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

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 five 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. CONCLUSION: 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.

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

Purpose: To elucidate the impact of demographics, including gender, race, ethnicity, and preferred language, on regional visual field (VF) loss and progression in glaucoma. Methods: Multivariable linear mixed regressions were performed to determine the impact of race, ethnicity, and preferred language on regional VF loss with adjustment for age and gender. Regional VF loss was defined by pointwise total deviation values and VF loss patterns quantified by an unsupervised machine learning method termed archetypal analysis. All cross-sectional and longitudinal analyses were performed both without and with adjustment for VF mean deviation, which represented overall VF loss severity. P values were corrected for multiple comparisons. Results: All results mentioned had corrected P values less than 0.05. Asian and Black patients showed worse pointwise VF loss than White patients with superior hemifield more affected. Patients with a preferred language other than English demonstrated worse pointwise VF loss than patients with English as their preferred language. Longitudinal analyses revealed Black patients showed worse VF loss/year compared to White patients. Patients with a preferred language other than English demonstrated worse VF loss/year compared to patients preferring English. Conclusions: Blacks and non-English speakers have more severe VF loss, with superior hemifield being more affected and faster VF worsening. Translational Relevance: This study furthered our understanding of racial, ethnic, and socioeconomic disparities in glaucoma outcomes. Understanding the VF loss burden in different racial, ethnic, and socioeconomic groups may guide more effective glaucoma screening and community outreach efforts. This research could help reduce vision loss and improve quality of life in disproportionately affected populations by guiding public health efforts to promote glaucoma awareness and access to care.

Gap Analysis of Glaucoma Examination Concept Representations within Standard SNOMED Clinical Terms.

PURPOSE: Standardization of eye care data is important for clinical interoperability and research . We aimed to address gaps in the representations of glaucoma examination concepts within Systemized Nomenclature of Medicine - Clinical Terms (SNOMED-CT), the preferred terminology of the American Academy of Ophthalmology. DESIGN: Study of data elements. METHODS: Structured eye exam data fields from two electronic health records (EHR) systems (Epic Systems and Medisoft) were compared against existing SNOMED-CT codes for concepts representing glaucoma examination findings3. Glaucoma specialists from multiple institutions were surveyed to identify high-priority gaps in representation, which were discussed among the SNOMED International Eye Care Clinical Reference Group. Proposals for new codes to address the gaps were formulated and submitted for inclusion in SNOMED-CT. MAIN OUTCOME MEASURES: Gaps in SNOMED-CT glaucoma examination concept representations RESULTS: We identified several gaps in SNOMED-CT regarding glaucoma examination concepts. A survey of glaucoma specialists identified high-priority data elements within the categories of tonometry and gonioscopy. For tonometry, there was consensus that we need to define new codes related to maximum intraocular pressure (IOP) and target IOP, and to delineate all methods of measuring IOP. These new codes were proposed and successfully added to SNOMED-CT for future use. Regarding gonioscopy, the current terminology did not include the ability to denote the gonioscopic grading system used (e.g., Shaffer or Spaeth), degree of angle pigmentation, iris configuration (except for plateau iris), and iris approach. There was also no ability to specify eye laterality or angle quadrant for gonioscopic findings. We proposed a framework for representing gonioscopic findings as observable entities in SNOMED-CT. DISCUSSION: There are existing gaps in the standardized representation of findings related to tonometry and gonioscopy within SNOMED-CT. These are important areas for evaluating clinical outcomes and enabling secondary use of EHR data for glaucoma research. This international, multi-institutional collaborative process enabled identification of gaps, prioritization, and development of data standards to address these gaps. CONCLUSION: Addressing these gaps and augmenting SNOMED-CT coverage of glaucoma examination findings could enhance clinical documentation and future research efforts related to glaucoma.

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

Purpose: To predict 10-2 Humphrey visual fields (VFs) from 24-2 VFs and associated non-total deviation features using deep learning. Methods: We included 5189 reliable 24-2 and 10-2 VF pairs from 2236 patients, and 28,409 reliable pairs of macular OCT scans and 24-2 VF from 19,527 eyes of 11,560 patients. We developed a transformer-based deep learning model using 52 total deviation values and nine VF test features to predict 68 10-2 total deviation values. The mean absolute error, root mean square error, and the R2 were evaluation metrics. We further evaluated whether the predicted 10-2 VFs can improve the structure-function relationship between macular thinning and paracentral VF loss in glaucoma. Results: The average mean absolute error and R2 for 68 10-2 VF test points were 3.30 ± 0.52 dB and 0.70 ± 0.11, respectively. The accuracy was lower in the inferior temporal region. The model placed greater emphasis on 24-2 VF points near the central fixation point when predicting the 10-2 VFs. The inclusion of nine VF test features improved the mean absolute error and R2 up to 0.17 ± 0.06 dB and 0.01 ± 0.01, respectively. Age was the most important 24-2 VF test parameter for 10-2 VF prediction. The predicted 10-2 VFs achieved an improved structure-function relationship between macular thinning and paracentral VF loss, with the R2 at the central 4, 12, and 16 locations of 24-2 VFs increased by 0.04, 0.05 and 0.05, respectively (P < 0.001). Conclusions: The 10-2 VFs may be predicted from 24-2 data. Translational Relevance: The predicted 10-2 VF has the potential to improve glaucoma diagnosis.

Gender based disparities in Medicare physician reimbursement persist across years and specialty.

Introduction: The gender pay gap is wide in medicine but the extent of this disparity across specialties and over time have not been elucidated. Here we evaluate differences in Medicare reimbursement between men and women physicians over time and by specialty, controlling for physician and practice characteristics. Methods: The Centers for Medicare & Medicaid Services Payment Data was used to determine total reimbursements and number of services submitted by physicians practicing in the US between 2013 and 2019. Data from the American Community Survey (ACS) were used to determine average income, unemployment rates, poverty rates, income, and educational attainment levels by zip code for each physician's practice location. Results: Among the 3,831,504 physicians included in this analysis from 2013-2019, 2,712,545 (70.8%) were men and 1,118,859 (29.2%) were women. Overall, men received more in Medicare reimbursements ($58,815 ± $104,772 vs. $32,205 ± $60,556, p<0.001) and billed more services (864 ± 1,780 vs. 505 ± 1,007, p<0.001) compared to women. The median Medicare reimbursement for men decreased from 2013 to 2019 from $59,710 to $57,874, while the median Medicare reimbursement for women increased from $30,575 to $33,456. Men were reimbursed more than women across all specialties with the greatest disparity in procedure-heavy specialties. The specialties with the highest difference in median Medicare reimbursement between men and women were ophthalmology ($99,452), dermatology ($84,844), cardiology ($64,112), nephrology ($62,352), and pulmonary medicine ($47,399). In linear regression models controlling for calendar year, years of experience, total number of services, and ACS zip-code-level variables, men received a higher amount of Medicare reimbursement in all specialties, as compared to women (p<0.01 for all). The percentage of top earning men (range: 65.0%-99.5%) surpassed the proportion of men in each specialty (range: 46.1%-94.6%), except public health and preventive medicine. Conclusions and Relevance: Women physicians continue to receive lower total Medicare reimbursements than men physicians, particularly in procedure-heavy specialties. Lower clinical volume and fewer procedural services among women physicians partially contribute to the disparities in reimbursement.

Similar Risk of Kidney Failure among Patients with Blinding Diseases Who Receive Ranibizumab, Aflibercept, and Bevacizumab: An Observational Health Data Sciences and Informatics Network Study.

PURPOSE: To characterize the incidence of kidney failure associated with intravitreal anti-VEGF exposure; and compare the risk of kidney failure in patients treated with ranibizumab, aflibercept, or bevacizumab. DESIGN: Retrospective cohort study across 12 databases in the Observational Health Data Sciences and Informatics (OHDSI) network. SUBJECTS: Subjects aged ≥ 18 years with ≥ 3 monthly intravitreal anti-VEGF medications for a blinding disease (diabetic retinopathy, diabetic macular edema, exudative age-related macular degeneration, or retinal vein occlusion). METHODS: The standardized incidence proportions and rates of kidney failure while on treatment with anti-VEGF were calculated. For each comparison (e.g., aflibercept versus ranibizumab), patients from each group were matched 1:1 using propensity scores. Cox proportional hazards models were used to estimate the risk of kidney failure while on treatment. A random effects meta-analysis was performed to combine each database's hazard ratio (HR) estimate into a single network-wide estimate. MAIN OUTCOME MEASURES: Incidence of kidney failure while on anti-VEGF treatment, and time from cohort entry to kidney failure. RESULTS: Of the 6.1 million patients with blinding diseases, 37 189 who received ranibizumab, 39 447 aflibercept, and 163 611 bevacizumab were included; the total treatment exposure time was 161 724 person-years. The average standardized incidence proportion of kidney failure was 678 per 100 000 persons (range, 0-2389), and incidence rate 742 per 100 000 person-years (range, 0-2661). The meta-analysis HR of kidney failure comparing aflibercept with ranibizumab was 1.01 (95% confidence interval [CI], 0.70-1.47; P = 0.45), ranibizumab with bevacizumab 0.95 (95% CI, 0.68-1.32; P = 0.62), and aflibercept with bevacizumab 0.95 (95% CI, 0.65-1.39; P = 0.60). CONCLUSIONS: There was no substantially different relative risk of kidney failure between those who received ranibizumab, bevacizumab, or aflibercept. Practicing ophthalmologists and nephrologists should be aware of the risk of kidney failure among patients receiving intravitreal anti-VEGF medications and that there is little empirical evidence to preferentially choose among the specific intravitreal anti-VEGF agents. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Assessment of linear regression of peripapillary optical coherence tomography retinal nerve fiber layer measurements to forecast glacuoma trajectory.

Linear regression of optical coherence tomography measurements of peripapillary retinal nerve fiber layer thickness is often used to detect glaucoma progression and forecast future disease course. However, current measurement frequencies suggest that clinicians often apply linear regression to a relatively small number of measurements (e.g., less than a handful). In this study, we estimate the accuracy of linear regression in predicting the next reliable measurement of average retinal nerve fiber layer thickness using Zeiss Cirrus optical coherence tomography measurements of average retinal nerve fiber layer thickness from a sample of 6,471 eyes with glaucoma or glaucoma-suspect status. Linear regression is compared to two null models: no glaucoma worsening, and worsening due to aging. Linear regression on the first M ≥ 2 measurements was significantly worse at predicting a reliable M+1st measurement for 2 ≤ M ≤ 6. This range was reduced to 2 ≤ M ≤ 5 when retinal nerve fiber layer thickness measurements were first "corrected" for scan quality. Simulations based on measurement frequencies in our sample-on average 393 ± 190 days between consecutive measurements-show that linear regression outperforms both null models when M ≥ 5 and the goal is to forecast moderate (75th percentile) worsening, and when M ≥ 3 for rapid (90th percentile) worsening. If linear regression is used to assess disease trajectory with a small number of measurements over short time periods (e.g., 1-2 years), as is often the case in clinical practice, the number of optical coherence tomography examinations needs to be increased.

Impact of the Coronavirus Disease 2019 Pandemic on Surgical Volumes Among Fellowship-Trained Glaucoma Subspecialists.

PRCIS: The change in glaucoma surgical volumes due to the coronavirus disease 2019 pandemic was not uniform across procedure types and was unequal between rural and urban practice locations. PURPOSE: To quantify the impact of the coronavirus disease 2019 pandemic on surgical volumes performed by fellowship-trained glaucoma subspecialists. MATERIALS AND METHODS: This retrospective cohort analysis of the Centers for Medicare and Medicaid Services Medicare Public Use File extracted all glaucoma surgeries, including microinvasive glaucoma surgeries (MIGSs), trabeculectomy, goniotomy, lasers, and cataract surgery, performed by fellowship-trained glaucoma surgeons in rural and urban areas between 2016 and 2020. Predicted estimates of 2020 surgical volumes were created utilizing linear squares regression. Percentage change between predicted and observed 2020 surgical volume estimates was analyzed. Statistical significance was achieved at P <0.05. RESULTS: In 2020, fellowship-trained glaucoma surgeons operated mostly in urban areas (N = 810, 95%). A 29% and 31% decrease in predicted cataract surgery volumes in urban and rural areas, respectively, was observed. Glaucoma surgeries experienced a 36% decrease from predicted estimates (N = 56,781). MIGS experienced an 86% and 75% decrease in rural and urban areas, respectively. Trabeculectomy in rural areas experienced a 16% increase relative to predicted estimates while urban areas experienced a decrease of 3% ( P > 0.05). The number of goniotomies decreased by 10% more in rural areas than in urban areas (-22% and -12%, respectively). Laser procedures decreased by 8% more in urban areas than in rural areas (-18% and -10%, respectively). CONCLUSIONS: Among glaucoma-trained surgeons, glaucoma surgeries experienced a greater volume loss than cataract surgeries. In urban US areas, relative reductions in MIGS and goniotomy volumes in urban areas may have been compensated by greater laser and trabeculectomy volumes. Trabeculectomies in rural areas were the only group exceeding predicted estimates. Glaucoma subspecialists may utilize these findings when planning for future events and in overcoming any remaining unmet need in terms of glaucoma care.

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

PRCIS: Using a large data set, we showed structural and functional differences between primary angle closure glaucoma (PACG) and primary open angle glaucoma (POAG). Primary angle closure glaucoma has relative structural preservation and worse functional loss inferiorly. PURPOSE: To identify structural and functional differences in PACG and POAG. MATERIALS AND METHODS: In this large cross-sectional study, differences in structural and functional damage were assessed among patients with POAG and PACG with optical coherence tomography and reliable visual field testing. RESULTS: In all, 283 patients with PACG and 4110 patients with POAG were included. Despite similar mean deviation on visual fields (mean [SD] -7.73 [7.92] vs. -7.53 [6.90] dB, P =0.72), patients with PACG had thicker global retinal nerve fiber layer (RNFL), smaller cup volume, smaller cup-to-disc ratio, and larger rim area than POAG (77 [20] vs. 71 [14] µm, 0.32 [0.28] vs. 0.40 [0.29] mm 3 , 0.6 [0.2] vs. 0.7 [0.1], 1.07 [0.40] vs. 0.89 [0.30] mm 2 , P <0.001 for all), while patients with POAG had more pronounced inferior RNFL thinning (82 [24] vs. 95 [35] µm, P <0.001). In a multivariable analysis, hyperopia [odds ratio (OR): 1.24, confidence interval (CI): 1.13-1.37], smaller cup-to-disc ratio (OR: 0.69, CI: 0.61-0.78), thicker inferior RNFL (OR: 1.15, CI: 1.06-1.26) and worse mean deviation (OR: 0.95, CI: 0.92-0.98) were associated with PACG. Functionally, POAG was associated with superior paracentral loss and PACG with inferior field loss. After adjusting for average RNFL thickness, PACG was associated with more diffuse loss than POAG (total deviation differences 1.26-3.2 dB). CONCLUSIONS: Patients with PACG had less structural damage than patients with POAG despite similar degrees of functional loss. Regional differences in patterns of functional and structural loss between POAG and PACG may improve disease monitoring for these glaucoma subtypes.

Short-term Detection of Fast Progressors in Glaucoma: The Fast Progression Assessment through Clustered Evaluation (Fast-PACE) Study.

PURPOSE: To evaluate the performance of an intensive, clustered testing approach in identifying eyes with rapid glaucoma progression over 6 months in the Fast Progression Assessment through Clustered Evaluation (Fast-PACE) Study. DESIGN: Prospective cohort study. PARTICIPANTS: A total of 125 eyes from 65 primary open-angle glaucoma (POAG) subjects. METHODS: Subjects underwent 2 sets of 5 weekly visits (clusters) separated by an average of 6 months and then were followed with single visits every 6 months for an overall mean follow-up of 25 months (mean of 17 tests). Each visit consisted of testing with standard automated perimetry (SAP) 24-2 and 10-2, and spectral-domain OCT (SD-OCT). Progression was assessed using trend analyses of SAP mean deviation (MD) and retinal nerve fiber layer (RNFL) thickness. Generalized estimating equations were applied to adjust for correlations between eyes for confidence interval (CI) estimation and hypothesis testing. MAIN OUTCOME MEASURES: Diagnostic accuracy of the 6-month clustering period to identify progression detected during the overall follow-up. RESULTS: A total of 19 of 125 eyes (15%, CI, 9%-24%) progressed based on SAP 24-2 MD over the 6-month clustering period. A total of 14 eyes (11%, CI, 6%-20%) progressed on SAP 10-2 MD, and 16 eyes (13%, CI, 8%-21%) progressed by RNFL thickness, with 30 of 125 eyes (24%, CI, 16%-34%) progressing by function, structure, or both. Of the 35 eyes progressing during the overall follow-up, 25 had progressed during the 6-month clustering period, for a sensitivity of 71% (CI, 53%-85%). Of the 90 eyes that did not progress during the overall follow-up, 85 also did not progress during the 6-month period, for a specificity of 94% (CI, 88%-98%). Of the 14 eyes considered fast progressors by SAP 24-2, SAP 10-2, or SD-OCT during the overall follow-up, 13 were identified as progressing during the 6-month cluster period, for a sensitivity of 93% (CI, 66%-100%) for identifying fast progression with a specificity of 85% (CI, 77%-90%). CONCLUSIONS: Clustered testing in the Fast-PACE Study detected fast-progressing glaucoma eyes over 6 months. The methodology could be applied in clinical trials investigating interventions to slow glaucoma progression and may be of value for short-term assessment of high-risk subjects. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references in the Footnotes and Disclosures at the end of this article.

The Impact of Achieving Target Intraocular Pressure on Glaucomatous Retinal Nerve Fiber Layer Thinning in a Treated Clinical Population.

PURPOSE: To estimate the effect of being below and above the clinician-set target intraocular pressure (IOP) on rates of glaucomatous retinal nerve fiber layer (RNFL) thinning in a treated real-world clinical population. DESIGN: Retrospective cohort study. METHODS: A total of 3256 eyes (1923 patients) with ≥5 reliable optical coherence tomography scans and 1 baseline visual field test were included. Linear mixed-effects modeling estimated the effects of the primary independent variables (mean target difference [measured IOP - target IOP] and mean IOP, mm Hg) on the primary dependent variable (RNFL slope, µm/y) while accounting for additional confounding variables (age, biological sex, race, baseline RNFL, baseline pachymetry, and disease severity). A spline term accounted for differential effects when above (target difference >0 mm Hg) and below (target difference ≤0 mm Hg) target pressure. RESULTS: Eyes below and above target had significantly different mean RNFL slopes (-0.44 vs -0.71 µm/y, P < .001). Each 1 mm Hg increase above target had a 0.143 µm/y faster rate of RNFL thinning (P < .001). Separating by disease severity, suspect, mild, moderate, and advanced glaucoma had 0.135 (P = .002), 0.116 (P = .009), 0.203 (P = .02), and 0.65 (P = .22) µm/y faster rates of RNFL thinning per 1 mm Hg increase, respectively. CONCLUSIONS: Being above the clinician-set target pressure is associated with more rapid RNFL thinning in suspect, mild, and moderate glaucoma. Faster rates of thinning were also present in advanced glaucoma, but statistical significance was limited by the lower sample size of eyes above target and the optical coherence tomography floor effect.

Advancing Toward a Common Data Model in Ophthalmology: Gap Analysis of General Eye Examination Concepts to Standard Observational Medical Outcomes Partnership (OMOP) Concepts.

Purpose: Evaluate the degree of concept coverage of the general eye examination in one widely used electronic health record (EHR) system using the Observational Health Data Sciences and Informatics Observational Medical Outcomes Partnership (OMOP) common data model (CDM). Design: Study of data elements. Participants: Not applicable. Methods: Data elements (field names and predefined entry values) from the general eye examination in the Epic foundation system were mapped to OMOP concepts and analyzed. Each mapping was given a Health Level 7 equivalence designation-equal when the OMOP concept had the same meaning as the source EHR concept, wider when it was missing information, narrower when it was overly specific, and unmatched when there was no match. Initial mappings were reviewed by 2 graders. Intergrader agreement for equivalence designation was calculated using Cohen's kappa. Agreement on the mapped OMOP concept was calculated as a percentage of total mappable concepts. Discrepancies were discussed and a final consensus created. Quantitative analysis was performed on wider and unmatched concepts. Main Outcome Measures: Gaps in OMOP concept coverage of EHR elements and intergrader agreement of mapped OMOP concepts. Results: A total of 698 data elements (210 fields, 488 values) from the EHR were analyzed. The intergrader kappa on the equivalence designation was 0.88 (standard error 0.03, P < 0.001). There was a 96% agreement on the mapped OMOP concept. In the final consensus mapping, 25% (1% fields, 31% values) of the EHR to OMOP concept mappings were considered equal, 50% (27% fields, 60% values) wider, 4% (8% fields, 2% values) narrower, and 21% (52% fields, 8% values) unmatched. Of the wider mapped elements, 46% were missing the laterality specification, 24% had other missing attributes, and 30% had both issues. Wider and unmatched EHR elements could be found in all areas of the general eye examination. Conclusions: Most data elements in the general eye examination could not be represented precisely using the OMOP CDM. Our work suggests multiple ways to improve the incorporation of important ophthalmology concepts in OMOP, including adding laterality to existing concepts. There exists a strong need to improve the coverage of ophthalmic concepts in source vocabularies so that the OMOP CDM can better accommodate vision research. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Identifying factors associated with fast visual field progression in patients with ocular hypertension based on unsupervised machine learning.

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 five 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, Stables, Slow progressors, and Fast progressors based on their mean of MD decline, 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 calcium channel blockers, being male, heart disease history, diabetes history, African American race, stroke history, and migraine headaches. Conclusion: 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, diabetes, and history of more using calcium channel blockers. Fast progressors were more from African American race and 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.

Comparing Ahmed-FP7 to Baerveldt-250 and Baerveldt-350 surgical outcomes: 1-year results from a retrospective cohort study leveraging the electronic health record.

OBJECTIVE: To compare outcomes following Ahmed-FP7 (AGI-FP7), Baerveldt-250mm2 (BGI-250), or Baerveldt-350mm2 (BGI-350) implantation. METHODS AND ANALYSIS: Retrospective cohort study comprising 800 eyes from 800 individuals who underwent surgery 1 January 2016-31 December 2020 at a tertiary-care institution. Data were extracted from standardised fields in the electronic health record. Primary outcome was failure (defined as intraocular pressure (IOP) ≤5 mm Hg or >18 mm Hg or reduction <20% at two consecutive visits from month 3 onwards; or visual acuity (VA) loss ≥3 lines; or return to the operating room (OR)). Secondary outcomes were IOP, VA, number of follow-up visits and return to the OR. RESULTS: A total of 523 AGI-FP7, 133 BGI-250 and 144 BGI-350 cases were analysed. The AGI-FP7 group was more likely to be younger and diagnosed with secondary glaucoma, with a higher mean baseline IOP (28.5±12.2 vs 22.0±7.7 mm Hg in BGI-250 and 23.4±9.0 in BGI-350, p<0.001). Cumulative failure rate at month 12 was 30% (AGI-FP7) vs 39% (BGI-250) vs 33% (BGI-350, p=0.159). Mean IOP at month 12 was lower in the BGI-350 group compared with AGI-FP7 (12.4±4.4 vs 14.8±5.6 mm Hg, p=0.003) but not BGI-250 (vs 13.1±4.6, p=0.710). Target IOP was achieved in 71% of AGI-FP7, 66% BGI-250, and 76% BGI-350. VA loss and rates of return to the OR did not differ between groups. Both BGI-250 and BGI-350 had more follow-up visits than AGI-FP7 (p<0.001). CONCLUSION: These three glaucoma drainage devices performed similarly within 1 year, with no difference in failure rates despite differing baseline patient characteristics.

Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images in Glaucoma.

Ophthalmic images, along with their derivatives like retinal nerve fiber layer (RNFL) thickness maps, play a crucial role in detecting and monitoring eye diseases such as glaucoma. For computer-aided diagnosis of eye diseases, the key technique is to automatically extract meaningful features from ophthalmic images that can reveal the biomarkers (e.g., RNFL thinning patterns) associated with functional vision loss. However, representation learning from ophthalmic images that links structural retinal damage with human vision loss is non-trivial mostly due to large anatomical variations between patients. This challenge is further amplified by the presence of image artifacts, commonly resulting from image acquisition and automated segmentation issues. In this paper, we present an artifact-tolerant unsupervised learning framework called EyeLearn for learning ophthalmic image representations in glaucoma cases. EyeLearn includes an artifact correction module to learn representations that optimally predict artifact-free images. In addition, EyeLearn adopts a clustering-guided contrastive learning strategy to explicitly capture the affinities within and between images. During training, images are dynamically organized into clusters to form contrastive samples, which encourage learning similar or dissimilar representations for images in the same or different clusters, respectively. To evaluate EyeLearn, we use the learned representations for visual field prediction and glaucoma detection with a real-world dataset of glaucoma patient ophthalmic images. Extensive experiments and comparisons with state-of-the-art methods confirm the effectiveness of EyeLearn in learning optimal feature representations from ophthalmic images.

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.

Low Vision Rehabilitation Service Utilization Before and After Implementation of a Clinical Decision Support System in Ophthalmology.

Importance: Electronic clinical decision support systems apply clinical guidelines in real time and offer a new approach to improve referral and utilization of low vision rehabilitation (LVR) care. Objective: To characterize patients and factors associated with LVR service utilization with and without the use of an electronic health record (EHR) clinical decision support system (CDSS) alert. Design, Setting, and Participants: Quality improvement study using EHR data to compare patients who did and did not utilize LVR service after referral between November 6, 2017, and October 5, 2019, (primary) and to assess overall service utilization rate from September 1, 2016, to April 2, 2021, regardless of referral status (secondary). Participants in the primary analysis were patients at a large ophthalmology department in an academic medical center in the US who received an LVR referral recommendation from their ophthalmologist according to the CDSS alert. The secondary analysis included patients with best documented visual acuity (BDVA) worse than 20/40 before, during, and after the CDSS implementation. Data were analyzed from August 2021 to April 2022. Exposures: Number and locations of referral recommendations for LVR service according to the CDSS alert in the primary analysis; active CDSS implementation in the secondary analysis. Main Outcomes and Measures: LVR service utilization rate was defined as the number of patients who accessed service among those who were referred (primary) and among those with BDVA worse than 20/40 (secondary). EHR data on patient demographics (age, sex, race, ethnicity) and ophthalmology encounter characteristics (numbers of referral recommendations, encounter location, and BDVA) were extracted. Results: Of the 429 patients (median [IQR] age, 71 [53 to 83] years; 233 female [54%]) who received a CDSS-based referral recommendation, 184 (42.9%) utilized LVR service. Compared with nonusers of LVR, users were more likely to have received at least 2 referral recommendations (12.5% vs 6.1%; χ21 = 5.29; P = .02) and at an ophthalmology location with onsite LVR service (87.5% vs 78.0%; χ21 = 6.50; P = .01). Onsite LVR service (odds ratio, 2.06; 95% CI, 1.18-3.61) persisted as the only statistically significant factor after adjusting for patient demographics and other referral characteristics. Among patients whose BDVA was worse than 20/40 before, during, and after the CDSS implementation regardless of referral status, the LVR service utilization rate was 6.1%, 13.8%, and 7.5%, respectively. Conclusions and Relevance: In this quality improvement study, ophthalmologist referral recommendations and onsite LVR services at the location where patients receive other ophthalmic care were significantly associated with service utilization. Ophthalmology CDSSs are promising tools to apply clinical guidelines in real time to improve connection to care.