Identifying the severity of diabetic retinopathy by visual function measures using both traditional statistical methods and interpretable machine learning: a cross-sectional study.

AIMS/HYPOTHESIS: To determine the extent to which diabetic retinopathy severity stage may be classified using machine learning (ML) and commonly used clinical measures of visual function together with age and sex. METHODS: We measured the visual function of 1901 eyes from 1032 participants in the Northern Ireland Sensory Ageing Study, deriving 12 variables from nine visual function tests. Missing values were imputed using chained equations. Participants were divided into four groups using clinical measures and grading of ophthalmic images: no diabetes mellitus (no DM), diabetes but no diabetic retinopathy (DM no DR), diabetic retinopathy without diabetic macular oedema (DR no DMO) and diabetic retinopathy with DMO (DR with DMO). Ensemble ML models were fitted to classify group membership for three tasks, distinguishing (A) the DM no DR group from the no DM group; (B) the DR no DMO group from the DM no DR group; and (C) the DR with DMO group from the DR no DMO group. More conventional multiple logistic regression models were also fitted for comparison. An interpretable ML technique was used to rank the contribution of visual function variables to predictions and to disentangle associations between diabetic eye disease and visual function from artefacts of the data collection process. RESULTS: The performance of the ensemble ML models was good across all three classification tasks, with accuracies of 0.92, 1.00 and 0.84, respectively, for tasks A-C, substantially exceeding the accuracies for logistic regression (0.84, 0.61 and 0.80, respectively). Reading index was highly ranked for tasks A and B, whereas near visual acuity and Moorfields chart acuity were important for task C. Microperimetry variables ranked highly for all three tasks, but this was partly due to a data artefact (a large proportion of missing values). CONCLUSIONS/INTERPRETATION: Ensemble ML models predicted status of diabetic eye disease with high accuracy using just age, sex and measures of visual function. Interpretable ML methods enabled us to identify profiles of visual function associated with different stages of diabetic eye disease, and to disentangle associations from artefacts of the data collection process. Together, these two techniques have great potential for developing prediction models using untidy real-world clinical data.

Smartphone-based remote monitoring of vision in macular disease enables early detection of worsening pathology and need for intravitreal therapy.

BACKGROUND/AIMS: To assess the outcomes of home monitoring of distortion caused by macular diseases using a smartphone-based application (app), and to examine them with hospital-based assessments of visual acuity (VA), optical coherence tomography-derived central macular thickness (CMT) and the requirement of intravitreal injection therapy. DESIGN: Observational study with retrospective analysis of data. METHODS: Participants were trained in the correct use of the app (Alleye, Oculocare, Zurich, Switzerland) in person or by using video and telephone consultations. Automated threshold-based alerts were communicated based on a traffic light system. A 'threshold alarm' was defined as three consecutive 'red' scores, and turned into a 'persistent alarm' if present for greater than a 7-day period. Changes of VA and CMT, and the requirement for intravitreal therapy after an alarm were examined. RESULTS: 245 patients performing a total of 11 592 tests (mean 46.9 tests per user) were included and 85 eyes (164 alarms) examined. Mean drop in VA from baseline was -4.23 letters (95% CI: -6.24 to -2.22; p<0.001) and mean increase in CMT was 29.5 µm (95% CI: -0.08 to 59.13; p=0.051). Sixty-six eyes (78.5%) producing alarms either had a drop in VA, increase in CMT or both and 60.0% received an injection. Eyes with persistent alarms had a greater loss of VA, -4.79 letters (95% CI: -6.73 to -2.85; p<0.001) or greater increase in CMT, +87.8 µm (95% CI: 5.2 to 170.4; p=0.038). CONCLUSION: Smartphone-based self-tests for macular disease may serve as reliable indicators for the worsening of pathology and the need for treatment.

Evidence for Structural and Functional Damage of the Inner Retina in Diabetes With No Diabetic Retinopathy.

Purpose: To provide structural and functional evidence of inner retinal loss in diabetes prior to vascular changes and interpret the structure-function relationship in the context of an established neural model. Methods: Data from one eye of 505 participants (134 with diabetes and no clinically evident vascular alterations of the retina) were included in this analysis. The data were collected as part of a large population-based study. Functional tests included best-corrected visual acuity, Pelli-Robson contrast sensitivity, mesopic microperimetry, and frequency doubling technology perimetry (FDT). Macular optical coherence tomography volume scans were collected for all participants. To interpret the structure-function relationship in the context of a neural model, ganglion cell layer (GCL) thickness was converted to local ganglion cell (GC) counts. Results: The GCL and inner plexiform layer were significantly thinner in participants with diabetes (P < 0.05), with no significant differences in the macular retinal nerve fiber layer or the outer retina. All functional tests except microperimetry showed a significant loss in diabetic patients (P < 0.05). Both FDT and microperimetry showed a significant relationship with the GC count (P < 0.05), consistent with predictions from a neural model for partial summation conditions. However, the FDT captured additional significant damage (P = 0.03) unexplained by the structural loss. Conclusions: Functional and structural measurements support early neuronal loss in diabetes. The structure-function relationship follows the predictions from an established neural model. Functional tests could be improved to operate in total summation conditions in the macula, becoming more sensitive to early loss.

Quantitative Parameters from OCT Angiography in Patients with Diabetic Retinopathy and in Those with Only Peripheral Retinopathy Compared with Control Participants.

Purpose: To describe the differences in a range of quantitative OCT angiography (OCTA) metrics across early stages of diabetic retinopathy (DR), providing robust effect estimates as well as sensitivity and specificity. Design: Cross-sectional study with population-based sampling. Participants: Four hundred forty-one eyes from 296 individuals: 328 control eyes (no diabetes mellitus [DM] and no DR), 55 eyes with DM and no DR, and 58 eyes with early nonproliferative DR. Methods: Multimodal retinal imaging included color fundus photography, color Optomap ultra-widefield imaging, and spectral-domain OCT (Spectralis OCT2; Heidelberg Engineering GmbH) with the OCTA module. All images were graded for the presence and severity of DR features. OCTA images were assessed manually for inclusion based on quality. Binary OCTA metrics were assessed after 3-dimensional projection artifact removal including from the nerve fiber layer vascular plexus, superficial vascular plexus (SVC), and deep vascular plexus (DVC) by Early Treatment Diabetic Retinopathy Study (ETDRS) grid, foveal avascular zone (FAZ) area, FAZ minimum and maximum diameter, perimeter length, and circularity. Main Outcome Measures: Diabetes mellitus and DR status and presence or absence of DR in the retinal periphery. Results: The reduction in vessel densities in participants with DM and manifest DR compared with control participants tended to be twice that of those with DM, but no DR, compared with control participants. Some evidence of spatial heterogeneity in vessel reductions was found in those yet to develop DR, whereas those with manifest DR had significant reductions across the ETDRS grid. The FAZ perimeter and circularity were impacted most significantly by DM, and those with DR showed decreased multispectral fractal dimensions compared with control participants. Eyes with peripheral DR had reduced vessel density compared with those with DM and no DR only in the superior outer, temporal inner, and temporal outer regions in the DVC and SVC. The area under the receiver operating characteristic curve ranged between 0.48 and 0.73. Conclusions: Significant differences in OCTA metrics can be found in those with DM before manifest DR using commercially available equipment with minimal image postprocessing. Although diagnostic performance was poor, these metrics may be useful for measuring change over time in clinical trials.

Combined Multimodal Analysis of Peripheral Retinal and Macular Circulation in Diabetic Retinopathy (COPRA Study).

PURPOSE: To systematically examine the relationships between the microvascular indices that are measured on OCT angiography (OCTA) and the presence and extent of peripheral nonperfusion in persons with diabetic retinopathy. DESIGN: A retrospective cross-sectional study of patients who had varying degrees of diabetic retinopathy. The study sample was recruited from 2 large tertiary referral retina clinics. PARTICIPANTS: In total, 82 eyes of 45 patients with varying degrees of diabetic retinopathy were enrolled and analyzed. MAIN OUTCOME MEASURES: Relationships between peripheral ischemia measured on fluorescein angiography (FA) and OCTA metrics, including foveal avascular zone (FAZ) and vessel density measurements. RESULTS: A significant decrease in mean signal index in both the superficial and deep plexus and binarized flow index in the superficial plexus were found with increasing duration of diabetes mellitus. OCT and OCTA grading showed increasing central macular thickness and prevalence of microvascular abnormalities in the superficial and deep capillary bed with worse retinopathy as measured on the Diabetic Retinopathy Severity Scale. FAZ area and major axis and minor axis length were strongly associated with diabetic retinopathy severity. On classifying eyes into tertiles of peripheral ischemia measured on FA, significant increases in various FAZ metrics, including FAZ area and minor axis length, were noted. Statistically worsening of FAZ OCTA metrics was only seen between tertiles 2 and 3, indicating a non-linear relationship. The presence of neovascularization of the disc, neovascularization elsewhere, or intraretinal microvascular abnormality was associated with a significant increase in FAZ major axis length in the superficial plexus and a significant decrease in binarized flow index in the deep plexus. CONCLUSIONS: OCTA metrics are indicators of the severity of peripheral retinal nonperfusion. However, the central ischemic index did not exhibit a linear relationship with peripheral capillary nonperfusion. Our findings suggest that a rise in intraocular vascular endothelial growth factor as a consequence of mild peripheral capillary nonperfusion may play a compensatory role in maintaining the central macular microcirculation. Further investigations with studies employing longitudinal design will improve our understanding of the relationship between macular microcirculation and peripheral ischemia.

Disorganization of Inner Retina and Outer Retinal Morphology in Diabetic Macular Edema.

Importance: In diabetic macular edema (DME), identification of baseline markers on spectral-domain optical coherence tomography (SD-OCT) and their association with severity of diabetic retinopathy (DR) might aid in disease management and the design of future trials. Objective: To examine associations between DR severity, retinal morphology on SD-OCT, and visual acuity in participants with DME. Design, Setting, and Participants: This cross-sectional observational case series was conducted at a single tertiary care referral center. Demographics, visual acuity, SD-OCT, and color fundus photographs of 80 individuals with DME (102 eyes) seen between December 28, 2013, and April 30, 2014, were analyzed between May 1 and July 31, 2016. Main Outcomes and Measures: Features captured on SD-OCT and thickness metrics. On SD-OCT we graded type and shape of DME, shape and presence of septae within the intraretinal cystoid abnormalities, presence of hyperreflective dots and foci, integrity of the external limiting membrane and ellipsoid zone, presence and extent of disorganization of the inner retinal layers (DRIL), and the status of the vitreomacular interface and epiretinal membrane. We measured retinal thickness at the fovea and at the site of maximum pathology, choroidal thickness at the fovea, and 1000 µm temporal and nasal to the fovea. Color photographs were graded to derive a DR severity stage. Results: The mean (SD) age was 63 (11) years, and 30 participants (37.5%) were women. The odds of having DRIL were greater in eyes with disrupted external limiting membrane (odds ratio [OR], 4.4; 95% CI, 1.6-12.0; P = .003), disrupted ellipsoid zone (OR, 2.7; 95% CI, 1.0-7.2; P = .03), presence of epiretinal membrane (OR, 2.8; 95% CI, 1.0-7.4; P = .03), and increase in retinal thickness at the fovea (OR, 1.6; 95% CI, 1.1-2.2; P < .001). Occurrence of DRIL was more likely in eyes with proliferative DR (OR, 7.3; 95% CI, 1.7-31.4; P = .007). Mean visual acuity decreased by approximately 4.7 letters for each 100-µm increase in the average global DRIL (95% CI, -7.9 to 1.4; P = .006). Conclusions and Relevance: An association was found between DRIL and disruption of the outer retina and increasing DR severity. Further longitudinal studies seem warranted to determine whether DRIL is a clinically relevant noninvasive morphological marker in eyes with DME.

Dyslipidemia and Diabetic Macular Edema: A Systematic Review and Meta-Analysis.

TOPIC: A systematic review and meta-analysis of dyslipidemia and diabetic macular edema (DME). CLINICAL RELEVANCE: Diabetic macular edema causes impairment of vision in patients with diabetes, and dyslipidemia has been reported as a risk factor for its development. A systematic review with a meta-analysis was undertaken to examine the evidence of an association between dyslipidemia and DME. METHODS: We defined eligibility criteria as randomized controlled trials (RCTs) and cohort, case-control, and cross-sectional studies reporting on the relationship between blood lipid levels and DME. We performed a literature search in MEDLINE, PubMed, and Embase from inception to September 2014. We used the Newcastle-Ottawa scale to assess the quality of case-control, cross-sectional, and cohort studies, and the Cochrane risk of bias tool for RCTs. RESULTS: The search strategy identified 4959 publications. After screening, we selected 21 articles for review (5 cross-sectional, 5 cohort, 7 case-control, and 4 RCTs). Meta-analysis of case-control studies revealed that mean levels of total serum cholesterol (TC), low-density lipoproteins (LDLs), and serum triglycerides (TGs) were significantly higher in patients with DME compared with those without DME (TC: 30.08; 95% confidence interval [CI], 21.14-39.02; P < 0.001; LDL: 18.62; 95% CI, 5.80-31.43; P < 0.05; TG: 24.82; 95% CI, 9.21-40.42; P < 0.05). Meta-analysis of RCTs did not show significant risk in worsening of hard exudates and severity of DME in the lipid-lowering group compared with placebo (hard exudates: relative risk, 1.00; 95% CI, 0.47-2.11; P = 1.00; DME: relative risk, 1.18; 95% CI, 0.75-1.86; P = 0.48). CONCLUSIONS: Despite evidence from the cohort studies and meta-analysis of the case-control studies suggesting a strong relationship between lipid levels and DME, this was not confirmed by the meta-analysis that included only prospective RCTs. Therefore, given the significant public health relevance of the topic, the relationship between lipid levels and DME deserves further investigation.

Optical coherence tomography (OCT) for detection of macular oedema in patients with diabetic retinopathy.

BACKGROUND: Diabetic macular oedema (DMO) is a thickening of the central retina, or the macula, and is associated with long-term visual loss in people with diabetic retinopathy (DR). Clinically significant macular oedema (CSMO) is the most severe form of DMO. Almost 30 years ago, the Early Treatment Diabetic Retinopathy Study (ETDRS) found that CSMO, diagnosed by means of stereoscopic fundus photography, leads to moderate visual loss in one of four people within three years. It also showed that grid or focal laser photocoagulation to the macula halves this risk. Recently, intravitreal injection of antiangiogenic drugs has also been used to try to improve vision in people with macular oedema due to DR.Optical coherence tomography (OCT) is based on optical reflectivity and is able to image retinal thickness and structure producing cross-sectional and three-dimensional images of the central retina. It is widely used because it provides objective and quantitative assessment of macular oedema, unlike the subjectivity of fundus biomicroscopic assessment which is routinely used by ophthalmologists instead of photography. Optical coherence tomography is also used for quantitative follow-up of the effects of treatment of CSMO. OBJECTIVES: To determine the diagnostic accuracy of OCT for detecting DMO and CSMO, defined according to ETDRS in 1985, in patients referred to ophthalmologists after DR is detected. In the update of this review we also aimed to assess whether OCT might be considered the new reference standard for detecting DMO. SEARCH METHODS: We searched the Cochrane Database of Systematic Reviews (CDSR), the Database of Abstracts of Reviews of Effects (DARE), the Health Technology Assessment Database (HTA) and the NHS Economic Evaluation Database (NHSEED) (The Cochrane Library 2013, Issue 5), Ovid MEDLINE, Ovid MEDLINE In-Process and Other Non-Indexed Citations, Ovid MEDLINE Daily, Ovid OLDMEDLINE (January 1946 to June 2013), EMBASE (January 1950 to June 2013), Web of Science Conference Proceedings Citation Index - Science (CPCI-S) (January 1990 to June 2013), BIOSIS Previews (January 1969 to June 2013), MEDION and the Aggressive Research Intelligence Facility database (ARIF). We did not use any date or language restrictions in the electronic searches for trials. We last searched the electronic databases on 25 June 2013. We checked bibliographies of relevant studies for additional references. SELECTION CRITERIA: We selected studies that assessed the diagnostic accuracy of any OCT model for detecting DMO or CSMO in patients with DR who were referred to eye clinics. Diabetic macular oedema and CSMO were diagnosed by means of fundus biomicroscopy by ophthalmologists or stereophotography by ophthalmologists or other trained personnel. DATA COLLECTION AND ANALYSIS: Three authors independently extracted data on study characteristics and measures of accuracy. We assessed data using random-effects hierarchical sROC meta-analysis models. MAIN RESULTS: We included 10 studies (830 participants, 1387 eyes), published between 1998 and 2012. Prevalence of CSMO was 19% to 65% (median 50%) in nine studies with CSMO as the target condition. Study quality was often unclear or at high risk of bias for QUADAS 2 items, specifically regarding study population selection and the exclusion of participants with poor quality images. Applicablity was unclear in all studies since professionals referring patients and results of prior testing were not reported. There was a specific 'unit of analysis' issue because both eyes of the majority of participants were included in the analyses as if they were independent.In nine studies providing data on CSMO (759 participants, 1303 eyes), pooled sensitivity was 0.78 (95% confidence interval (CI) 0.72 to 0.83) and specificity was 0.86 (95% CI 0.76 to 0.93). The median central retinal thickness cut-off we selected for data extraction was 250 µm (range 230 µm to 300 µm). Central CSMO was the target condition in all but two studies and thus our results cannot be applied to non-central CSMO.Data from three studies reporting accuracy for detection of DMO (180 participants, 343 eyes) were not pooled. Sensitivities and specificities were about 0.80 in two studies and were both 1.00 in the third study.Since this review was conceived, the role of OCT has changed and has become a key ingredient of decision-making at all levels of ophthalmic care in this field. Moreover, disagreements between OCT and fundus examination are informative, especially false positives which are referred to as subclinical DMO and are at higher risk of developing clinical CSMO. AUTHORS' CONCLUSIONS: Using retinal thickness thresholds lower than 300 µm and ophthalmologist's fundus assessment as reference standard, central retinal thickness measured with OCT was not sufficiently accurate to diagnose the central type of CSMO in patients with DR referred to retina clinics. However, at least OCT false positives are generally cases of subclinical DMO that cannot be detected clinically but still suffer from increased risk of disease progression. Therefore, the increasing availability of OCT devices, together with their precision and the ability to inform on retinal layer structure, now make OCT widely recognised as the new reference standard for assessment of DMO, even in some screening settings. Thus, this review will not be updated further.

Profile of retinal vasculitis in a tertiary eye care center in Eastern India.

AIMS: To provide a fact file on the etiology, clinical presentations and management of retinal vasculitis in Eastern India. MATERIALS AND METHODS: Retrospective, record based analysis of retinal vasculitis cases in a tertiary care center in Eastern India from January 2007 to December 2009 . RESULTS: One hundred and thirteen eyes of 70 patients of retinal vasculitis were included in this study. Sixty (85.7%) patients were male (mean age 33± 11.1 years) and 10 (14.3%) were female (mean age 32.4 ± 13.6 years). Vasculitis was bilateral in 43 (61.4%) and unilateral in 27 (38.6%) patients. Commonest symptoms were dimness of vision (73; 64.6%) and floaters (36; 31.9%). Vascular sheathing (82; 72.6%) and vitritis (51; 45.1%) were commonest signs. Mantoux test was positive in 21 (30%) patients but tuberculosis was confirmed in only four (5.71%) patients. Raised serum angiotensin-converting enzyme level and positive antinuclear antibody level were reported in four (5.71%) patients each. Human leukocyte antigen B5 (HLA B5) marker was present in one (1.4%) patient. However, none of the total 70 patients were found to have a conclusively proven systemic disease attributable as the cause of retinal vasculitis. Oral corticosteroid (60; 85.7%) was the mainstay of treatment. Forty-eight (42.5%) eyes maintained their initial visual acuity and 43 (38%) gained one or more line at mean follow-up of 16.6± 6.3 months. CONCLUSION: Retinal vasculitis cases had similar clinical presentations and common treatment plan. There was no systemic disease association with vasculitis warranting a careful approach in prescribing investigations.

Distortion maps from preferential hyperacuity perimetry are helpful in monitoring functional response to Lucentis therapy.

PURPOSE: To use preferential hyperacuity perimetry to obtain a quantitative measure of central visual field distortion that would aid in the monitoring of functional responsiveness to ranibizumab treatment. METHODS: This study is a retrospective analysis of data from patients with neovascular age-related macular degeneration treated with ranibizumab. Preferential hyperacuity perimetry (PHP) were performed before and within 10 days of treatment. Pre- and posttreatment PHP metamorphopsia maps of contours showing 6 levels of metamorphopsia severity (S1 through S6; least to most distortion) were analyzed. Optical coherence tomography (OCT) outputs were subjected to standardized grading to generate metrics on subretinal fluid height, maximum retinal thickness, outer high-reflectivity band thickness, and height of pigment epithelial detachment (OCT metrics). RESULTS: Complete data were available from 17 patients. Statistically significant reductions were seen between baseline and posttreatment in PHP contour areas and OCT metrics, except for maximum retinal thickness. Mean best-corrected visual acuity improved by two letters, but this was not statistically significant. Change in PHP parameters correlated strongly with change in subretinal fluid height, with P values of <0.01 for most comparisons. Change in best-corrected visual acuity did not correlate with change in any of the OCT metrics or PHP distortion map areas. CONCLUSION: The reduction in the contour map area seen on PHP outputs occurs rapidly and correlates with the resolution of subretinal fluid, suggesting that this parameter may be used to monitor response to therapy.

SRPK1: a cisplatin sensitive protein expressed in retinoblastoma.

Chemotherapy is an essential modality in the treatment of retinoblastoma (RB). Mammalian serine/arginine-rich protein-specific kinase 1 (SRPK1) is a cisplatin-sensitivity-related protein and its downregulation is known to be associated with decreased response to cisplatin and carboplatin. We investigated the expression of SRPK1 in 63 archival RB and correlated its expression with pathologic staging and exposure to chemotherapy. The majority of the RB (62/63) were advanced stage (Groups D and E) with intermediate to high risk of treatment failure according to the new international classification for intraocular RB and SRPK1 was reduced in 32/62 (51%) tumors. SRPK1 protein expression was reduced in (100%) 8/8 RB that had recurred in the orbit or had metastasized. SRPK1 protein expression is reduced in RB with advanced stage of presentation and this may add to drug resistance mechanisms in RB.