Prediction of Glaucoma Progression with Structural Parameters: Comparison of Optical Coherence Tomography and Clinical Disc Parameters

GRAPE: A multi-modal dataset of longitudinal follow-up visual field and fundus images for glaucoma management

As one of the leading causes of irreversible blindness worldwide, glaucoma is characterized by structural damage and functional loss. Glaucoma patients often have a long follow-up and prognosis prediction is an important part in treatment. However, existing public glaucoma datasets are almost cross-sectional, concentrating on segmentation on optic disc (OD) and glaucoma diagnosis. With the development of artificial intelligence (AI), the deep learning model can already provide accurate prediction of future visual field (VF) and its progression with the support of longitudinal datasets. Here, we proposed a public longitudinal glaucoma real-world appraisal progression ensemble (GRAPE) dataset. The GRAPE dataset contains 1115 follow-up records from 263 eyes, with VFs, fundus images, OCT measurements and clinical information, and OD segmentation and VF progression are annotated. Two baseline models demonstrated the feasibility in prediction of VF and its progression. This dataset will advance AI research in glaucoma management.

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.

Combining Optical Coherence Tomography and Optical Coherence Tomography Angiography Longitudinal Data for the Detection of Visual Field Progression in Glaucoma

PURPOSE

To use longitudinal optical coherence tomography (OCT) and OCT angiography (OCTA) data to detect glaucomatous visual field (VF) progression with a supervised machine learning approach.

DESIGN

Prospective cohort study.

METHODS

One hundred ten eyes of patients with suspected glaucoma (33.6%) and patients with glaucoma (66.4%) with a minimum of 5 24-2 VF tests and 3 optic nerve head and macula images over an average follow-up duration of 4.1 years were included. VF progression was defined using a composite measure including either a "likely progression event" on Guided Progression Analysis, a statistically significant negative slope of VF mean deviation or VF index, or a positive pointwise linear regression event. Feature-based gradient boosting classifiers were developed using different subsets of baseline and longitudinal OCT and OCTA summary parameters. The area under the receiver operating characteristic curve (AUROC) was used to compare the classification performance of different models.

RESULTS

VF progression was detected in 28 eyes (25.5%). The model with combined baseline and longitudinal OCT and OCTA parameters at the global and hemifield levels had the best classification accuracy to detect VF progression (AUROC = 0.89). Models including combined OCT and OCTA parameters had higher classification accuracy compared with those with individual subsets of OCT or OCTA features alone. Including hemifield measurements significantly improved the models' classification accuracy compared with using global measurements alone. Including longitudinal rates of change of OCT and OCTA parameters (AUROCs = 0.80-0.89) considerably increased the classification accuracy of the models with baseline measurements alone (AUROCs = 0.60-0.63).

CONCLUSIONS

Longitudinal OCTA measurements complement OCT-derived structural metrics for the evaluation of functional VF loss in patients with glaucoma.

Decrease Retinal Thickness in Patients with Chronic Migraine Evaluated by Optical Coherence Tomography

The purpose of this study is to determine the possible alterations that may occur in the thickness of the retinal nerve fibre layer (RNFL), ganglion cell layer (GCL), and macular thickness in patients with chronic migraines compared with healthy controls. Hence, we examined some of the possibilities that are offered by optical coherence tomography (OCT) in order to study different neurological diseases and to study its application, in this case, how it may be applied to patients with chronic migraines. This was an observational cross-sectional study in adults aged 18-65 years. The study group consisted of 90 patients (90 eyes) with chronic migraines who met the inclusion criteria, and 90 healthy controls (90 eyes) matched for age and sex. Retinal thickness was measured by spectral domain OCT (SD-OCT). The thickness of the superior quadrant of the peripapillary RNFL, as well as the mean thickness in the macula, RNFL macular, and GCL was significantly thinner in chronic migraine patients than in healthy controls (p ≤ 0.05). Chronic migraines are associated with a decrease in retinal thickness which is detectable by an OCT diagnostic technique. The quantification of the axonal damage could be used as a biomarker to help in the diagnosis and monitoring of this pathology. Further studies will be needed to confirm these findings.

Predictors for elevation of Intraocular Pressure (IOP) on glaucoma patients; a retrospective cohort study design

OBJECTIVE

Because of the increase in the number of cases, currently, glaucoma is a significant public health issue that it leads to optic nerve damage and vision loss. High Intraocular Pressure reading indicates that the treatment given to a glaucoma patient is not sufficient/ adequate. Hence, the elevation of intraocular pressure is one of the indicators that, the therapy given to glaucoma patients under treatment is inadequate. Therefore, the main objective of the current study was to investigate predictors for the variation of elevation of IOP readings on glaucoma patients.

MATERIALS AND METHODS

A retrospective cohort study design was conducted on 1254 glaucoma patients, whose followed-ups were from September 2015 to August 2016 at Felege Hiwot Teaching and Specialized Hospital, North West Ethiopia. Data analysis was conducted using Statistical Analysis of Systems (SAS) software version 9.2 and AMOS software. The parameter estimation was conducted using the maximum likelihood estimation technique.

RESULTS

Main effects like age (β = 0.01, t-value = 0.15, p-value = 0.018), patients with normal blood pressure (β = -3.35, t-value = -2.28, p-value = 0.0263), patients without diabetics (β = -3.79, t-value = -2.47, p-value = 0.014), visiting times (β = -6.00, t-value = -5.02, p-value = 0.0001), farmer glaucoma patients (β = -6.04, t-value = 3.87, p-value = 0.0001) had significant and indirect effect for the variation of elevation of IOP on glaucoma patients. Interaction effects like visiting time with existence of diabetes, visiting time with cataract surgery significantly effected on the variable of interest. Hence, both main and interaction effects had significant effects on the variable of interest. This study had identified socio-demographic characteristics, personal/individual behaviors, and clinical factors for the variation of elevation of IOP. The findings, in the current investigation, help health staff to conduct health-related education for awareness creation. Health-related education, about the progression of glaucoma, should be conducted on patients.

A deep-learning system predicts glaucoma incidence and progression using retinal photographs

BackgroundDeep learning has been widely used for glaucoma diagnosis. However, there is no clinically validated algorithm for glaucoma incidence and progression prediction. This study aims to develop a clinically feasible deep-learning system for predicting and stratifying the risk of glaucoma onset and progression based on color fundus photographs (CFPs), with clinical validation of performance in external population cohorts.MethodsWe established data sets of CFPs and visual fields collected from longitudinal cohorts. The mean follow-up duration was 3 to 5 years across the data sets. Artificial intelligence (AI) models were developed to predict future glaucoma incidence and progression based on the CFPs of 17,497 eyes in 9346 patients. The area under the receiver operating characteristic (AUROC) curve, sensitivity, and specificity of the AI models were calculated with reference to the labels provided by experienced ophthalmologists. Incidence and progression of glaucoma were determined based on longitudinal CFP images or visual fields, respectively.ResultsThe AI model to predict glaucoma incidence achieved an AUROC of 0.90 (0.81-0.99) in the validation set and demonstrated good generalizability, with AUROCs of 0.89 (0.83-0.95) and 0.88 (0.79-0.97) in external test sets 1 and 2, respectively. The AI model to predict glaucoma progression achieved an AUROC of 0.91 (0.88-0.94) in the validation set, and also demonstrated outstanding predictive performance with AUROCs of 0.87 (0.81-0.92) and 0.88 (0.83-0.94) in external test sets 1 and 2, respectively.ConclusionOur study demonstrates the feasibility of deep-learning algorithms in the early detection and prediction of glaucoma progression.FUNDINGNational Natural Science Foundation of China (NSFC); the High-level Hospital Construction Project, Zhongshan Ophthalmic Center, Sun Yat-sen University; the Science and Technology Program of Guangzhou, China (2021), the Science and Technology Development Fund (FDCT) of Macau, and FDCT-NSFC.

Longitudinal Changes in Peripapillary Retinal Nerve Fiber Layer and Macular Ganglion Cell Inner Plexiform Layer in Progressive Myopia and Glaucoma Among Adolescents

Purpose

This study aimed to investigate the differences in longitudinal changes in the peripapillary retinal nerve fiber layer (pRNFL) and macular ganglion cell plus inner plexiform layer (GCIPL) caused by progressive myopia and glaucoma among adolescents.

Design

This was a retrospective observational study.

Methods

A total of forty-seven and 25 eyes of 47 and 25 adolescents with myopia progression (MP) and glaucoma progression (GP), respectively, who were followed up at the Zhongshan Ophthalmic Center for at least 3 years, were included in the study. The pRNFL and GCIPL that measured at the initial and last visits were analyzed.

Results

The median follow-up period was 5 years for both two groups. During follow-up, the whole, superior, and inferior pRNFL decreased in both the MP and GP groups, (p < 0.001). Nasal pRNFL decreased in the MP group (p < 0.001) but had no significant difference in the GP group (p = 0.19). Temporal pRNFL was increased in the MP group (p < 0.001) but decreased in the GP group (p < 0.001). The average and sectoral GCIPL decreased in both groups (p < 0.001). The annual change rate of temporal pRNFL and pRNFL at 10-, 8-, 9-, and 7-clock-hour sectors and the inferotemporal GCIPL has better diagnostic value to differentiate glaucoma from myopia (the area under the receiver operating characteristic curve, AUC > 0.85).

Conclusion

Glaucoma and MP could cause loss of the pRNFL and GCIPL in adolescents; however, the loss patterns were different between the two groups. The temporal quadrant and 7-, 8-, 9-, and 10-clock-hour sector pRNFL and the inferotemporal GCIPL can help distinguish pRNFL and GCIPL loss caused by glaucoma or MP.

Risk factors for undergoing surgery in patients with newly diagnosed open-angle glaucoma

Despite the clinical importance of glaucoma surgery, studies on its prevalence and risk factors are limited. We analyzed a database comprising approximately 1,000,000 Korean residents to investigate the prevalence and risk factors for undergoing glaucoma surgery within 5 years of diagnosis with open-angle glaucoma. Of the 4,303 patients evaluated, 226 (5.3%) underwent glaucoma surgery. Factors associated with the likelihood of glaucoma surgery included the use of two or more eye drops (odds ratio [OR], 30.30; 95% confidence interval [CI], 10.95–83.84), intake of oral carbonic anhydrase inhibitor (OR, 1.79; 95% CI, 1.23–2.61), age > 55 years (55–65 years: OR, 1.71; 95% CI, 1.06–2.76; > 65 years: OR 1.72; 95% CI, 1.10–2.70), female sex (OR, 1.46; 95% CI, 1.10–1.94), middle- and high-income (OR, 2.36; 95% CI, 1.30–4.28, OR, 1.86; 95% CI, 1.03–3.35, respectively), and metropolitan residence (OR, 1.61; 95% CI, 1.14–2.26). Our nomogram for predicting the likelihood of glaucoma surgery showed an acceptable result. In conclusion, older age, female sex, and the intensity of intraocular pressure lowering treatment increased the likelihood of undergoing glaucoma surgery. Our findings indicated that a lower socioeconomic status may forestall receiving this necessary surgery, which requires further attention.

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.

Association of foveal avascular zone area withstructural and functional progression in glaucoma patients

BACKGROUND

To investigate whether quantitative optical coherence tomography angiography (OCTA) metrics of the superficial/deep macular retina and optic disc are associated with glaucoma progression risk.

METHODS

A total of 238 eyes from 119 patients with open angle glaucoma or ocular hypertension, and no history of systemic hypertension or diabetes mellitus were included. All participants underwent OCTA imaging with a swept-source OCT (DRI-OCT 1, Topcon, Japan). OCTA metrics of superficial capillary plexus (SCP) and deep capillary plexus (DCP) in the macular region, and radial peripapillary capillary network of the optic disc were measured by a customised MATLAB program to obtain foveal avascular zone (FAZ) area, FAZ circularity and capillary density of SCP/DCP, and capillary density of the peripapillary region. Relationships between baseline OCTA metrics, visual field (VF) metrics, intraocular pressure fluctuation and risk of glaucoma progression were analysed with the Cox proportional hazards model. A frailty model was used to adjust for intereye correlation.

RESULTS

During a mean follow-up duration of 29.39 months (range 12-56 months), 50, 48 and 16 eyes were determined to have retinal nerve fibre layer (RNFL), ganglion cell-inner plexiform layer (GC-IPL) and VF progression respectively. FAZ area per SD increase at baseline were significantly associated with both RNFL thinning (HR 1.73 95% CI 1.04 to 2.90); p=0.036) and GC-IPL thinning (HR 2.62, 95% CI 1.59 to 4.31; p<0.001), after adjusting for age, axial length and other potential confounding factors. VF progression was associated with age (HR 1.05, 95% CI 1.02 to 1.08; p<0.001) and mean deviation value (HR 0.91, 95% CI 0.84 to 0.98; p=0.010), but not with any OCTA metrics.

CONCLUSION

Enlarged FAZ area measured by OCTA was associated with a higher risk of RNFL and GC-IPL thinning associated with glaucoma, but not with functional deterioration in glaucoma.

Detection of Neurological and Ophthalmological Pathologies with Optical Coherence Tomography Using Retinal Thickness Measurements: A Bibliometric Study

We carry out a bibliometric analysis on neurological and ophthalmological pathologies based on retinal nerve fiber layer (RNFL) thickness measured with optical coherence tomography (OCT). Documents were selected from Scopus database. We have applied the most commonly used bibliometric indicators, both for production and dispersion, as Price’s law of scientific literature growth, Lotka’s law, the transient index, and the Bradford model. Finally, the participation index of the different countries and affiliations was calculated. Two-hundred-and-forty-one documents from the period 2000–2019 were retrieved. Scientific production was better adjusted to linear growth (r = 0.88) than exponential (r = 0.87). The duplication time of the documents obtained was 5.6 years. The transience index was 89.62%, which indicates that most of the scientific production is due to very few authors. The signature rate per document was 5.2. Nine journals made up the Bradford core. USA and University of California present the highest production. The most frequently discussed topics on RNFL thinning are glaucoma and neurodegenerative diseases (NDD). The growth of the scientific literature on RNFL thickness was linear, with a very high rate of transience, which indicates low productivity and the presence of numerous authors who sporadically publish on this topic. No evidence of a saturation point was observed. In the last 10 years, there has been an increase in documents relating the decline of RNFL to NDD.

Macular imaging with optical coherence tomography in glaucoma

With the advent of spectral-domain optical coherence tomography, imaging of the posterior segment of the eye can be carried out rapidly at multiple anatomical locations, including the optic nerve head, circumpapillary retinal nerve fiber layer, and macula. There is now ample evidence to support the role of spectral-domain optical coherence tomography imaging of the macula for detection of early glaucoma. Macular spectral-domain optical coherence tomography measurements demonstrate high reproducibility, and evidence on its utility for detection of glaucoma progression is accumulating. We present a comprehensive review of macular spectral-domain optical coherence tomography imaging emerging as an essential diagnostic tool in glaucoma.