Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry

PURPOSE: To evaluate the sensitivity and specificity of machine learning classifiers (MLCs) for glaucoma diagnosis using Spectral Domain OCT (SD-OCT) and standard automated perimetry (SAP). METHODS: Observational cross-sectional study. Sixty two glaucoma patients and 48 healthy individuals were included. All patients underwent a complete ophthalmologic examination, achromatic standard automated perimetry (SAP) and retinal nerve fiber layer (RNFL) imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec Inc., Dublin, California). Receiver operating characteristic (ROC) curves were obtained for all SD-OCT parameters and global indices of SAP. Subsequently, the following MLCs were tested using parameters from the SD-OCT and SAP: Bagging (BAG), Naive-Bayes (NB), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Random Forest (RAN), Ensemble Selection (ENS), Classification Tree (CTREE), Ada Boost M1(ADA),Support Vector Machine Linear (SVML) and Support Vector Machine Gaussian (SVMG). Areas under the receiver operating characteristic curves (aROC) obtained for isolated SAP and OCT parameters were compared with MLCs using OCT+SAP data. RESULTS: Combining OCT and SAP data, MLCs' aROCs varied from 0.777(CTREE) to 0.946 (RAN).The best OCT+SAP aROC obtained with RAN (0.946) was significantly larger the best single OCT parameter (p<0.05), but was not significantly different from the aROC obtained with the best single SAP parameter (p=0.19). CONCLUSION: Machine learning classifiers trained on OCT and SAP data can successfully discriminate between healthy and glaucomatous eyes. The combination of OCT and SAP measurements improved the diagnostic accuracy compared with OCT data alone.

Estresse em pacientes com glaucoma primário de ângulo aberto

Glaucoma Primário de Ângulo Aberto (GPAA) é uma importante causa de cegueira no mundo. O presente trabalho teve como objetivo investigar: (1) presença e tipo de estresse; (2) relação do número de colírios e estresse; (3) percepção do glaucoma e tratamento. Um estudo transversal e quantitativo foi realizado com 102 pacientes do Ambulatório de Oftalmologia do HC-FMUSP, com roteiro temático e Inventário de Sintomas de Estresse de Lipp. A maioria dos pacientes apresentou estresse (65,7%) e não houve correlação entre estresse e número de colírios. "Tempo de tratamento", "dificuldades na vida diária" e "dificuldades em pingar o colírio" foram variáveis independentemente associadas ao estresse. Conclui-se que o estresse pode interferir negativamente no enfrentamento da doença em pacientes com GPAA.

Three-monthly intravitreal bevacizumab injections for neovascular age-related macular degeneration: short-term visual acuity results

PURPOSE. To evaluate the change in vision after 3 monthly consecutive intravitreal injections of 1.25 mg of bevacizumab for neovascular age-related macular degeneration (AMD). METHODS. A retrospective analysis of 35 eyes was performed. Visual acuity (VA) at initial visit and at each follow-up visit was compared. The injection of bevacizumab was performed at 30-day intervals and patients were observed for 5 months after the last injection. RESULTS. Of the 35 eyes, 9 had received previous treatment with photodynamic therapy with or without 4 mg of intravitreal triamcinolone. VA was measured in Snellen table and transformed into logMAR for statistical purposes. Mean age was 76.66 years (range, 49-90 years). There were 24(69%) women and 11(31%) men. Mean VA at the initial visit was 0.92 +/- 0.50. At month 1, mean VA was 0.84 +/- 0.51 and at month 2 was 0.74 +/- 0.51. At month 3, mean VA remained 0.74 +/- 0.49. Six and 8 months after the initial visit, VA was 0.79 +/- 0.49 and 0.77 +/- 0.50, respectively. The improvement in VA was statistically significant at month 2 and at the end of the follow-up (8 months) compared with the baseline VA. CONCLUSIONS. Three consecutive monthly injections of intravitreal bevacizumab to treat neovascular AMD is effective in improving VA in the short term. Longer prospective studies should be performed to confirm VA stability after the third injection. (Eur J Ophthalmol 2010; 20: 740-4)

Impact of Atypical Retardation Patterns on Detection of Glaucoma Progression using the GDx with Variable Corneal Compensation

PURPOSE: To evaluate the impact of atypical retardation patterns (ARP) on detection of progressive retinal nerve fiber layer (RNFL) loss using scanning laser polarimetry with variable corneal compensation (VCC). DESIGN: Observational cohort study. METHODS: The study included 377 eyes of 221 patients with a median follow-up of 4.0 years. Images were obtained annually with the GDx VCC (Carl Zeiss Med, itec Inc, Dublin, California, USA), along with optic disc stereophotographs and standard automated perimetry (SAP) visual fields. Progression was determined by the Guided Progression Analysis software for SAP and by masked assessment of stereophotographs by expert graders. The typical scan score (TSS) was used to quantify the presence of ARPs on GDx VCC images. Random coefficients models were used to evaluate the relationship between ARP and RNFL thickness measurements over time. RESULTS: Thirty-eight eyes (10%) showed progression over time on visual fields, stereophotographs, or both. Changes in TSS scores from baseline were significantly associated with changes in RNFL thickness measurements in both progressing and nonprogressing eyes. Each I unit increase in TSS score was associated with a 0.19-mu m decrease in RNFL thickness measurement (P < .001) over time. CONCLUSIONS: ARPs had a significant effect on detection of progressive RNFL loss with the GDx VCC. Eyes with large amounts of atypical patterns, great fluctuations on these patterns over time, or both may show changes in measurements that can appear falsely as glaucomatous progression or can mask true changes in the RNFL. (Am J Ophthalmol 2009;148:155-163. (C) 2009 by Elsevier Inc. All rights reserved.)

Risk Factors for Visual Field Progression in Treated Glaucoma

Objective: To determine intraocular pressure (IOP)-dependent and IOP-independent variables associated with visual field (VF) progression in treated glaucoma. Design: Retrospective cohort of the Glaucoma Progression Study. Methods: Consecutive, treated glaucoma patients with repeatable VF loss who had 8 or more VF examinations of either eye, using the Swedish Interactive Threshold Algorithm (24-2 SITA-Standard, Humphrey Field Analyzer II; Carl Zeiss Meditec, Inc, Dublin, California), during the period between January 1999 and September 2009 were included. Visual field progression was evaluated using automated pointwise linear regression. Evaluated data included age, sex, race, central corneal thickness, baseline VF mean deviation, mean follow-up IOP, peak IOP, IOP fluctuation, a detected disc hemorrhage, and presence of beta-zone parapapillary atrophy. Results: We selected 587 eyes of 587 patients (mean [SD] age, 64.9 [13.0] years). The mean (SD) number of VFs was 11.1 (3.0), spanning a mean (SD) of 6.4 (1.7) years. In the univariable model, older age (odds ratio [OR], 1.19 per decade; P = .01), baseline diagnosis of exfoliation syndrome (OR, 1.79; P = .01), decreased central corneal thickness (OR, 1.38 per 40 mu m thinner; P < .01), a detected disc hemorrhage (OR, 2.31; P < .01), presence of beta-zone parapapillary atrophy (OR, 2.17; P < .01), and all IOP parameters (mean follow-up, peak, and fluctuation; P < .01) were associated with increased risk of VF progression. In the multivariable model, peak IOP (OR, 1.13; P < .01), thinner central corneal thickness (OR, 1.45 per 40 mu m thinner; P < .01), a detected disc hemorrhage (OR, 2.59; P < .01), and presence of beta-zone parapapillary atrophy (OR, 2.38; P < .01) were associated with VF progression. Conclusions: IOP-dependent and IOP-independent risk factors affect disease progression in treated glaucoma. Peak IOP is a better predictor of progression than is IOP mean or fluctuation.

Effect of Disease Severity and Optic Disc Size on Diagnostic Accuracy of RTVue Spectral Domain Optical Coherence Tomograph in Glaucoma

PURPOSE. To evaluate the effect of disease severity and optic disc size on the diagnostic accuracies of optic nerve head (ONH), retinal nerve fiber layer (RNFL), and macular parameters with RTVue (Optovue, Fremont, CA) spectral domain optical coherence tomography (SDOCT) in glaucoma. METHODS. 110 eyes of 62 normal subjects and 193 eyes of 136 glaucoma patients from the Diagnostic Innovations in Glaucoma Study underwent ONH, RNFL, and macular imaging with RTVue. Severity of glaucoma was based on visual field index (VFI) values from standard automated perimetry. Optic disc size was based on disc area measurement using the Heidelberg Retina Tomograph II (Heidelberg Engineering, Dossenheim, Germany). Influence of disease severity and disc size on the diagnostic accuracy of RTVue was evaluated by receiver operating characteristic (ROC) and logistic regression models. RESULTS. Areas under ROC curve (AUC) of all scanning areas increased (P < 0.05) as disease severity increased. For a VFI value of 99%, indicating early damage, AUCs for rim area, average RNLI thickness, and ganglion cell complex-root mean square were 0.693, 0.799, and 0.779, respectively. For a VFI of 70%, indicating severe damage, corresponding AUCs were 0.828, 0.985, and 0.992, respectively. Optic disc size did not influence the AUCs of any of the SDOCT scanning protocols of RTVue (P > 0.05). Sensitivity of the rim area increased and specificity decreased in large optic discs. CONCLUSIONS. Diagnostic accuracies of RTVue scanning protocols for glaucoma were significantly influenced by disease severity. Sensitivity of the rim area increased in large optic discs at the expense of specificity. (Invest Ophthalmol Vis Sci. 2011;92:1290-1296) DOI:10.1167/iovs.10-5516

Comparison of Different Spectral Domain Optical Coherence Tomography Scanning Areas for Glaucoma Diagnosis

Purpose: To evaluate retinal nerve fiber layer (RNFL), optic nerve head (ONH), and macular thickness measurements for glaucoma detection using the RTVue spectral domain optical coherence tomograph. Design: Diagnostic, case-control study. Participants: One hundred forty eyes of 106 glaucoma patients and 74 eyes of 40 healthy subjects from the Diagnostic Innovations in Glaucoma Study (DIGS). Methods: All patients underwent ocular imaging with the commercially available RTVue. Optic nerve head, RNFL thickness, and macular thickness scans were obtained during the same visit. Receiver operating characteristic (ROC) curves and sensitivities at fixed specificities (80% and 95%) were calculated for each parameter. Main Outcome Measures: Areas under the ROC curves (AUC) and sensitivities at fixed specificities of 80% and 95%. Results: The AUC for the RNFL parameter with best performance, inferior quadrant thickness, was significantly higher than that of the best-performing ONH parameter, inferior rim area (0.884 vs 0.812, respectively; P = 0.04). There was no difference between ROC curve areas of the best RNFL thickness parameters and the best inner macular thickness measurement, ganglion cell complex root mean square (ROC curve area = 0.870). Conclusions: The RTVue RNFL and inner retinal macular thickness measurements had good ability to detect eyes with glaucomatous visual field loss and performed significantly better than ONH parameters.

Effect of Disease Severity on the Performance of Cirrus Spectral-Domain OCT for Glaucoma Diagnosis

PURPOSE. To evaluate the effect of disease severity on the diagnostic accuracy of the Cirrus Optical Coherence Tomograph (Cirrus HD-OCT; Carl Zeiss Meditec, Inc., Dublin, CA) for glaucoma detection. METHODS. One hundred thirty-five glaucomatous eyes of 99 patients and 79 normal eyes of 47 control subjects were recruited from the longitudinal Diagnostic Innovations in Glaucoma Study (DIGS). The severity of the disease was graded based on the visual field index (VFI) from standard automated perimetry. Imaging of the retinal nerve fiber layer (RNFL) was obtained using the optic disc cube protocol available on the Cirrus HD-OCT. Pooled receiver operating characteristic (ROC) curves were initially obtained for each parameter of the Cirrus HD-OCT. The effect of disease severity on diagnostic performance was evaluated by fitting an ROC regression model, with VFI used as a covariate, and calculating the area under the ROC curve (AUCs) for different levels of disease severity. RESULTS. The largest pooled AUCs were for average thickness (0.892), inferior quadrant thickness (0.881), and superior quadrant thickness (0.874). Disease severity had a significant influence on the detection of glaucoma. For the average RNFL thickness parameter, AUCs were 0.962, 0.932, 0.886, and 0.822 for VFIs of 70%, 80%, 90%, and 100%, respectively. CONCLUSIONS. Disease severity had a significant effect on the diagnostic performance of the Cirrus HD-OCT and thus should be considered when interpreting results from this device and when considering the potential applications of this instrument for diagnosing glaucoma in the various clinical settings. (Invest Ophthalmol Vis Sci. 2010;51:4104-4109) DOI:10.1167/iovs.094716

A Comparison of Rates of Change in Neuroretinal Rim Area and Retinal Nerve Fiber Layer Thickness in Progressive Glaucoma

PURPOSE. To evaluate and compare rates of change in neuro-retinal rim area (RA) and retinal nerve fiber layer thickness (RNFLT) measurements in glaucoma patients, those with suspected glaucoma, and normal subjects observed over time. METHODS. In this observational cohort study, patients recruited from two longitudinal studies (Diagnostic Innovations in Glaucoma Study-DIGS and African Descent and Evaluation Study-ADAGES) were observed with standard achromatic perimetry (SAP), optic disc stereophotographs, confocal scanning laser ophthalmoscopy (HRT-3; Heidelberg Engineering, Heidelberg, Germany), and scanning laser polarimetry (GDx-VCC; Carl Zeiss Meditec, Inc., Dublin, CA). Glaucoma progression was determined by the Guided Progression Analysis software for standard automated perimetry [SAP] and by masked assessment of serial optic disc stereophotographs by expert graders. Random-coefficients models were used to evaluate rates of change in average RNFLT and global RA measurements and their relationship with glaucoma progression. RESULTS. At baseline, 194 (31%) eyes were glaucomatous, 347 (55%) had suspected glaucoma, and 88 (14%) were normal. Forty-six (9%) eyes showed progression by SAP and/or stereophotographs, during an average follow-up of 3.3 (+/-0.7) years. The average rate of decline for RNFLT measurements was significantly higher in the progressing group than in the non-progressing group (-0.65 vs. -0.11 mu m/y, respectively; P < 0.001), whereas RA decline was not significantly different between these groups (-0.0058 vs. -0.0073 mm(2)/y, respectively; P = 0.727). The areas under the receiver operating characteristic (ROC) curves used to discriminate progressing versus nonprogressing eyes were 0.811 and 0.507 for the rates of change in the RNFLT and RA, respectively (P < 0.001). CONCLUSIONS. The ability to discriminate eyes with progressing glaucoma by SAP and/or stereophotographs from stable eyes was significantly greater for RNFLT than for RA measurements. (Invest Ophthalmol Vis Sci. 2010;51:3531-3539) DOI: 10.1167/iovs.09-4350

Agreement for Detecting Glaucoma Progression with the GDx Guided Progression Analysis, Automated Perimetry, and Optic Disc Photography

Purpose: To evaluate the ability of the GDx Variable Corneal Compensation (VCC) Guided Progression Analysis (GPA) software for detecting glaucomatous progression. Design: Observational cohort study. Participants: The study included 453 eyes from 252 individuals followed for an average of 46 +/- 14 months as part of the Diagnostic Innovations in Glaucoma Study. At baseline, 29% of the eyes were classified as glaucomatous, 67% of the eyes were classified as suspects, and 5% of the eyes were classified as healthy. Methods: Images were obtained annually with the GDx VCC and analyzed for progression using the Fast Mode of the GDx GPA software. Progression using conventional methods was determined by the GPA software for standard automated achromatic perimetry (SAP) and by masked assessment of optic disc stereophotographs by expert graders. Main Outcome Measures: Sensitivity, specificity, and likelihood ratios (LRs) for detection of glaucoma progression using the GDx GPA were calculated with SAP and optic disc stereophotographs used as reference standards. Agreement among the different methods was reported using the AC(1) coefficient. Results: Thirty-four of the 431 glaucoma and glaucoma suspect eyes (8%) showed progression by SAP or optic disc stereophotographs. The GDx GPA detected 17 of these eyes for a sensitivity of 50%. Fourteen eyes showed progression only by the GDx GPA with a specificity of 96%. Positive and negative LRs were 12.5 and 0.5, respectively. None of the healthy eyes showed progression by the GDx GPA, with a specificity of 100% in this group. Inter-method agreement (AC1 coefficient and 95% confidence intervals) for non-progressing and progressing eyes was 0.96 (0.94-0.97) and 0.44 (0.28-0.61), respectively. Conclusions: The GDx GPA detected glaucoma progression in a significant number of cases showing progression by conventional methods, with high specificity and high positive LRs. Estimates of the accuracy for detecting progression suggest that the GDx GPA could be used to complement clinical evaluation in the detection of longitudinal change in glaucoma. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references. Ophthalmology 2010; 117: 462-470 (C) 2010 by the American Academy of Ophthalmology.

Agreement between stress intraocular pressure and long-term intraocular pressure measurements in primary open angle glaucoma

The aim of this paper is to study the correlation between the intraocular pressure peaks and fluctuation detected during the water drinking test and the same parameters observed during long-term follow up. This prospective cohort study enrolled 22 eyes of 22 newly diagnosed primary open angle glaucoma patients. After an initial complete ophthalmological examination, patients were started on antiglaucoma medication and returned 4 weeks later to perform the water drinking test. Thereafter, patients were evaluated at least eight times within a period of 6-12 months. The intraocular pressure peaks and fluctuation detected during the water drinking stress test were compared with those observed during regular office visits. Spearman`s correlation coefficient and Bland-Altman Plots were used for statistical analysis. The mean age of participants was 54.3 +/- 8.2 years (+/- SD), 59% were women, and average mean deviation -10.2 +/- 4.5 dB. The mean follow-up period was 8.2 +/- 2.0 months. The average intraocular pressure peaks and fluctuation during the water drinking test were 20.0 +/- 2.9 mmHg and 40 +/- 10%, respectively, and 18.1 +/- 2.8 mmHg and 30 +/- 10% during follow up. Spearman`s correlation coefficients were significant and strong between the intraocular pressure peaks and fluctuation detected during the water drinking test and during the follow-up period (P < 0.001, rho = 0.76 and 0.82, respectively). There was good agreement between the variables. The intraocular pressure peaks and fluctuation detected during the water drinking test showed significant correlation and agreement with the pressures observed during follow-up visits. Stress tests could be used to estimate long-term intraocular pressure variation.

Comparison of HRT-3 glaucoma probability score and subjective stereophotograph assessment for prediction of progression in glaucoma

PURPOSE. To assess whether baseline Glaucoma Probability Score (GPS; HRT-3; Heidelberg Engineering, Dossenheim, Germany) results are predictive of progression in patients with suspected glaucoma. The GPS is a new feature of the confocal scanning laser ophthalmoscope that generates an operator-independent, three-dimensional model of the optic nerve head and gives a score for the probability that this model is consistent with glaucomatous damage. METHODS. The study included 223 patients with suspected glaucoma during an average follow-up of 63.3 months. Included subjects had a suspect optic disc appearance and/or elevated intraocular pressure, but normal visual fields. Conversion was defined as development of either repeatable abnormal visual fields or glaucomatous deterioration in the appearance of the optic disc during the study period. The association between baseline GPS and conversion was investigated by Cox regression models. RESULTS. Fifty-four (24.2%) eyes converted. In multivariate models, both higher values of GPS global and subjective stereophotograph assessment ( larger cup-disc ratio and glaucomatous grading) were predictive of conversion: adjusted hazard ratios (95% CI): 1.31 (1.15 - 1.50) per 0.1 higher global GPS, 1.34 (1.12 - 1.62) per 0.1 higher CDR, and 2.34 (1.22 - 4.47) for abnormal grading, respectively. No significant differences ( P > 0.05 for all comparisons) were found between the c-index values ( equivalent to area under ROC curve) for the multivariate models (0.732, 0.705, and 0.699, respectively). CONCLUSIONS. GPS values were predictive of conversion in our population of patients with suspected glaucoma. Further, they performed as well as subjective assessment of the optic disc. These results suggest that GPS could potentially replace stereophotograph as a tool for estimating the likelihood of conversion to glaucoma.

Graves` orbitopathy: frequency of ocular hypertension and glaucoma

Purpose To determine the relationship between ocular hypertension and glaucoma in patients with Graves` orbitopathy. Methods A total of 107 patients with a diagnosis of Graves` orbitopathy, followed at the Oculoplasty sector of the University Hospital, Medical School of Ribeirao Preto, were evaluated by applanation tonometry, computed visual campimetry (Humphrey 30-2, Full Threshold) and analysis and photographic documentation of the optic nerve. The patients considered to have the suspicion of glaucoma were re-evaluated 1 year later for diagnostic confirmation or exclusion. Results A 3.74% prevalence of ocular hypertension (four patients) and a 2.8% prevalence of glaucoma (three patients) was observed. When considering only patients older than 40 years, the prevalence of ocular hypertension was 5.4% (four patients) and the prevalence of glaucoma was 4.76% (three patients). Conclusion The present study did not reveal a statistically significant difference in the prevalence of ocular hypertension or glaucoma between patients with Graves` orbitopathy and the general population.

Glaucoma and Keratoprosthesis Surgery Role of Adjunctive Cyclophotocoagulation

Purpose: To evaluate the efficacy and safety of diode laser transscleral cyclophotocoagulation (DLTSC) to control intraocular pressure (IOP) in keratoprosthesis patients with uncontrolled glaucoma. Patients and Methods: Between 1993 and 2007, 18 eyes of 18 patients underwent DLTSC, either before (n = 3), during (n = I), or after (n = 14) keratoprosthesis surgery. Keratoprosthesis type 1 was used in 72%. All but one of these patients received an Ahmed Glaucoma Valve, either with or after the keratoprosthesis placement. Best-corrected visual acuity, IOP (assessed by digital palpation), number of medications, and complications were recorded preoperatively, at day 7, at 1, 3, and 6 months then every 6 months postoperatively. Results: Mean follow-tip was 26.6 +/- 19.6 months (mean +/- SD) and mean age was 50.1 +/- 15.6 years. Glaucoma was identified in 1 I eyes before keratoprosthesis surgery and in 7 eyes after. Mean postoperative IOP was significantly reduced at 6, 12, 24, 36, and 48 months after DLTSC. DLTSC was repeated in 6 eyes. At final visit, mean best-corrected visual acuity was not decreased and there were no statistically significant differences in the number of glaucoma medications. Two patients had complications after DLTSC: a conjunctival dehiscence and a fungal endophthalmitis. Conclusions: DLTSC has beneficial long-term effects in the control of IOP and can be considered in the management of keratoprosthesis patients with refractory glaucoma.

Corticosteroid-induced glaucoma in a child after a scleral reinforcement procedure

Corticoteroid-induced glaucoma can result from either topical or systemic corticosteroid use. Compared with adults, the corticosteroid response in children is less well known. The case is reported of a child who developed glaucoma after receiving topical corticosteroids following a scleral re-inforcement procedure. The raised intraocular pressure was controlled after cessation of the corticosteroids and with the use of antiglaucoma therapy. As many forms of cortico-steroids are widely used, children on corticosteroids should have regular intraocular pressure measurements as part of their management.