RMSE) and mean absolute error (MAE) of the total deviation value (TDV) were calculated as accuracy metrics.

RESULTS

The performance of the periodic model (D = 365) improved significantly over aperiodic model. Overall prediction error (MAE) was 2.56 ± 0.46 dB versus 3.26 ± 0.41 dB (periodic vs. aperiodic) (p < 0.001). A higher perimetric frequency was better for predicting future VF. The overall prediction error (RMSE) was 3.15 ± 2.29 dB versus 3.42 ± 2.25 dB (D = 180 vs. D = 365). Increasing the number of input VFs improved the performance of VF prediction in D = 180 periodic model (3.15 ± 2.29 dB vs. 3.18 ± 2.34 dB, p < 0.001). The 6-LSTM in the D = 180 periodic model was more robust to worsening of VF reliability and disease severity. The prediction accuracy worsened as the false-negative rate increased and the mean deviation decreased.

CONCLUSION

Data preprocessing with augmentation improved the VF prediction of the RNN model using multi-center datasets. The periodic RNN model predicted the future VF significantly better than the aperiodic RNN model.

Use of artificial intelligence in forecasting glaucoma progression

Artificial intelligence (AI) has been widely used in ophthalmology for disease detection and monitoring progression. For glaucoma research, AI has been used to understand progression patterns and forecast disease trajectory based on analysis of clinical and imaging data. Techniques such as machine learning, natural language processing, and deep learning have been employed for this purpose. The results from studies using AI for forecasting glaucoma progression however vary considerably due to dataset constraints, lack of a standard progression definition and differences in methodology and approach. While glaucoma detection and screening have been the focus of most research that has been published in the last few years, in this narrative review we focus on studies that specifically address glaucoma progression. We also summarize the current evidence, highlight studies that have translational potential, and provide suggestions on how future research that addresses glaucoma progression can be improved.

Bidirectional Neural Network Model for Glaucoma Progression Prediction

Deep learning models are usually utilized to learn from spatial data, only a few studies are proposed to predict glaucoma time progression utilizing deep learning models. In this article, we present a bidirectional recurrent deep learning model (Bi-RM) to detect prospective progressive visual field diagnoses. A dataset of 5413 different eyes from 3321 samples is utilized as the learning phase dataset and 1272 eyes are used for testing. Five consecutive diagnoses are recorded from the dataset as input and the sixth progressive visual field diagnosis is matched with the prediction of the Bi-RM. The precision metrics of the Bi-RM are validated in association with the linear regression algorithm (LR) and term memory (TM) technique. The total prediction error of the Bi-RM is significantly less than those of LR and TM. In the class prediction, Bi-RM depicts the least prediction error in all three methods in most of the testing cases. In addition, Bi-RM is not impacted by the reliability keys and the glaucoma degree.

A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach

Glaucoma is a leading cause of irreversible blindness, and its worsening is most often monitored with visual field (VF) testing. Deep learning models (DLM) may help identify VF worsening consistently and reproducibly. In this study, we developed and investigated the performance of a DLM on a large population of glaucoma patients. We included 5099 patients (8705 eyes) seen at one institute from June 1990 to June 2020 that had VF testing as well as clinician assessment of VF worsening. Since there is no gold standard to identify VF worsening, we used a consensus of six commonly used algorithmic methods which include global regressions as well as point-wise change in the VFs. We used the consensus decision as a reference standard to train/test the DLM and evaluate clinician performance. 80%, 10%, and 10% of patients were included in training, validation, and test sets, respectively. Of the 873 eyes in the test set, 309 [60.6%] were from females and the median age was 62.4; (IQR 54.8-68.9). The DLM achieved an AUC of 0.94 (95% CI 0.93-0.99). Even after removing the 6 most recent VFs, providing fewer data points to the model, the DLM successfully identified worsening with an AUC of 0.78 (95% CI 0.72-0.84). Clinician assessment of worsening (based on documentation from the health record at the time of the final VF in each eye) had an AUC of 0.64 (95% CI 0.63-0.66). Both the DLM and clinician performed worse when the initial disease was more severe. This data shows that a DLM trained on a consensus of methods to define worsening successfully identified VF worsening and could help guide clinicians during routine clinical care.

Glaucoma progression. Clinical practice guide

OBJECTIVE

To provide general recommendations that serve as a guide for the evaluation and management of glaucomatous progression in daily clinical practice based on the existing quality of clinical evidence.

METHODS

After defining the objectives and scope of the guide, the working group was formed and structured clinical questions were formulated following the PICO (Patient, Intervention, Comparison, Outcomes) format. Once all the existing clinical evidence had been independently evaluated with the AMSTAR 2 (Assessment of Multiple Systematic Reviews) and Cochrane "Risk of bias" tools by at least two reviewers, recommendations were formulated following the Scottish Intercollegiate Guideline network (SIGN) methodology.

RESULTS

Recommendations with their corresponding levels of evidence that may be useful in the interpretation and decision-making related to the different methods for the detection of glaucomatous progression are presented.

CONCLUSIONS

Despite the fact that for many of the questions the level of scientific evidence available is not very high, this clinical practice guideline offers an updated review of the different existing aspects related to the evaluation and management of glaucomatous progression.

Applications of Artificial Intelligence and Deep Learning in Glaucoma

Diagnosis and detection of progression of glaucoma remains challenging. Artificial intelligence-based tools have the potential to improve and standardize the assessment of glaucoma but development of these algorithms is difficult given the multimodal and variable nature of the diagnosis. Currently, most algorithms are focused on a single imaging modality, specifically screening and diagnosis based on fundus photos or optical coherence tomography images. Use of anterior segment optical coherence tomography and goniophotographs is limited. The majority of algorithms designed for disease progression prediction are based on visual fields. No studies in our literature search assessed the use of artificial intelligence for treatment response prediction and no studies conducted prospective testing of their algorithms. Additional challenges to the development of artificial intelligence-based tools include scarcity of data and a lack of consensus in diagnostic criteria. Although research in the use of artificial intelligence for glaucoma is promising, additional work is needed to develop clinically usable tools.

An Objective and Easy-to-Use Glaucoma Functional Severity Staging System Based on Artificial Intelligence

OBJECTIVE

The objective of this study was to develop an objective and easy-to-use glaucoma staging system based on visual fields (VFs).

SUBJECTS AND PARTICIPANTS

A total of 13,231 VFs from 8077 subjects were used to develop models and 8024 VFs from 4445 subjects were used to validate models.

METHODS

We developed an unsupervised machine learning model to identify clusters with similar VF values. We annotated the clusters based on their respective mean deviation (MD). We computed optimal MD thresholds that discriminate clusters with the highest accuracy based on Bayes minimum error principle. We evaluated the accuracy of the staging system and validated findings based on an independent validation dataset.

RESULTS

The unsupervised k -means algorithm discovered 4 clusters with 6784, 4034, 1541, and 872 VFs and average MDs of 0.0 dB (±1.4: SD), -4.8 dB (±1.9), -12.2 dB (±2.9), and -23.0 dB (±3.8), respectively. The supervised Bayes minimum error classifier identified optimal MD thresholds of -2.2, -8.0, and -17.3 dB for discriminating normal eyes and eyes at the early, moderate, and advanced stages of glaucoma. The accuracy of the glaucoma staging system was 94%, based on identified MD thresholds with respect to the initial k -means clusters.

CONCLUSIONS

We discovered that 4 severity levels based on MD thresholds of -2.2, -8.0, and -17.3 dB, provides the optimal number of severity stages based on unsupervised and supervised machine learning. This glaucoma staging system is unbiased, objective, easy-to-use, and consistent, which makes it highly suitable for use in glaucoma research and for day-to-day clinical practice.

The Development and Clinical Application of Innovative Optical Ophthalmic Imaging Techniques

The field of ophthalmic imaging has grown substantially over the last years. Massive improvements in image processing and computer hardware have allowed the emergence of multiple imaging techniques of the eye that can transform patient care. The purpose of this review is to describe the most recent advances in eye imaging and explain how new technologies and imaging methods can be utilized in a clinical setting. The introduction of optical coherence tomography (OCT) was a revolution in eye imaging and has since become the standard of care for a plethora of conditions. Its most recent iterations, OCT angiography, and visible light OCT, as well as imaging modalities, such as fluorescent lifetime imaging ophthalmoscopy, would allow a more thorough evaluation of patients and provide additional information on disease processes. Toward that goal, the application of adaptive optics (AO) and full-field scanning to a variety of eye imaging techniques has further allowed the histologic study of single cells in the retina and anterior segment. Toward the goal of remote eye care and more accessible eye imaging, methods such as handheld OCT devices and imaging through smartphones, have emerged. Finally, incorporating artificial intelligence (AI) in eye images has the potential to become a new milestone for eye imaging while also contributing in social aspects of eye care.

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

PURPOSE OF REVIEW

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

RECENT FINDINGS

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

SUMMARY

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

A Structure-Related Fine-Grained Deep Learning System With Diversity Data for Universal Glaucoma Visual Field Grading

Purpose

Glaucoma is the main cause of irreversible blindness worldwide. However, the diagnosis and treatment of glaucoma remain difficult because of the lack of an effective glaucoma grading measure. In this study, we aimed to propose an artificial intelligence system to provide adequate assessment of glaucoma patients.

Methods

A total of 16,356 visual fields (VFs) measured by Octopus perimeters and Humphrey Field Analyzer (HFA) were collected, from three hospitals in China and the public Harvard database. We developed a fine-grained grading deep learning system, named FGGDL, to evaluate the VF loss, compared to ophthalmologists. Subsequently, we discuss the relationship between structural and functional damage for the comprehensive evaluation of glaucoma level. In addition, we developed an interactive interface and performed a cross-validation study to test its auxiliary ability. The performance was valued by F1 score, overall accuracy and area under the curve (AUC).

Results

The FGGDL achieved a high accuracy of 85 and 90%, and AUC of 0.93 and 0.90 for HFA and Octopus data, respectively. It was significantly superior (p < 0.01) to that of medical students and nearly equal (p = 0.614) to that of ophthalmic clinicians. For the cross-validation study, the diagnosis accuracy was almost improved (p < 0.05).

Conclusion

We proposed a deep learning system to grade VF of glaucoma with a high detection accuracy, for effective and adequate assessment for glaucoma patients. Besides, with the convenient and credible interface, this system can promote telemedicine and be used as a self-assessment tool for patients with long-duration diseases.

The Role of Artificial Intelligence in the Diagnosis and Management of Glaucoma

Glaucomatous optic neuropathy is the leading cause of irreversible blindness worldwide. Diagnosis and monitoring of disease involves integrating information from the clinical examination with subjective data from visual field testing and objective biometric data that includes pachymetry, corneal hysteresis, and optic nerve and retinal imaging. This intricate process is further complicated by the lack of clear definitions for the presence and progression of glaucomatous optic neuropathy, which makes it vulnerable to clinician interpretation error. Artificial intelligence (AI) and AI-enabled workflows have been proposed as a plausible solution. Applications derived from this field of computer science can improve the quality and robustness of insights obtained from clinical data that can enhance the clinician's approach to patient care. This review clarifies key terms and concepts used in AI literature, discusses the current advances of AI in glaucoma, elucidates the clinical advantages and challenges to implementing this technology, and highlights potential future applications.

Evaluating multidisciplinary glaucoma care: visual field progression and loss of sight year analysis in the community vs hospital setting

BACKGROUND

A variety of shared care models have been developed, which aim to stratify glaucoma patients according to risk of disease progression. However, there is limited published data on the rate of glaucoma progression in the hospital vs community setting. Here we aimed to compare rates of glaucomatous visual field progression in the Cambridge Community Optometrist Glaucoma Scheme (COGS) and Addenbrooke's Hospital Glaucoma Clinic (AGC).

METHODS

A retrospective comparative cohort review was performed. Patients with five or more visual field tests were included. Zeiss Forum software was used to calculate the MD progression rate (dB/year). Loss of sight years (LSY) were also calculated for both COGS and AGC.

RESULTS

Overall, 8465 visual field tests from 854 patients were reviewed. In all, 362 eyes from the AGC group and 210 eyes from COGS were included. The MD deterioration rate was significantly lower in the COGS patients compared with the AGC group (-0.1 vs -0.3 dB/year; p < 0.0001). No patients in the COGS group were predicted to become blind within their lifetime by LSY analysis. Fifteen patients were at risk in the AGC group.

CONCLUSION

This service evaluation shows that COGS is an effective scheme to stratify lower risk glaucoma patients, increasing the capacity within hospital eye services. COGS patients have a lower rate of visual field deterioration compared to AGC patients. Effective communication between community and tertiary schemes is essential to facilitate transfer of patients requiring further hospital management reliably and efficiently, with the potential for low-risk patients to be followed safely in the community.

[Artificial intelligence and glaucoma: A literature review]

In recent years, research in artificial intelligence (AI) has experienced an unprecedented surge in the field of ophthalmology, in particular glaucoma. The diagnosis and follow-up of glaucoma is complex and relies on a body of clinical evidence and ancillary tests. This large amount of information from structural and functional testing of the optic nerve and macula makes glaucoma a particularly appropriate field for the application of AI. In this paper, we will review work using AI in the field of glaucoma, whether for screening, diagnosis or detection of progression. Many AI strategies have shown promising results for glaucoma detection using fundus photography, optical coherence tomography, or automated perimetry. The combination of these imaging modalities increases the performance of AI algorithms, with results comparable to those of humans. We will discuss potential applications as well as obstacles and limitations to the deployment and validation of such models. While there is no doubt that AI has the potential to revolutionize glaucoma management and screening, research in the coming years will need to address unavoidable questions regarding the clinical significance of such results and the explicability of the predictions.

UWHVF: A Real-World, Open Source Dataset of Perimetry Tests From the Humphrey Field Analyzer at the University of Washington

Purpose

This article describes the Humphrey field analyzer (HFA) dataset from the Department of Ophthalmology at the University of Washington.

Methods

Pointwise sensitivities were extracted from HFA 24-2, stimulus III visual fields (VF). Total deviation (TD), mean TD (MTD), pattern deviation, and pattern standard deviation (PSD) were calculated. Progression analysis was performed with simple linear regression on global, regional, and pointwise values for VF series with greater than four tests spanning at least four months. VF data were extracted independently of clinical information except for patient age, gender, and laterality

Results

This dataset includes 28,943 VFs from 7248 eyes of 3871 patients. Progression was calculated for 2985 eyes from 1579 patients. Median [interquartile range] age was 64 years [54, 73], and follow-up was 2.49 years [1.11, 5.03]. Baseline MTD was −4.51 dB [−8.01, −2.65], and baseline PSD was 2.41 dB [1.7, 5.34].

Conclusion

MTD was found to decrease by −0.10 dB/yr [−0.40, 0.11] in eyes for which progression analysis was able to be performed. VFs with deep localized defects, PSD > 12 dB and MTD −15 dB to −25 dB, were plotted, visually inspected, and found to be consistent with neurologic or glaucomatous VFs from patients. For a small number of tests, extracted sensitivity values were compared to corresponding printouts and confirmed to match.

Translational Relevance

This open access pointwise VF dataset serves as a source of raw data for investigation such as VF behavior, clinical comparisons to trials, and development of new machine learning algorithms.

Can Artificial Intelligence Predict Glaucomatous Visual Field Progression? A Spatial-Ordinal Convolutional Neural Network Model

PURPOSE

To develop an artificial neural network model incorporating both spatial and ordinal approaches to predict glaucomatous visual field (VF) progression.

DESIGN

Cohort study. Methods From a cohort of primary open-angle glaucoma patients, 9212 eyes of 6047 patients who underwent regular reliable VF examinations for >4 years were included. We constructed all possible spatial-ordinal tensors by stacking 3 consecutive VF tests (VF-blocks) with at least 3 years of follow-up. Trend-based, event-based, and combined criteria were defined to determine the progression. VF-blocks were considered "progressed" if progression occurred within 3 years; the progression was further confirmed after 3 years. We constructed 6 convolutional neural network (NN) models and 2 linear models: regression on global indices and pointwise linear regression (PLR). We compared area under the receiver operating characteristic curve (AUROC) of each model for the prediction of glaucomatous VF progression.

RESULTS

Among 43,260 VF-blocks, 4406 (10.2%), 4376 (10.1%), and 2394 (5.5%) VF-blocks were classified as progression-based on trend-based and event-based and combined criteria. For all 3 criteria, the progression group was significantly older and had worse initial MD and VF index (VFI) than the nonprogression group (P < .001 for all). The best-performing NN model had an AUROC of 0.864 with a sensitivity of 0.42 at a specificity of 0.95. In contrast, an AUROC of 0.611 was estimated from a sensitivity of 0.28 at a specificity of 0.84 for the PLR.

CONCLUSIONS

The NN models incorporating spatial-ordinal characteristics demonstrated significantly better performance than the linear models in the prediction of glaucomatous VF progression.

Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review

BACKGROUND

Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements.

OBJECTIVE

The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions.

METHODS

For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations.

RESULTS

We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study.

CONCLUSIONS

Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.

Development of glaucoma predictive model and risk factors assessment based on supervised models

Objectives

To develop and to propose a machine learning model for predicting glaucoma and identifying its risk factors.

Method

Data analysis pipeline is designed for this study based on Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. The main steps of the pipeline include data sampling, preprocessing, classification and evaluation and validation. Data sampling for providing the training dataset was performed with balanced sampling based on over-sampling and under-sampling methods. Data preprocessing steps were missing value imputation and normalization. For classification step, several machine learning models were designed for predicting glaucoma including Decision Trees (DTs), K-Nearest Neighbors (K-NN), Support Vector Machines (SVM), Random Forests (RFs), Extra Trees (ETs) and Bagging Ensemble methods. Moreover, in the classification step, a novel stacking ensemble model is designed and proposed using the superior classifiers.

Results

The data were from Shahroud Eye Cohort Study including demographic and ophthalmology data for 5190 participants aged 40-64 living in Shahroud, northeast Iran. The main variables considered in this dataset were 67 demographics, ophthalmologic, optometric, perimetry, and biometry features for 4561 people, including 4474 non-glaucoma participants and 87 glaucoma patients. Experimental results show that DTs and RFs trained based on under-sampling of the training dataset have superior performance for predicting glaucoma than the compared single classifiers and bagging ensemble methods with the average accuracy of 87.61 and 88.87, the sensitivity of 73.80 and 72.35, specificity of 87.88 and 89.10 and area under the curve (AUC) of 91.04 and 94.53, respectively. The proposed stacking ensemble has an average accuracy of 83.56, a sensitivity of 82.21, a specificity of 81.32, and an AUC of 88.54.

Conclusions

In this study, a machine learning model is proposed and developed to predict glaucoma disease among persons aged 40-64. Top predictors in this study considered features for discriminating and predicting non-glaucoma persons from glaucoma patients include the number of the visual field detect on perimetry, vertical cup to disk ratio, white to white diameter, systolic blood pressure, pupil barycenter on Y coordinate, age, and axial length.

Detecting Progression of Retinitis Pigmentosa Using the Binomial Pointwise Linear Regression Method

Purpose

A method of evaluating central visual field (VF) progression in eyes with retinitis pigmentosa (RP) has still to be established. We previously reported the potential merit of applying a binomial test to pointwise linear regression (binomial PLR) in glaucoma progression. In the current study, we investigated the usefulness of binomial PLR in eyes with RP.

Methods

A series of 10 VFs (VF 1–10, Humphrey field analyzer, 10-2 test) from 196 eyes of 103 patients with RP were collected retrospectively. The PLR was performed by regressing the total deviation of all test points with the complete series of 10 VFs. The accuracy (positive predictive value, negative predictive value, and false-positive rate) and the time required to detect VF progression with shorter VF series (from VF 1–5 to VF 1–9) were compared across the binomial PLR, a permutation analysis of PLR (PoPLR), and a mean deviation (MD) trend analysis.

Results

In evaluating VF progression, the binomial PLR was comparable with the PoPLR and MD trend analyses in its positive predictive value (0.55 to 0.95), negative predictive value (0.67 to 0.92), and false-positive rate (0.01 to 0.05). The binomial PLR required significantly less time to detect VF progression (5.0 ± 2.0 years) than the PoPLR and MD trend analyses (P < 0.01, P < 0.001, respectively).

Conclusions

The application of a binomial PLR achieved reliable and earlier detection of central VF progression in eyes with RP.

Translational Relevance

A binomial PLR was useful in assessing VF progression in RP.

Measures of disease activity in glaucoma

Glaucoma is the leading cause of irreversible blindness globally which significantly affects the quality of life and has a substantial economic impact. Effective detective methods are necessary to identify glaucoma as early as possible. Regular eye examinations are important for detecting the disease early and preventing deterioration of vision and quality of life. Current methods of measuring disease activity are powerful in describing the functional and structural changes in glaucomatous eyes. However, there is still a need for a novel tool to detect glaucoma earlier and more accurately. Tear fluid biomarker analysis and new imaging technology provide novel surrogate endpoints of glaucoma. Artificial intelligence is a post-diagnostic tool that can analyse ophthalmic test results. A detail review of currently used clinical tests in glaucoma include intraocular pressure test, visual field test and optical coherence tomography are presented. The advanced technologies for glaucoma measurement which can identify specific disease characteristics, as well as the mechanism, performance and future perspectives of these devices are highlighted. Applications of AI in diagnosis and prediction in glaucoma are mentioned. With the development in imaging tools, sensor technologies and artificial intelligence, diagnostic evaluation of glaucoma must assess more variables to facilitate earlier diagnosis and management in the future.

Optical Coherence Tomography and Glaucoma

Early detection and monitoring are critical to the diagnosis and management of glaucoma, a progressive optic neuropathy that causes irreversible blindness. Optical coherence tomography (OCT) has become a commonly utilized imaging modality that aids in the detection and monitoring of structural glaucomatous damage. Since its inception in 1991, OCT has progressed through multiple iterations, from time-domain OCT, to spectral-domain OCT, to swept-source OCT, all of which have progressively improved the resolution and speed of scans. Even newer technological advancements and OCT applications, such as adaptive optics, visible-light OCT, and OCT-angiography, have enriched the use of OCT in the evaluation of glaucoma. This article reviews current commercial and state-of-the-art OCT technologies and analytic techniques in the context of their utility for glaucoma diagnosis and management, as well as promising future directions.

Telehealth and Screening Strategies in the Diagnosis and Management of Glaucoma

Telehealth has become a viable option for glaucoma screening and glaucoma monitoring due to advances in technology. The ability to measure intraocular pressure without an anesthetic and to take optic nerve photographs without pharmacologic pupillary dilation using portable equipment have allowed glaucoma screening programs to generate enough data for assessment. At home, patients can perform visual acuity testing, web-based visual field testing, rebound tonometry, and video visits with the physician to monitor for glaucomatous progression. Artificial intelligence will enhance the accuracy of data interpretation and inspire confidence in popularizing telehealth for glaucoma.

Prediction of Visual Field Progression from OCT Structural Measures in Moderate to Advanced Glaucoma

PURPOSE

To test the hypothesis that visual field (VF) progression can be predicted from baseline and longitudinal optical coherence tomography (OCT) structural measurements.

DESIGN

Prospective cohort study.

METHODS

A total of 104 eyes (104 patients) with ≥3 years of follow-up and ≥5 VF examinations were enrolled. We defined VF progression based on pointwise linear regression on 24-2 VF (≥3 locations with slope less than or equal to -1.0 dB/year and P < .01). We used elastic net logistic regression (ENR) and machine learning to predict VF progression with demographics, baseline circumpapillary retinal nerve fiber layer (RNFL), macular ganglion cell/inner plexiform layer (GCIPL) thickness, and RNFL and GCIPL change rates at central 24 superpixels and 3 eccentricities, 3.4°, 5.5°, and 6.8°, from fovea and hemimaculas. Areas-under-ROC curves (AUC) were used to compare models.

RESULTS

Average ± SD follow-up and VF examinations were 4.5 ± 0.9 years and 8.7 ± 1.6, respectively. VF progression was detected in 23 eyes (22%). ENR selected rates of change of superotemporal RNFL sector and GCIPL change rates in 5 central superpixels and at 3.4° and 5.6° eccentricities as the best predictor subset (AUC = 0.79 ± 0.12). Best machine learning predictors consisted of baseline superior hemimacular GCIPL thickness and GCIPL change rates at 3.4° eccentricity and 3 central superpixels (AUC = 0.81 ± 0.10). Models using GCIPL-only structural variables performed better than RNFL-only models.

CONCLUSIONS

VF progression can be predicted with clinically relevant accuracy from baseline and longitudinal structural data. Further refinement of proposed models would assist clinicians with timely prediction of functional glaucoma progression and clinical decision making.

Artificial intelligence in ophthalmology and healthcare: An updated review of the techniques in use

Artificial intelligence (AI) refers to “the ability of a digital machine or computer to accomplish tasks that traditionally have required human intelligence.” These days, artificial intelligence is becoming popular in healthcare and more so in ophthalmology. It has shown promising results in diabetic retinopathy detection and referral. Recently, Indian data has depicted that the new algorithms can be generalized to the Indian population as well. An increased understanding of the tools is required especially by the practitioners and medical researchers so that they can contribute meaningfully to the development of the technology and not become mere data providers and data labelers. While AI is extensively being used by finance, marketing and travel industry, its application is more recent in medicine. The applications based on artificial intelligence have the potential to benefit all stakeholders in the healthcare industry.

Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective

The simultaneous maturation of multiple digital and telecommunications technologies in 2020 has created an unprecedented opportunity for ophthalmology to adapt to new models of care using tele-health supported by digital innovations. These digital innovations include artificial intelligence (AI), 5th generation (5G) telecommunication networks and the Internet of Things (IoT), creating an inter-dependent ecosystem offering opportunities to develop new models of eye care addressing the challenges of COVID-19 and beyond. Ophthalmology has thrived in some of these areas partly due to its many image-based investigations. Tele-health and AI provide synchronous solutions to challenges facing ophthalmologists and healthcare providers worldwide. This article reviews how countries across the world have utilised these digital innovations to tackle diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration, glaucoma, refractive error correction, cataract and other anterior segment disorders. The review summarises the digital strategies that countries are developing and discusses technologies that may increasingly enter the clinical workflow and processes of ophthalmologists. Furthermore as countries around the world have initiated a series of escalating containment and mitigation measures during the COVID-19 pandemic, the delivery of eye care services globally has been significantly impacted. As ophthalmic services adapt and form a "new normal", the rapid adoption of some of telehealth and digital innovation during the pandemic is also discussed. Finally, challenges for validation and clinical implementation are considered, as well as recommendations on future directions.

Fundus-controlled perimetry (microperimetry): Application as outcome measure in clinical trials

Fundus-controlled perimetry (FCP, also called 'microperimetry') allows for spatially-resolved mapping of visual sensitivity and measurement of fixation stability, both in clinical practice as well as research. The accurate spatial characterization of visual function enabled by FCP can provide insightful information about disease severity and progression not reflected by best-corrected visual acuity in a large range of disorders. This is especially important for monitoring of retinal diseases that initially spare the central retina in earlier disease stages. Improved intra- and inter-session retest-variability through fundus-tracking and precise point-wise follow-up examinations even in patients with unstable fixation represent key advantages of these technique. The design of disease-specific test patterns and protocols reduces the burden of extensive and time-consuming FCP testing, permitting a more meaningful and focused application. Recent developments also allow for photoreceptor-specific testing through implementation of dark-adapted chromatic and photopic testing. A detailed understanding of the variety of available devices and test settings is a key prerequisite for the design and optimization of FCP protocols in future natural history studies and clinical trials. Accordingly, this review describes the theoretical and technical background of FCP, its prior application in clinical and research settings, data that qualify the application of FCP as an outcome measure in clinical trials as well as ongoing and future developments.

Development and Validation of Automated Visual Field Report Extraction Platform Using Computer Vision Tools

Purpose: To introduce and validate hvf_extraction_script, an open-source software script for the automated extraction and structuring of metadata, value plot data, and percentile plot data from Humphrey visual field (HVF) report images.

Methods: Validation was performed on 90 HVF reports over three different report layouts, including a total of 1,530 metadata fields, 15,536 value plot data points, and 10,210 percentile data points, between the computer script and four human extractors, compared against DICOM reference data. Computer extraction and human extraction were compared on extraction time as well as accuracy of extraction for metadata, value plot data, and percentile plot data.

Results: Computer extraction required 4.9-8.9 s per report, compared to the 6.5-19 min required by human extractors, representing a more than 40-fold difference in extraction speed. Computer metadata extraction error rate varied from an aggregate 1.2-3.5%, compared to 0.2-9.2% for human metadata extraction across all layouts. Computer value data point extraction had an aggregate error rate of 0.9% for version 1, <0.01% in version 2, and 0.15% in version 3, compared to 0.8-9.2% aggregate error rate for human extraction. Computer percentile data point extraction similarly had very low error rates, with no errors occurring in version 1 and 2, and 0.06% error rate in version 3, compared to 0.06-12.2% error rate for human extraction.

Conclusions: This study introduces and validates hvf_extraction_script, an open-source tool for fast, accurate, automated data extraction of HVF reports to facilitate analysis of large-volume HVF datasets, and demonstrates the value of image processing tools in facilitating faster and cheaper large-volume data extraction in research settings.

Digital Image Processing and Development of Machine Learning Models for the Discrimination of Corneal Pathology: An Experimental Model

Machine learning (ML) has an impressive capacity to learn and analyze a large volume of data. This study aimed to train different algorithms to discriminate between healthy and pathologic corneal images by evaluating digitally processed spectral-domain optical coherence tomography (SD-OCT) corneal images. A set of 22 SD-OCT images belonging to a random set of corneal pathologies was compared to 71 healthy corneas (control group). A binary classification method was applied where three approaches of ML were explored. Once all images were analyzed, representative areas from every digital image were also extracted, processed and analyzed for a statistical feature comparison between healthy and pathologic corneas. The best performance was obtained from transfer learning—support vector machine (TL-SVM) (AUC = 0.94, SPE 88%, SEN 100%) and transfer learning—random forest (TL- RF) method (AUC = 0.92, SPE 84%, SEN 100%), followed by convolutional neural network (CNN) (AUC = 0.84, SPE 77%, SEN 91%) and random forest (AUC = 0.77, SPE 60%, SEN 95%). The highest diagnostic accuracy in classifying corneal images was achieved with the TL-SVM and the TL-RF models. In image classification, CNN was a strong predictor. This pilot experimental study developed a systematic mechanized system to discern pathologic from healthy corneas using a small sample.

Deep learning-enabled medical computer vision

A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields-including medicine-to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques-powered by deep learning-for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit-including cardiology, pathology, dermatology, ophthalmology-and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies.

Optical coherence tomography-based deep-learning model for detecting central serous chorioretinopathy

Central serous chorioretinopathy (CSC) is a common condition characterized by serous detachment of the neurosensory retina at the posterior pole. We built a deep learning system model to diagnose CSC, and distinguish chronic from acute CSC using spectral domain optical coherence tomography (SD-OCT) images. Data from SD-OCT images of patients with CSC and a control group were analyzed with a convolutional neural network. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were used to evaluate the model. For CSC diagnosis, our model showed an accuracy, sensitivity, and specificity of 93.8%, 90.0%, and 99.1%, respectively; AUROC was 98.9% (95% CI, 0.983–0.995); and its diagnostic performance was comparable with VGG-16, Resnet-50, and the diagnoses of five different ophthalmologists. For distinguishing chronic from acute cases, the accuracy, sensitivity, and specificity were 97.6%, 100.0%, and 92.6%, respectively; AUROC was 99.4% (95% CI, 0.985–1.000); performance was better than VGG-16 and Resnet-50, and was as good as the ophthalmologists. Our model performed well when diagnosing CSC and yielded highly accurate results when distinguishing between acute and chronic cases. Thus, automated deep learning system algorithms could play a role independent of human experts in the diagnosis of CSC.

Artificial Intelligence Algorithms to Diagnose Glaucoma and Detect Glaucoma Progression: Translation to Clinical Practice

Purpose

This concise review aims to explore the potential for the clinical implementation of artificial intelligence (AI) strategies for detecting glaucoma and monitoring glaucoma progression.

Methods

Nonsystematic literature review using the search combinations “Artificial Intelligence,” “Deep Learning,” “Machine Learning,” “Neural Networks,” “Bayesian Networks,” “Glaucoma Diagnosis,” and “Glaucoma Progression.” Information on sensitivity and specificity regarding glaucoma diagnosis and progression analysis as well as methodological details were extracted.

Results

Numerous AI strategies provide promising levels of specificity and sensitivity for structural (e.g. optical coherence tomography [OCT] imaging, fundus photography) and functional (visual field [VF] testing) test modalities used for the detection of glaucoma. Area under receiver operating curve (AROC) values of > 0.90 were achieved with every modality. Combining structural and functional inputs has been shown to even more improve the diagnostic ability. Regarding glaucoma progression, AI strategies can detect progression earlier than conventional methods or potentially from one single VF test.

Conclusions

AI algorithms applied to fundus photographs for screening purposes may provide good results using a simple and widely accessible test. However, for patients who are likely to have glaucoma more sophisticated methods should be used including data from OCT and perimetry. Outputs may serve as an adjunct to assist clinical decision making, whereas also enhancing the efficiency, productivity, and quality of the delivery of glaucoma care. Patients with diagnosed glaucoma may benefit from future algorithms to evaluate their risk of progression. Challenges are yet to be overcome, including the external validity of AI strategies, a move from a “black box” toward “explainable AI,” and likely regulatory hurdles. However, it is clear that AI can enhance the role of specialist clinicians and will inevitably shape the future of the delivery of glaucoma care to the next generation.

Translational Relevance

The promising levels of diagnostic accuracy reported by AI strategies across the modalities used in clinical practice for glaucoma detection can pave the way for the development of reliable models appropriate for their translation into clinical practice. Future incorporation of AI into healthcare models may help address the current limitations of access and timely management of patients with glaucoma across the world.

Development and clinical deployment of a smartphone-based visual field deep learning system for glaucoma detection

By 2040, ~100 million people will have glaucoma. To date, there are a lack of high-efficiency glaucoma diagnostic tools based on visual fields (VFs). Herein, we develop and evaluate the performance of 'iGlaucoma', a smartphone application-based deep learning system (DLS) in detecting glaucomatous VF changes. A total of 1,614,808 data points of 10,784 VFs (5542 patients) from seven centers in China were included in this study, divided over two phases. In Phase I, 1,581,060 data points from 10,135 VFs of 5105 patients were included to train (8424 VFs), validate (598 VFs) and test (3 independent test sets-200, 406, 507 samples) the diagnostic performance of the DLS. In Phase II, using the same DLS, iGlaucoma cloud-based application further tested on 33,748 data points from 649 VFs of 437 patients from three glaucoma clinics. With reference to three experienced expert glaucomatologists, the diagnostic performance (area under curve [AUC], sensitivity and specificity) of the DLS and six ophthalmologists were evaluated in detecting glaucoma. In Phase I, the DLS outperformed all six ophthalmologists in the three test sets (AUC of 0.834-0.877, with a sensitivity of 0.831-0.922 and a specificity of 0.676-0.709). In Phase II, iGlaucoma had 0.99 accuracy in recognizing different patterns in pattern deviation probability plots region, with corresponding AUC, sensitivity and specificity of 0.966 (0.953-0.979), 0.954 (0.930-0.977), and 0.873 (0.838-0.908), respectively. The 'iGlaucoma' is a clinically effective glaucoma diagnostic tool to detect glaucoma from humphrey VFs, although the target population will need to be carefully identified with glaucoma expertise input.

Artificial intelligence and deep learning in glaucoma: Current state and future prospects

Over the past few years, there has been an unprecedented and tremendous excitement for artificial intelligence (AI) research in the field of Ophthalmology; this has naturally been translated to glaucoma-a progressive optic neuropathy characterized by retinal ganglion cell axon loss and associated visual field defects. In this review, we aim to discuss how AI may have a unique opportunity to tackle the many challenges faced in the glaucoma clinic. This is because glaucoma remains poorly understood with difficulties in providing early diagnosis and prognosis accurately and in a timely fashion. In the short term, AI could also become a game changer by paving the way for the first cost-effective glaucoma screening campaigns. While there are undeniable technical and clinical challenges ahead, and more so than for other ophthalmic disorders whereby AI is already booming, we strongly believe that glaucoma specialists should embrace AI as a companion to their practice. Finally, this review will also remind ourselves that glaucoma is a complex group of disorders with a multitude of physiological manifestations that cannot yet be observed clinically. AI in glaucoma is here to stay, but it will not be the only tool to solve glaucoma.

A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression

Because of recent advances in computing technology and the availability of large datasets, deep learning has risen to the forefront of artificial intelligence, with performances that often equal, or sometimes even exceed, those of human subjects on a variety of tasks, especially those related to image classification and pattern recognition. As one of the medical fields that is highly dependent on ancillary imaging tests, ophthalmology has been in a prime position to witness the application of deep learning algorithms that can help analyze the vast amount of data coming from those tests. In particular, glaucoma stands as one of the conditions where application of deep learning algorithms could potentially lead to better use of the vast amount of information coming from structural and functional tests evaluating the optic nerve and macula. The purpose of this article is to critically review recent applications of deep learning models in glaucoma, discussing their advantages but also focusing on the challenges inherent to the development of such models for screening, diagnosis and detection of progression. After a brief general overview of deep learning and how it compares to traditional machine learning classifiers, we discuss issues related to the training and validation of deep learning models and how they specifically apply to glaucoma. We then discuss specific scenarios where deep learning has been proposed for use in glaucoma, such as screening with fundus photography, and diagnosis and detection of glaucoma progression with optical coherence tomography and standard automated perimetry.

Translational Relevance

Deep learning algorithms have the potential to significantly improve diagnostic capabilities in glaucoma, but their application in clinical practice requires careful validation, with consideration of the target population, the reference standards used to build the models, and potential sources of bias.

An artificial intelligence model for the simulation of visual effects in patients with visual field defects

Background

This study aimed to simulate the visual field (VF) effects of patients with VF defects using deep learning and computer vision technology.

Methods

We collected 3,660 Humphrey visual fields (HVFs) as data samples, including 3,263 reliable 24-2 HVFs. The convolutional neural network (CNN) analyzed and converted the grayscale map of reliable samples into structured data. The artificial intelligence (AI) simulations were developed using computer vision technology. In statistical analyses, the pilot study determined 687 reliable samples to conduct clinical trials, and the two independent sample t-tests were used to calculate the difference of the cumulative gray values. Three volunteers evaluated the matching degree of shape and position between the grayscale map and the AI simulation, which was graded from 0 to100 scores. Based on the average ranking, the proportion of good and excellent grades was determined, and thus the reliability of the AI simulations was assessed.

Results

The reliable samples in the experimental data consisted of 1,334 normal samples and 1,929 abnormal samples. Based on the existing mature CNN model, the fully connected layer was integrated to analyze the VF damage parameters of the input images, and the prediction accuracy of the damage type of the VF defects was up to 89%. By mapping the area and damage information in the VF damage parameter quintuple data set into the real scene image and adjusting the darkening effect according to the damage parameter, the visual effects in patients were simulated in the real scene image. In the clinical validation, there was no statistically significant difference in the cumulative gray value (P>0.05). The good and excellent proportion of the average scores reached 96.0%, thus confirming the accuracy of the AI model.

Conclusions

An AI model with high accuracy was established to simulate the visual effects in patients with VF defects.

Artificial Intelligence Classification of Central Visual Field Patterns in Glaucoma

PURPOSE

To quantify the central visual field (VF) loss patterns in glaucoma using artificial intelligence.

DESIGN

Retrospective study.

PARTICIPANTS

VFs of 8712 patients with 13 951 Humphrey 10-2 test results from 13 951 eyes for cross-sectional analyses, and 824 patients with at least 5 reliable 10-2 test results at 6-month intervals or more from 1191 eyes for longitudinal analyses.

METHODS

Total deviation values were used to determine the central VF patterns using the most recent 10-2 test results. A 24-2 VF within a 3-month window of the 10-2 tests was used to stage eyes into mild, moderate, or severe functional loss using the Hodapp-Anderson-Parrish scale at baseline. Archetypal analysis was applied to determine the central VF patterns. Cross-validation was performed to determine the optimal number of patterns. Stepwise regression was applied to select the optimal feature combination of global indices, average baseline decomposition coefficients from central VFs archetypes, and other factors to predict central VF mean deviation (MD) slope based on the Bayesian information criterion (BIC).

MAIN OUTCOME MEASURES

The central VF patterns stratified by severity stage based on 24-2 test results and a model to predict the central VF MD change over time using baseline test results.

RESULTS

From cross-sectional analysis, 17 distinct central VF patterns were determined for the 13 951 eyes across the spectrum of disease severity. These central VF patterns could be divided into isolated superior loss, isolated inferior loss, diffuse loss, and other loss patterns. Notably, 4 of the 5 patterns of diffuse VF loss preserved the less vulnerable inferotemporal zone, whereas they lost most of the remaining more vulnerable zone described by the Hood model. Inclusion of coefficients from central VF archetypical patterns strongly improved the prediction of central VF MD slope (BIC decrease, 35; BIC decrease of >6 indicating strong prediction improvement) than using only the global indices of 2 baseline VF results. Eyes with baseline VF results with more superonasal and inferonasal loss were more likely to show worsening MD over time.

CONCLUSIONS

We quantified central VF patterns in glaucoma, which were used to improve the prediction of central VF worsening compared with using only global indices.