Tobias Elze

An Artificial Intelligence Approach to Detect Visual Field Progression in Glaucoma Based on Spatial Pattern Analysis.

The archetype method can inform clinicians of VF progression patterns.

Systemic and Ocular Determinants of Peripapillary Retinal Nerve Fiber Layer Thickness Measurements in the European Eye Epidemiology (E3) Population.

In addition to previously described determinants such as age and refraction, we found that systemic vascular and neurovascular diseases were associated with reduced pRNFLT.

Trends and Usage Patterns of Minimally Invasive Glaucoma Surgery in the United States: IRIS® Registry Analysis 2013-2018.

A significant increase in MIGS use occurred over the recent 6-year period, despite limited evidence of their long-term safety or effectiveness, highlighting the need for trials comparing safety and outcomes of novel MIGS versus traditional…

Sex-Specific Differences in Circumpapillary Retinal Nerve Fiber Layer Thickness.

Substantial sex effects on cRNFL thickness were found at 56.8% of all 768 circumpapillary locations, with specific patterns for different sectors.

Artificial Intelligence Classification of Central Visual Field Patterns in Glaucoma.

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

Characterization of Central Visual Field Loss in End-stage Glaucoma by Unsupervised Artificial Intelligence.

In this study, central VF loss in end-stage glaucoma was found to exhibit characteristic patterns that might be associated with different subtypes.

Reversal of Glaucoma Hemifield Test Results and Visual Field Features in Glaucoma.

Using VF features may predict the GHT results reversal to WNL after 2 consecutive ONL results.

Race and Ethnicity Differences in Disease Severity and Visual Field Progression Among Glaucoma Patients.

Black, Asian and Hispanic patients had greater baseline severity vs.

Agreement and Predictors of Discordance of 6 Visual Field Progression Algorithms.

This extremely large comparative series demonstrated that existing algorithms have limited agreement and that agreement varies with clinical parameters, including institution.

Monitoring Glaucomatous Functional Loss Using an Artificial Intelligence-Enabled Dashboard.

The AI-enabled glaucoma dashboard, developed using a large VF dataset containing a broad spectrum of visual deficit types, has the potential to provide clinicians with a user-friendly tool for determination of the severity of glaucomatous…

Effectiveness of Microinvasive Glaucoma Surgery in the United States: Intelligent Research in Sight Registry Analysis 2013-2019.

In current United States clinical practice, MIGS has substantially lower reoperation rates when performed with phacoemulsification, especially for ECP and goniotomy or canaloplasty.

An Artificial Intelligence Approach to Assess Spatial Patterns of Retinal Nerve Fiber Layer Thickness Maps in Glaucoma.

Using RPs improved the VF prediction compared with using sectoral RNFLTs.

Deep Ocular Phenotyping Across Primary Open-Angle Glaucoma Genetic Burden.

Results suggest that PRS identified a group of individuals at substantially higher risk for POAG.

Cohort Study of Race/Ethnicity and Incident Primary Open-Angle Glaucoma Characterized by Autonomously Determined Visual Field Loss Patterns.

Blacks, compared to non-Hispanic whites, had higher risks of POAG with early central and advanced VF loss.

Relationship Between Central Retinal Vessel Trunk Location and Visual Field Loss in Glaucoma.

CRVTL nasalization is significantly and exclusively correlated to central VF loss for all glaucoma severities independent of cpRNFLT, and thus might be a structural biomarker of central VF loss.

Associations between Optic Nerve Head-Related Anatomical Parameters and Refractive Error over the Full Range of Glaucoma Severity.

Our results suggest that SE should be considered when interpreting the OD and its circumpapillary region for diagnostic purposes.

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

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.

Comparison of Perimetric Outcomes from a Tablet Perimeter, Smart Visual Function Analyzer, and Humphrey Field Analyzer.

Although average MD values from the 2 novel devices suggest that they provide similar results to the HFA, point-by-point comparisons highlight notable deviations.

Predicting Global Test-Retest Variability of Visual Fields in Glaucoma.

Inclusion of archetype VF loss patterns and TD values based on first VF improved the prediction of the global test-retest variability than using traditional global VF indices alone.

Estimating the Severity of Visual Field Damage From Retinal Nerve Fiber Layer Thickness Measurements With Artificial Intelligence.

The proposed ANN model estimated MD from RNFL measurements better than multivariable linear regression model, random forest, support vector regressor, and 1-D CNN models.

Racial Disparities in Glaucoma Vision Outcomes and Eye Care Utilization: An IRIS Registry Analysis.

We found that significant disparities in US eye care exist with Black, Hispanic, and Native American patients having worse vision outcomes and less disease monitoring.

Effectiveness of Trabeculectomy and Tube Shunt with versus without Concurrent Phacoemulsification: Intelligent Research in Sight Registry Longitudinal Analysis.

Reoperation rates within the first 3 years after trabeculectomy and GDD with and without phacoemulsification were low.

Norms of Interocular Circumpapillary Retinal Nerve Fiber Layer Thickness Differences at 768 Retinal Locations.

We provide pointwise normative distributions of interocular cpRNFLT differences at an unprecedentedly high spatial resolution of 768 A-scans and reveal considerable location specific asymmetries as well as their associations with age and scanning radius differences…

The Interrelationship between Refractive Error, Blood Vessel Anatomy, and Glaucomatous Visual Field Loss.

BV locations outside the ONH are sufficiently stable over glaucoma severity to represent individual eye anatomy, and the IAA at 1.73 mm eccentricity is the optimal parameter to be considered for novel OCT RNFLT norms.

Artifact Correction in Retinal Nerve Fiber Layer Thickness Maps Using Deep Learning and Its Clinical Utility in Glaucoma.

Artifact correction for RNFLTs improves VF and progression prediction in glaucoma.

Characteristics of p.Gln368Ter Myocilin Variant and Influence of Polygenic Risk on Glaucoma Penetrance in the UK Biobank.

One in 4 individuals with the MYOC p.Gln368Ter mutation demonstrated evidence of glaucoma, a substantially higher penetrance than previously estimated, with 69% of cases undetected.

Baseline Age and Mean Deviation Affect the Rate of Glaucomatous Vision Loss.

Older age and worse MD at baseline are associated with more rapid VF progression in this large dataset.

Archetypal Analysis Reveals Quantifiable Patterns of Visual Field Loss in Optic Neuritis.

AA identifies and quantifies archetypal, ON-specific patterns of VF loss.

Development and Comparison of Machine Learning Algorithms to Determine Visual Field Progression.

MLCs showed a moderate to high level of accuracy, sensitivity, and specificity and were more balanced than conventional algorithms.

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

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.

Unsupervised Machine Learning Identifies Quantifiable Patterns of Visual Field Loss in Idiopathic Intracranial Hypertension.

Archetypal analysis identifies quantifiable, archetypal VF defects that resemble those commonly seen in IIH.

Treatment Patterns of Childhood Glaucoma in the United States: Analysis of IRISRegistry (Intelligent Research in Sight).

We found that 1 in 6 childhood glaucoma eyes underwent glaucoma-related procedures, and nearly all received antiglaucoma medications.

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

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.

Risk Factors for Glaucoma Diagnosis and Surgical Intervention following Pediatric Cataract Surgery in the IRIS® Registry.

Glaucoma following cataract surgery diagnosis in children in the IRIS Registry was associated with young age, aphakia, unilateral cataract, and Black race.

Risk Factors for Glaucoma Drainage Device Revision or Removal Using the IRIS Registry.

The size and scope of the IRIS Registry allows for detection of subtle associations between risk factors and GDD revision or removal surgery.

Variability and Power to Detect Progression of Different Visual Field Patterns.

Time to detect central VF progression was reduced with 10-2 MD compared with 24-2 and C24-2 MD in glaucoma eyes in this large dataset, in part because 10-2 tests had lower variability.

Participant Experience Using Novel Perimetry Tests to Monitor Glaucoma Progression.

Users reported a preference for novel VF devices. Overall participant experience using these devices was positive, supporting the feasibility of home monitoring of VFs from an experience perspective.

Deep Learning for Localized Detection of Optic Disc Hemorrhages.

An autonomous object detection model is superior to an image classification model for detecting disc hemorrhages, and performed comparably to 2 clinicians.

Normative Percentiles of Retinal Nerve Fiber Layer Thickness and Glaucomatous Visual Field Loss.

Our results challenge the assumption that normative percentiles from OCT machines improve prediction of glaucomatous visual field loss.

Archetypal Analysis Reveals Consistent Visual Field Patterns for Stimulus Sizes III and V in Glaucoma and NAION.

AA shows that size V VFs provide quantifiable patterns of loss similar to size III. This aids in comparing stimulus sizes for monitoring VF patterns in disease progression.

Comparison of Structural and Functional Features in Primary Angle Closure and Open Angle Glaucomas.

Patients with PACG had less structural damage than patients with POAG despite similar degrees of functional loss.

The Epidemiology and Risk Factors for the Progression of Sympathetic Ophthalmia in the United States: An IRIS Registry Analysis.

SO following trauma and ophthalmic procedure is potentially rarer than previously reported, as measured in this large ophthalmic medical record database.

Three-dimensional Neuroretinal Rim Thickness and Visual Fields in Glaucoma: A Broken-stick Model.

When neuroretinal rim tissue, characterized by MDB thickness in OCT, is below a third of the normal value, VF damage in the decibel scale becomes detectable.

Effectiveness of Angle-Based Minimally Invasive Glaucoma Surgery after Laser Trabeculoplasty: An Analysis of the IRIS® Registry (Intelligent Research in Sight).

Prior LTP may be associated with a higher chance of subsequent glaucoma surgery following ab-MIGS, either with or without concurrent phacoemulsification.

Inter-Eye Association of Visual Field Defects in Glaucoma and Its Clinical Utility.

VF patterns of the worse eye are predictive of VF defects in the better eye.

Accuracy of ICD-10 Glaucoma Codes in a Large Academic Practice.

Comparison of structure-function correlation among IMO visual function analyser and Humphrey field analyser.

The IMOvifa test took less time and resulted in slightly less severe defects than HFA. MS in all sectors was moderately to strongly correlated. Function-structure correlations were similar when using either perimeter.

Transformer-Based Deep Learning Prediction of 10-Degree Humphrey Visual Field Tests From 24-Degree Data.

The predicted 10-2 VF has the potential to improve glaucoma diagnosis.

Improving Visual Field Forecasting by Correcting for the Effects of Poor Visual Field Reliability.

Including all VFs in the trend estimation has more predictive power for future reliable VFs than excluding unreliable VFs. Correcting for VF reliability further improves model accuracy.

Structure-Function Mapping Using a Three-Dimensional Neuroretinal Rim Parameter Derived From Spectral Domain Optical Coherence Tomography Volume Scans.

Three-dimensional MDB neuroretinal rim thickness relates to visual function as strongly as the most commonly used SD-OCT parameter for glaucoma, two-dimensional peripapillary RNFL thickness.

Graft Failure After Pediatric Penetrating Keratoplasty in the United States.

Approximately half of children undergoing PK in the IRIS Registry experienced graft failure within 5 years of transplantation.

Geographic Distribution of Access to Glaucoma Surgery: An IRIS® Registry (Intelligent Research in Sight) Analysis.

Patients are more likely to receive most types of glaucoma surgeries in urban practice locations.

Association Between Cup-to-Disc Ratio and Structural and Functional Damage Parameters in Glaucoma: Insights From Multiparametric Modeling.

CDR is subject to ceiling effects for glaucoma-related outcomes and poor at discriminating early glaucomatous damage. CDR values should be interpreted with care, particularly in screening settings.

Complications After Pediatric Penetrating Keratoplasty: An IRIS Registry Study.

Infectious keratitis was the most common postoperative complication in children undergoing PK.

ChatGPT-Assisted Glaucoma Diagnosis: A Health-Equitable Multi-Ancestry Analysis Using Visual Field and Optical Coherence Tomography Data.

ChatGPT o1 Pro diagnosed glaucoma similarly to specialists using only VF and OCT data. The model performance was similar across ancestral groups and genetic predispositions to glaucoma.

Comparison of Glaucoma Surgery Incidence and Outcomes in Pseudoexfoliation and Primary Open-Angle Glaucoma: IRIS® Registry Analysis.

Patients with PXG were nearly twice as likely to undergo glaucoma surgery than those with POAG, even when the baseline characteristics were balanced, reflecting the more aggressive nature of PXG.

Causes and Treatments of Malignant Glaucoma in the United States: Analysis of IRIS® Registry.

More than half of the eyes with MG had a pre-existing glaucoma diagnosis.

Dual-Level Pattern Tree for Visual Field Improves Glaucoma Progression and Polygenic Risk Prediction.

Trunk-branch VF classifiers were superior to trunk-only characterizations for predicting functional progression and glaucoma PRS.

Factors Associated With Gonioscopy Coding Before Glaucoma Procedures in the IRISRegistry.

Preoperative gonioscopy use and/or coding is lower than expected, given current guidelines. Among glaucoma procedures, ab interno MIGS were associated with lower preoperative gonioscopy utilization.

The Impact of Myopia on Regional Visual Field Loss and Progression in Glaucoma.

Lower SE values are associated with worse paracentral VF loss. Worse myopia is associated with functional progression, even when excluding patients with high myopia.

Genetic Risk for Open-Angle Glaucoma Subtypes Is Associated with Specific Visual Field Defect Classes.

Higher POAG PRSs and NTG PRSs were associated with paracentral VF loss, whereas higher HTG GRS was linked to total VF loss, but not paracentral defects.

Impact of Demographics on Regional Visual Field Loss and Deterioration in Glaucoma.

Blacks and non-English speakers have more severe VF loss, with superior hemifield being more affected and faster VF worsening.

Reply.

Patterns of Retinal Nerve Fiber Layer Loss in Different Subtypes of Open Angle Glaucoma Using Spectral Domain Optical Coherence Tomography.

This study suggests that SD-OCT may be able to detect significant differences in patterns of RNFL thinning for different subtypes of OAG.