Ocular Hypertension Treatment Study Research Articles

The need for more pragmatic trials in glaucoma research.

There have been a number of clinical trials in glaucoma research published in the past two decades. Most of these trials were designed to evaluate very specific issues in selected populations placing them in the explanatory end of the pragmatic-explanatory continuum. The purpose of this study was to assess the level of pragmatism of published randomized controlled trials in glaucoma. A PubMed search using 'glaucoma' from 1995 to 2022 and randomized controlled trial (RCT) article type was done. Each study was assessed by three independent examiners using the Pragmatic-Explanatory Continuum Indicator Summary version 2 (PRECIS-2) toolkit. Scores were calculated for each study to determine the level of pragmatism. A summed score ≥36 was indicative of a very pragmatic study. Thirty-two different articles were included in the analysis. These papers represented 13 different landmark trials. The median PRECIS-2 score was 32 (range, 25 for the Early Manifest Glaucoma Trial (EMGT) to 34 to the Collaborative Normal Tension Glaucoma Study (CNTGS) and the Ocular Hypertension Treatment Study). The Treatment of Advanced Glaucoma Study (TAGS), was considered very pragmatic and scored 33 points. Despite the number of RCTs in glaucoma, there is still a need for more pragmatic studies.

Polygenic Risk Scores for Glaucoma Onset in the Ocular Hypertension Treatment Study

Primary open-angle glaucoma (POAG) is a highly heritable disease, with 127 identified risk loci to date. Polygenic risk score (PRS) may provide a clinically useful measure of aggregate genetic burden and improve patient risk stratification. To assess whether a PRS improves prediction of POAG onset in patients with ocular hypertension. This was a post hoc analysis of the Ocular Hypertension Treatment Study. Data were collected from 22 US sites with a mean (SD) follow-up of 14.0 (6.9) years. A total of 1636 participants were followed up from February 1994 to December 2008; 1077 participants were enrolled in an ancillary genetics study, of which 1009 met criteria for this analysis. PRS was calculated using summary statistics from the largest cross-ancestry POAG meta-analysis, with weights trained using 8 813 496 variants from 449 186 cross-ancestry participants in the UK Biobank. Data were analyzed from July 2022 to December 2023. From February 1994 to June 2002, participants were randomized to either topical intraocular pressure-lowering medication or close observation. After June 2002, both groups received medication. Outcome measures were hazard ratios for POAG onset. Concordance index and time-dependent areas under the receiver operating characteristic curve were used to compare the predictive performance of multivariable Cox proportional hazards models. Of 1009 included participants, 562 (55.7%) were female, and the mean (SD) age was 55.9 (9.3) years. The mean (SD) PRS was significantly higher for 350 POAG converters (0.24 [0.95]) compared with 659 nonconverters (-0.12 [1.00]) (P < .001). POAG risk increased 1.36% (95% CI, 1.08-1.64) with each higher PRS decile, with conversion ranging from 9.52% (95% CI, 7.09-11.95) in the lowest PRS decile to 21.81% (95% CI, 19.37-24.25) in the highest decile. Comparison of low-risk and high-risk PRS tertiles showed a 2.0-fold increase in 20-year POAG risk for participants of European and African ancestries. In the subgroup randomized to delayed treatment, each increase in PRS decile was associated with a 0.52-year (95% CI, 0.01-1.03) decrease in age at diagnosis (P = .047). No significant linear association between PRS and age at POAG diagnosis was present in the early treatment group. Prediction models significantly improved with the addition of PRS as a covariate (C index = 0.77) compared with the Ocular Hypertension Treatment Study baseline model (C index = 0.75) (P < .001). Each 1-SD higher PRS conferred a mean hazard ratio of 1.25 (95% CI, 1.13-1.44) for POAG onset. Higher PRS was associated with increased risk for POAG in patients with ocular hypertension. The inclusion of a PRS improved the prediction of POAG onset. ClinicalTrials.gov Identifier: NCT00000125.

Machine Learning-Derived Baseline Visual Field Patterns Predict Future Glaucoma Onset in the Ocular Hypertension Treatment Study.

The Ocular Hypertension Treatment Study (OHTS) identified risk factors for primary open-angle glaucoma (POAG) in patients with ocular hypertension, including pattern standard deviation (PSD). Archetypal analysis, an unsupervised machine learning method, may offer a more interpretable approach to risk stratification by identifying patterns in baseline visual fields (VFs). There were 3272 eyes available in the OHTS. Archetypal analysis was applied using 24-2 baseline VFs, and model selection was performed with cross-validation. Decomposition coefficients for archetypes (ATs) were calculated. A penalized Cox proportional hazards model was implemented to select discriminative ATs. The AT model was compared to the OHTS model. Associations were identified between ATs with both POAG onset and VF progression, defined by mean deviation change per year. We selected 8494 baseline VFs. Optimal AT count was 19. The highest prevalence ATs were AT9, AT11, and AT7. The AT-based prediction model had a C-index of 0.75 for POAG onset. Multivariable models demonstrated that a one-interquartile range increase in the AT5 (hazard ratio [HR] = 1.14; 95% confidence interval [CI], 1.04-1.25), AT8 (HR = 1.22; 95% CI, 1.09-1.37), AT15 (HR = 1.26; 95% CI, 1.12-1.41), and AT17 (HR = 1.17; 95% CI, 1.03-1.31) coefficients conferred increased risk of POAG onset. AT5, AT10, and AT14 were significantly associated with rapid VF progression. In a subgroup analysis by high-risk ATs (>95th percentile or <75th percentile coefficients), PSD lost significance as a predictor of POAG in the low-risk group. Baseline VFs, prior to detectable glaucomatous damage, contain occult patterns representing early changes that may increase the risk of POAG onset and VF progression in patients with ocular hypertension. The relationship between PSD and POAG is modified by the presence of high-risk patterns at baseline. An AT-based prediction model for POAG may provide more interpretable glaucoma-specific information in a clinical setting.

Visual field progression patterns in the ocular hypertension treatment study correspond to vulnerability regions of the disc.

To determine the locations on the 24-2 visual field (VF) testing grid that are most likely to progress in patients with ocular hypertension (OHTN). Based on a structural model of superior and inferior areas of relative vulnerability at the optic disc, we hypothesized that the nasal and paracentral regions are more prone to show a reduction in sensitivity. Posthoc analysis of data collected in phases 1 and 2 of the Ocular Hypertension Treatment Study (OHTS). A pointwise analysis was applied to determine the progression patterns in the early and delayed treatment groups. Each group's progression rate and frequency were calculated for each of the 52 locations corresponding to the 24-2 VF strategy, using trend- and event-based analyses, respectively. For the event-based analysis, the events were most commonly found in the nasal and paracentral regions. The same regions, with some modest variation, were found to have the fastest rates of progression (ROP) measured with trend analysis. A similar pattern of progression was observed in both the early and delayed treatment groups. The difference in event rates and ROP between the early and delayed treatment groups was also greatest in the nasal and paracentral regions. Development of VF loss in ocular hypertensive eyes appears to be consistent with the vulnerability zones previously described in glaucomatous eyes with established VF loss. Ocular hypotensive treatment likely helps to slow the rate of progression in these regions. This suggests that careful monitoring of these locations may be useful.

Deep Learning Identifies High-Quality Fundus Photographs and Increases Accuracy in Automated Primary Open Angle Glaucoma Detection.

To develop and evaluate a deep learning (DL) model to assess fundus photograph quality, and quantitatively measure its impact on automated POAG detection in independent study populations. Image quality ground truth was determined by manual review of 2815 fundus photographs of healthy and POAG eyes from the Diagnostic Innovations in Glaucoma Study and African Descent and Glaucoma Evaluation Study (DIGS/ADAGES), as well as 11,350 from the Ocular Hypertension Treatment Study (OHTS). Human experts assessed a photograph as high quality if of sufficient quality to determine POAG status and poor quality if not. A DL quality model was trained on photographs from DIGS/ADAGES and tested on OHTS. The effect of DL quality assessment on DL POAG detection was measured using area under the receiver operating characteristic (AUROC). The DL quality model yielded an AUROC of 0.97 for differentiating between high- and low-quality photographs; qualitative human review affirmed high model performance. Diagnostic accuracy of the DL POAG model was significantly greater (P < 0.001) in good (AUROC, 0.87; 95% CI, 0.80-0.92) compared with poor quality photographs (AUROC, 0.77; 95% CI, 0.67-0.88). The DL quality model was able to accurately assess fundus photograph quality. Using automated quality assessment to filter out low-quality photographs increased the accuracy of a DL POAG detection model. Incorporating DL quality assessment into automated review of fundus photographs can help to decrease the burden of manual review and improve accuracy for automated DL POAG detection.

Deep learning models to predict primary open‐angle glaucoma

SummaryGlaucoma is a major cause of blindness and vision impairment worldwide, and visual field (VF) tests are essential for monitoring the conversion of glaucoma. While previous studies have primarily focused on using VF data at a single time point for glaucoma prediction, there has been limited exploration of longitudinal trajectories. Additionally, many deep learning techniques treat the time‐to‐glaucoma prediction as a binary classification problem (glaucoma Yes/No), resulting in the misclassification of some censored subjects into the nonglaucoma category and decreased power. To tackle these challenges, we propose and implement several deep‐learning approaches that naturally incorporate temporal and spatial information from longitudinal VF data to predict time‐to‐glaucoma. When evaluated on the Ocular Hypertension Treatment Study (OHTS) dataset, our proposed convolutional neural network (CNN)‐long short‐term memory (LSTM) emerged as the top‐performing model among all those examined. The implementation code can be found online (https://github.com/rivenzhou/VF_prediction).

What is the Optimal Frequency of Visual Field Testing to Detect Rapid Progression Among Hypertensive Eyes?

We evaluated 16,351 visual field (VF) tests from Ocular Hypertension Treatment Study (OHTS) database and showed that more frequent testing resulted in a shorter time to detect glaucoma progression, with the best trade-off being the 6-month intervals for high-risk and 12 months for low-risk patients. To investigate the effect of different testing intervals on time to detect visual field progression in eyes with ocular hypertension. A total of 16,351 reliable 30-2 VF tests from 1575 eyes of the OHTS-1 observation arm with a mean (95% CI) follow-up of 4.8 (4.7-4.8) years were analyzed. Computer simulations (n = 10,000 eyes) based on mean deviation values and the residuals of risk groups (according to their baseline 5 y risk of developing primary open angle glaucoma: low, medium, and high risk) were performed to estimate time to detect progression with testing intervals of 4, 6, 12, and 24 months using linear regression. The time to detect VF progression ( P < 5%) at 80% power was calculated based on the mean deviation slope of -0.42 dB/year. We assessed the time to detect a -3 dB loss as an estimate of clinically meaningful perimetric loss. At 80% power, based on the progression of -0.42 dB/year, the best trade-off to detect significant rates of VF change to clinically meaningful perimetric loss in high, medium, and low-risk patients was 6, 6, and 12-month intervals, respectively. Given the importance of not missing the conversion to glaucoma, the frequency of testing used in OHTS (6 mo) was optimal for the detection of progression in high-risk patients. Low-risk patients could potentially be tested every 12 months to optimize resource utilization.

Risk Calculation in the Medication Arm of the Ocular Hypertension Treatment Study

Risk assessment is integral to the management of individuals with ocular hypertension (OHTN). This study aims to determine the predictive accuracy of the Ocular Hypertension Treatment Study 5-year risk calculator (OHTS calculator) among treated patients with OHTN by applying it to patients randomized to the Ocular Hypertension Treatment Study (OHTS) medication arm. Post hoc secondary analysis of a randomized clinical trial. Individuals participating in the OHTS who were randomized to the medication arm. Only participants with complete baseline data in both eyes were included (n=726). The hazard ratios (HRs) of the medication group in OHTS were compared to the HR used for the OHTS calculator using the z-test statistic to establish the OHTS calculator's generalizability to the OHTS medication arm. The performance of the OHTS calculator among the OHTS medication group was evaluated twice, using both untreated baseline intraocular pressure (IOP) and average treated IOP during the first 24 months for the IOP variable. The performance was determined based on the model's accuracy in estimating the risk of reaching an OHTS primary open-angle glaucoma (POAG) end point using calibration chi-square and discriminating between participants who did or did not develop POAG. The HRs for the OHTS medication arm were not significantly different from those used in the OHTS calculator for untreated OHTN derived from observation arm data (P>0.1). Based on the calibration chi-square test for the medication group, the OHTS calculator prediction model had good predictive accuracy when using the mean treated IOP and poorer predictive accuracy with the untreated baseline IOP (chi-square 10 and 29, respectively). The model had good discrimination with treated IOP (c-statistic=0.77), comparable to what has been reported for the OHTS calculator in the OHTS observation group. The OHTS calculator can be applied to treated patients with OHTN, and repeat risk calculation after initiating IOP reduction may provide useful information that can aid in disease management. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Retinal Nerve Fiber Layer Optical Texture Analysis: Detecting Axonal Fiber Bundle Defects in Patients with Ocular Hypertension

To apply retinal nerve fiber layer (RNFL) optical texture analysis (ROTA) to investigate the prevalence, patterns, and risk factors of RNFL defects in patients with ocular hypertension (OHT) who showed normal optic disc and RNFL configuration in clinical examination, normal RNFL thickness on OCT analysis, and normal visual field (VF) results. Cross-sectional study. Six hundred eyes of 306 patients with OHT. All participants underwent clinical examination of the optic disc and RNFL, OCT RNFL imaging, and 24-2 standard automated perimetry. To detect RNFL defects, ROTA was applied. The risk score for glaucoma development was calculated according to the Ocular Hypertension Treatment Study and European Glaucoma Prevention Study (OHTS-EGPS) risk prediction model. Risk factors associated with RNFL defects were analyzed using multilevel logistic regression analysis. Prevalence of RNFL defects. The average intraocular pressure (IOP) measured from 3 separate visits within 6 months was 24.9 ± 1.8 mmHg for the eye with higher IOP and 23.7 ± 1.7 mmHg for the eye with lower IOP; the respective central corneal thicknesses were 568.7 ± 30.8 μm and 568.8 ± 31.2 μm. Of 306 patients with OHT, 10.8% (33 patients, 37 eyes) demonstrated RNFL defects in ROTA in at least 1 eye. Of the 37 eyes with RNFL defects, the superior arcuate bundle was the most frequently involved (62.2%), followed by the superior papillomacular bundle (27.0%) and the inferior papillomacular bundle (21.6%). Papillofoveal bundle defects were observed in 10.8% of eyes. The smallest RNFL defect spanned 0.0° along Bruch's membrane opening margin, whereas the widest RNFL defect extended over 29.3°. Age (years) (odds ratio [OR], 1.08; 95% confidence interval [CI], 1.03-1.13), VF pattern standard deviation (decibels [dB]) (OR, 1.82; 95% CI, 1.01-3.29), cup volume (mm3) (OR, 1.24; 95% CI, 1.01-1.53), and the OHTS-EPGS risk score (OR, 1.04; 95% CI, 1.01-1.07) were associated with RNFL defects. A considerable proportion of patients with OHT who showed no signs of optic disc and RNFL thickness abnormalities on clinical and OCT examination exhibited RNFL defects on ROTA. Axonal fiber bundle defects on ROTA may represent the earliest discernible sign of glaucoma in the glaucoma continuum. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

The Patterns of Visual Field Defects in Primary Angle-Closure Glaucoma Compared to High-Tension Glaucoma and Normal-Tension Glaucoma

Introduction: The aim of this study was to compare the patterns of visual field (VF) defects in primary angle-closure glaucoma (PACG) to control groups of eyes with high-tension glaucoma (HTG) and normal-tension glaucoma (NTG). Methods: Forty-eight eyes with PACG were enrolled, and control eyes with HTG and NTG matched for age, sex, and mean deviation of VF defect were selected. VF tests were performed using the 24-2 program of the Humphrey field analyzer. VF defects were classified into six patterns with the Ocular Hypertension Treatment Study classification system and were categorized into three stages (early, moderate, and advanced). Each hemifield was divided into five regions according to the Glaucoma Hemifield Test (GHT). The mean total deviation (TD) of each GHT region was calculated. Results: Compared with HTG and NTG groups, the partial arcuate VF defects were more common in the PACG group. In the PACG group, the nasal GHT region in the inferior hemifield had the worst mean TD (−8.48 ± 8.62 dB), followed by the arcuate 1 (−7.81 ± 7.91 dB), arcuate 2 (−7.46 ± 7.43 dB), paracentral (−7.19 ± 7.98 dB), and central (−5.14 ± 6.24 dB) regions; the mean TD of the central region was significantly better than those for all other regions (all p Conclusion: Patterns of VF defect in PACG patients differ from those with HTG and NTG. This discrepancy might be due to the differences in the pathogenic mechanisms of glaucomatous optic neuropathy.

Primary Open-Angle Glaucoma Diagnosis from Optic Disc Photographs Using a Siamese Network.

Primary open-angle glaucoma (POAG) is one of the leading causes of irreversible blindness in the United States and worldwide. Although deep learning methods have been proposed to diagnose POAG, these methods all used a single image as input. Contrastingly, glaucoma specialists typically compare the follow-up image with the baseline image to diagnose incident glaucoma. To simulate this process, we proposed a Siamese neural network, POAGNet, to detect POAG from optic disc photographs. The POAGNet, an algorithm for glaucoma diagnosis, is developed using optic disc photographs. The POAGNet was trained and evaluated on 2 data sets: (1) 37 339 optic disc photographs from 1636 Ocular Hypertension Treatment Study (OHTS) participants and (2) 3684 optic disc photographs from the Sequential fundus Images for Glaucoma (SIG) data set. Gold standard labels were obtained using reading center grades. We proposed a Siamese network model, POAGNet, to simulate the clinical process of identifying POAG from optic disc photographs. The POAGNet consists of 2 side outputs for deep supervision and uses convolution to measure the similarity between 2 networks. The main outcome measures are the area under the receiver operating characteristiccurve, accuracy, sensitivity, and specificity. In POAG diagnosis, extensive experiments show that POAGNet performed better than the best state-of-the-art model on the OHTS test set (area under the curve [AUC] 0.9587 versus 0.8750). It also outperformed the baseline models on the SIG test set (AUC 0.7518 versus 0.6434). To assess the transferability of POAGNet, we also validated the impact of cross-data set variability on our model. The model trained on OHTS achieved an AUC of 0.7490 on SIG, comparable to the previous model trained on the same data set. When using the combination of SIG and OHTS for training, our model achieved superior AUC to the single-data model (AUC 0.8165 versus 0.7518). These demonstrate the relative generalizability of POAGNet. By simulating the clinical grading process, POAGNet demonstrated high accuracy in POAG diagnosis. These results highlight the potential of deep learning to assist and enhance clinical POAG diagnosis. The POAGNet is publicly available on https://github.com/bionlplab/poagnet.

Follow-up studies of the classical landmark studies in Glaucoma.

It was not until the nineteen nineties that there was scientific evidence for the primary treatment concept of glaucoma, lowering intraocular pressure. The treatment concept of lowering intraocular pressure is now proven by randomized controlled clinical trials (landmark studies). This review provides an overview of the follow-up studies to these landmark studies from the last 18 months. The 20-year data of the ocular hypertension treatment study showed a 49% incidence of primary open-angle glaucoma. The data of this landmark study was used for developing different machine learning algorithms. Bilateral disease, disc hemorrhages, and higher intraocular pressure (IOP) were risk factors for visual field deterioration in the United Kingdom Glaucoma Treatment Study. The Advanced Glaucoma Intervention Trial and the Collaborative Initial Glaucoma Treatment Study identified demographic factors, comorbidity, and clinical variables associated with visual field damage. Analysis was performed on Chinese subsets from the Laser in Glaucoma and Ocular Hypertension Study (LiGHT). Looking at all the follow-up studies to the tube shunt landmark studies, preoperative IOP, neovascular glaucoma, Ahmed implantation, and younger age were predictors of failure. A follow-up study to the Effectiveness in Angle-Closure Glaucoma in Lens Extraction Study showed that patients were ten times more likely to maintain a drop-free target IOP after lens extraction than after laser iridotomy. A superior location for iridotomy results in significantly more significant angle widening than temporal or nasal locations, as shown by a follow-up study to the Zhongshan Angle Closure Prevention Trial using OCT and gonioscopy. The number of published follow-up studies to the landmark studies in glaucoma show the ongoing development of clinical questions in management of glaucoma.

Potential for Collider Bias in Studies Examining the Association of Central Corneal Thickness With Glaucoma.

Central corneal thickness (CCT) may be biologically related to glaucoma or observed as associated with glaucoma simply due to its effect on intraocular pressure (IOP) measurement. We aimed to determine if the previously reported CCT-glaucoma associations, in which the analyses were adjusted for IOP or participants were selected on IOP, could be explained by collider bias. We simulated datasets mimicking a longitudinal population-based study (Los Angeles Latino Eye Study) and a trial (Ocular Hypertension Treatment Study) such that: (i) CCT was not truly associated with glaucoma, (ii) CCT and true IOP both contribute to measured IOP, and (iii) true IOP contributes to glaucoma risk. We then tested whether an association between CCT and glaucoma could be spuriously induced simply by adjusting for or selecting on measured IOP. A thinner CCT was significantly associated with higher glaucoma incidence in the simulated longitudinal population-based study when adjusted for measured IOP, but not crudely (unadjusted). A thinner CCT was crudely associated with glaucoma incidence in the simulated trial in which the participants were selected for high measured IOP. Effect sizes in the simulations were similar to those observed in the original studies. Our findings question whether CCT is biologically associated with glaucoma and suggest that current evidence may be due to collider bias. This indicates that CCT alone cannot be used as a factor to identify people at high risk of glaucoma in the general population. Using CCT in combination with IOP may be superior to using IOP alone.

Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization

To compare the diagnostic accuracy and explainability of a Vision Transformer deep learning technique, Data-efficient image Transformer (DeiT), and ResNet-50, trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG) and identify the salient areas of the photographs most important for each model's decision-making process. Evaluation of a diagnostic technology. Overall 66 715 photographs from 1636 OHTS participants and an additional 5 external datasets of 16 137 photographs of healthy and glaucoma eyes. Data-efficient image Transformer models were trained to detect 5 ground-truth OHTS POAG classifications: OHTS end point committee POAG determinations because of disc changes (model 1), visual field (VF) changes (model 2), or either disc or VF changes (model 3) and Reading Center determinations based on disc (model 4) and VFs (model 5). The best-performing DeiT models were compared with ResNet-50 models on OHTS and 5 external datasets. Diagnostic performance was compared using areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities. The explainability of the DeiT and ResNet-50 models was compared by evaluating the attention maps derived directly from DeiT to 3 gradient-weighted class activation map strategies. Compared with our best-performing ResNet-50 models, the DeiT models demonstrated similar performance on the OHTS test sets for all 5 ground-truth POAG labels; AUROC ranged from 0.82 (model 5) to 0.91 (model 1). Data-efficientimage Transformer AUROC was consistently higher than ResNet-50 on the 5 external datasets. For example, AUROC for the main OHTS end point (model 3) was between 0.08 and 0.20 higher in the DeiT than ResNet-50 models. The saliency maps from the DeiT highlight localized areas of the neuroretinal rim, suggesting important rim features for classification. The same maps in the ResNet-50 models show a more diffuse, generalized distribution around the optic disc. Vision Transformers have the potential to improve generalizability and explainability in deep learning models, detecting eye disease and possibly other medical conditions that rely on imaging for clinical diagnosis and management.

Automated diagnosing primary open-angle glaucoma from fundus image by simulating human’s grading with deep learning

Primary open-angle glaucoma (POAG) is a leading cause of irreversible blindness worldwide. Although deep learning methods have been proposed to diagnose POAG, it remains challenging to develop a robust and explainable algorithm to automatically facilitate the downstream diagnostic tasks. In this study, we present an automated classification algorithm, GlaucomaNet, to identify POAG using variable fundus photographs from different populations and settings. GlaucomaNet consists of two convolutional neural networks to simulate the human grading process: learning the discriminative features and fusing the features for grading. We evaluated GlaucomaNet on two datasets: Ocular Hypertension Treatment Study (OHTS) participants and the Large-scale Attention-based Glaucoma (LAG) dataset. GlaucomaNet achieved the highest AUC of 0.904 and 0.997 for POAG diagnosis on OHTS and LAG datasets. An ensemble of network architectures further improved diagnostic accuracy. By simulating the human grading process, GlaucomaNet demonstrated high accuracy with increased transparency in POAG diagnosis (comprehensiveness scores of 97% and 36%). These methods also address two well-known challenges in the field: the need for increased image data diversity and relying heavily on perimetry for POAG diagnosis. These results highlight the potential of deep learning to assist and enhance clinical POAG diagnosis. GlaucomaNet is publicly available on https://github.com/bionlplab/GlaucomaNet.

Comparing statistical methods in assessing the prognostic effect of biomarker variability on time-to-event clinical outcomes

BackgroundIn recent years there is increasing interest in modeling the effect of early longitudinal biomarker data on future time-to-event or other outcomes. Sometimes investigators are also interested in knowing whether the variability of biomarkers is independently predictive of clinical outcomes. This question in most applications is addressed via a two-stage approach where summary statistics such as variance are calculated in the first stage and then used in models as covariates to predict clinical outcome in the second stage. The objective of this study is to compare the relative performance of various methods in estimating the effect of biomarker variability.MethodsA joint model and 4 different two-stage approaches (naïve, landmark analysis, time-dependent Cox model, and regression calibration) were illustrated using data from a large multi-center randomized phase III trial, the Ocular Hypertension Treatment Study (OHTS), regarding the association between the variability of intraocular pressure (IOP) and the development of primary open-angle glaucoma (POAG). The model performance was also evaluated in terms of bias using simulated data from the joint model of longitudinal IOP and time to POAG. The parameters for simulation were chosen after OHTS data, and the association between longitudinal and survival data was introduced via underlying, unobserved, and error-free parameters including subject-specific variance.ResultsIn the OHTS data, joint modeling and two-stage methods reached consistent conclusion that IOP variability showed no significant association with the risk of POAG. In the simulated data with no association between IOP variability and time-to-POAG, all the two-stage methods (except the naïve approach) provided a reliable estimation. When a moderate effect of IOP variability on POAG was imposed, all the two-stage methods underestimated the true association as compared with the joint modeling while the model-based two-stage method (regression calibration) resulted in the least bias.ConclusionRegression calibration and joint modelling are the preferred methods in assessing the effect of biomarker variability. Two-stage methods with sample-based measures should be used with caution unless there exists a relatively long series of longitudinal measurements and/or strong effect size (NCT00000125).

Machine-Identified Patterns of Visual Field Loss and an Association with Rapid Progression in the Ocular Hypertension Treatment Study

To identify patterns of visual field (VF) loss based on unsupervised machine learning and to identify patterns that are associated with rapid progression. Cross-sectional and longitudinal study. A total of 2231 abnormal VFs from 205 eyes of 176 Ocular Hypertension Treatment Study (OHTS) participants followed over approximately 16 years. Visual fields were assessed by an unsupervised deep archetypal analysis algorithm and an OHTS-certified VF reader to identify prevalent patterns of VF loss. Machine-identified patterns of glaucoma damage were compared against those patterns previously identified (expert-identified) in the OHTS in 2003. Based on the longitudinal VFs of each eye, VF loss patterns that were strongly associated with rapid glaucoma progression were identified. Machine-expert correspondence and type of patterns of VF loss associated with rapid progression. The average VF mean deviation (MD) at conversion to glaucoma was-2.7 decibels (dB) (standard deviation [SD]= 2.4 dB), whereas the average MD of the eyes at the last visit was-5.2 dB (SD= 5.5 dB). Fifty out of 205 eyes had MD rate of-1 dB/year or worse and were considered rapid progressors. Eighteen machine-identified patterns of VF loss were compared with expert-identified patterns, in which 13 patterns of VF loss were similar. The most prevalent expert-identified patterns included partial arcuate, paracentral, and nasal step defects, and the most prevalent machine-identified patterns included temporal wedge, partial arcuate, nasal step, and paracentral VF defects. One of the machine-identified patterns of VF loss predicted future rapid VF progression after adjustment for age, sex, and initial MD. An automated machine learning system can identify patterns of VF loss and could provide objective and reproducible nomenclature for characterizing early signs of visual defects and rapid progression in patients with glaucoma.

Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning

Automated deep learning (DL) analyses of fundus photographs potentially can reduce the cost and improve the efficiency of reading center assessment of end points in clinical trials. To investigate the diagnostic accuracy of DL algorithms trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG). In this diagnostic study, 1636 OHTS participants from 22 sites with a mean (range) follow-up of 10.7 (0-14.3) years. A total of 66 715 photographs from 3272 eyes were used to train and test a ResNet-50 model to detect the OHTS Endpoint Committee POAG determination based on optic disc (287 eyes, 3502 photographs) and/or visual field (198 eyes, 2300 visual fields) changes. Three independent test sets were used to evaluate the generalizability of the model. Areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities were calculated to compare model performance. Evaluation of false-positive rates was used to determine whether the DL model detected POAG before the OHTS Endpoint Committee POAG determination. A total of 1147 participants were included in the training set (661 [57.6%] female; mean age, 57.2 years; 95% CI, 56.6-57.8), 167 in the validation set (97 [58.1%] female; mean age, 57.1 years; 95% CI, 55.6-58.7), and 322 in the test set (173 [53.7%] female; mean age, 57.2 years; 95% CI, 56.1-58.2). The DL model achieved an AUROC of 0.88 (95% CI, 0.82-0.92) for the OHTS Endpoint Committee determination of optic disc or VF changes. For the OHTS end points based on optic disc changes or visual field changes, AUROCs were 0.91 (95% CI, 0.88-0.94) and 0.86 (95% CI, 0.76-0.93), respectively. False-positive rates (at 90% specificity) were higher in photographs of eyes that later developed POAG by disc or visual field (27.5% [56 of 204]) compared with eyes that did not develop POAG (11.4% [50 of 440]) during follow-up. The diagnostic accuracy of the DL model developed on the optic disc end point applied to 3 independent data sets was lower, with AUROCs ranging from 0.74 (95% CI, 0.70-0.77) to 0.79 (95% CI, 0.78-0.81). The model's high diagnostic accuracy using OHTS photographs suggests that DL has the potential to standardize and automate POAG determination for clinical trials and management. In addition, the higher false-positive rate in early photographs of eyes that later developed POAG suggests that DL models detected POAG in some eyes earlier than the OHTS Endpoint Committee, reflecting the OHTS design that emphasized a high specificity for POAG determination by requiring a clinically significant change from baseline.

Multi-scale Multi-structure Siamese Network (MMSNet) for Primary Open-Angle Glaucoma Prediction.

Primary open-angle glaucoma (POAG) is one of the leading causes of irreversible blindness in the United States and worldwide. POAG prediction before onset plays an important role in early treatment. Although deep learning methods have been proposed to predict POAG, these methods mainly focus on current status prediction. In addition, all these methods used a single image as input. On the other hand, glaucoma specialists determine a glaucomatous eye by comparing the follow-up optic nerve image with the baseline along with supplementary clinical data. To simulate this process, we proposed a Multi-scale Multi-structure Siamese Network (MMSNet) to predict future POAG event from fundus photographs. The MMSNet consists of two side-outputs for deep supervision and 2D blocks to utilize two-dimensional features to assist classification. The MMSNet network was trained and evaluated on a large dataset: 37,339 fundus photographs from 1,636 Ocular Hypertension Treatment Study (OHTS) participants. Extensive experiments show that MMSNet outperforms the state-of-the-art on two "POAG prediction before onset" tasks. Our AUC are 0.9312 and 0.9507, which are 0.2204 and 0.1490 higher than the state-of-the-art, respectively. In addition, an ablation study is performed to check the contribution of different components. These results highlight the potential of deep learning to assist and enhance the prediction of future POAG event. The proposed network will be publicly available on https://github.com/bionlplab/MMSNet.

Structure/function/treatment in glaucoma: progress over the last 10years

Since the 1990s several so-called landmark studies were carried out, which played an important role in the management of glaucoma patients due to their multicenter, randomized and masked structure. The Ocular Hypertension Treatment Study (OHTS) and the Collaborative Initial Treatment Glaucoma Study (CIGTS) and their follow-up studies are especially important in the conservative glaucoma management and in the evaluation of structure and function. The OHTS examined if lowering of the intraocular pressure (IOP) treatment reduces the progression from ocular hypertension to primary open angle glaucoma and what risk factors influence the progression. The CIGTS examined the progression of glaucoma in patients treated either with pharmacotherapy or with surgery. The recent studies, the United Kingdom Glaucoma Treatment Study (UKGTS) and Glaucoma Automated Test Evaluation (GATE) investigated the influence of treatment with latanoprost on the development of visual field defects and examination of different screening tests in glaucoma, respectively. The OHTS provided results that justify prophylactic treatment as well as watchful waiting. The results of CIGTS showed that under certain conditions surgical treatment of a newly discovered glaucoma can be recommended for moderate to advanced glaucoma. In the UKGTS treatment with latanoprost reduced the intraocular pressure and also the progression of visual field defects in beginning and moderate glaucoma damage. The GATE study found no clear-cut advantage of screening examinations, with cost effectiveness and without a substantial proportion of diagnoses being missed.