A pilot cost-analysis study comparing AI-based EyeArt® and ophthalmologist assessment of diabetic retinopathy in minority women in Oslo, Norway

BACKGROUND

Diabetic retinopathy (DR) is the leading cause of adult blindness in the working age population worldwide, which can be prevented by early detection. Regular eye examinations are recommended and crucial for detecting sight-threatening DR. Use of artificial intelligence (AI) to lessen the burden on the healthcare system is needed.

PURPOSE

To perform a pilot cost-analysis study for detecting DR in a cohort of minority women with DM in Oslo, Norway, that have the highest prevalence of diabetes mellitus (DM) in the country, using both manual (ophthalmologist) and autonomous (AI) grading. This is the first study in Norway, as far as we know, that uses AI in DR- grading of retinal images.

METHODS

On Minority Women's Day, November 1, 2017, in Oslo, Norway, 33 patients (66 eyes) over 18 years of age diagnosed with DM (T1D and T2D) were screened. The Eidon - True Color Confocal Scanner (CenterVue, United States) was used for retinal imaging and graded for DR after screening had been completed, by an ophthalmologist and automatically, using EyeArt Automated DR Detection System, version 2.1.0 (EyeArt, EyeNuk, CA, USA). The gradings were based on the International Clinical Diabetic Retinopathy (ICDR) severity scale [1] detecting the presence or absence of referable DR. Cost-minimization analyses were performed for both grading methods.

RESULTS

33 women (64 eyes) were eligible for the analysis. A very good inter-rater agreement was found: 0.98 (P < 0.01), between the human and AI-based EyeArt grading system for detecting DR. The prevalence of DR was 18.6% (95% CI: 11.4-25.8%), and the sensitivity and specificity were 100% (95% CI: 100-100% and 95% CI: 100-100%), respectively. The cost difference for AI screening compared to human screening was $143 lower per patient (cost-saving) in favour of AI.

CONCLUSION

Our results indicate that The EyeArt AI system is both a reliable, cost-saving, and useful tool for DR grading in clinical practice.

Association of lipid-lowering drugs and antidiabetic drugs with age-related macular degeneration: a meta-analysis in Europeans

BACKGROUND/AIMS

To investigate the association of commonly used systemic medications with prevalent age-related macular degeneration (AMD) in the general population.

METHODS

We included 38 694 adults from 14 population-based and hospital-based studies from the European Eye Epidemiology consortium. We examined associations between the use of systemic medications and any prevalent AMD as well as any late AMD using multivariable logistic regression modelling per study and pooled results using random effects meta-analysis.

RESULTS

Between studies, mean age ranged from 61.5±7.1 to 82.6±3.8 years and prevalence ranged from 12.1% to 64.5% and from 0.5% to 35.5% for any and late AMD, respectively. In the meta-analysis of fully adjusted multivariable models, lipid-lowering drugs (LLD) and antidiabetic drugs were associated with lower prevalent any AMD (OR 0.85, 95% CI=0.79 to 0.91 and OR 0.78, 95% CI=0.66 to 0.91). We found no association with late AMD or with any other medication.

CONCLUSION

Our study indicates a potential beneficial effect of LLD and antidiabetic drug use on prevalence of AMD across multiple European cohorts. Our findings support the importance of metabolic processes in the multifactorial aetiology of AMD.

A Pilot Study of Implementing Diabetic Retinopathy Screening in the Oslo Region, Norway: Baseline Results

PURPOSE

to gain insight into the baseline parameters of a population with diabetes mellitus (DM) included in a pilot diabetic retinopathy (DR) screening program at Oslo University Hospital (OUH), Norway.

METHODS

This was a cross-sectional study of a cohort of adult patients (≥18 years) with type 1 or 2 DM (T1D and T2D). We measured the best-corrected visual acuity (BCVA), blood pressure (BP), heart rate (HR), intraocular pressure (IOP), height and weight. We also collected HbA1c, total serum cholesterol and urine-albumin, -creatinine and -albumin-to-creatinine ratio (ACR), as well as socio-demographic parameters, medications and previous screening history. We obtained color fundus photographs, which were graded by two experienced ophthalmologists according to the International Clinical Disease Severity Scale for DR.

RESULTS

The study included 180 eyes of 90 patients: 12 patients (13.3%) had T1D and 78 (86.7%) had T2D. In the T1D group, 5 patients (41.7%) had no DR, and 7 (58.3%) had some degree of DR. In the T2D group, 60 patients (76.9%) had no DR, and 18 (23.1%) had some degree of DR. None of the patients had proliferative DR. Of the 43 patients not newly diagnosed (time of diagnosis > 5 years for T1D and >1 years for T2D), 37.5% of the T1D patients and 5.7% of the T2D patients had previously undergone regular screening. Univariate analyses found for the whole cohort significant associations between DR and age, HbA1c, urine albumin-to-creatinine ratio, body mass index (BMI) and duration of DM. For the T2D group alone, there were significant associations between DR and HbA1c, BMI, urine creatinine, urine albumin-to-creatinine ratio and duration of DM. The analysis also showed three times higher odds for DR in the T1D group than the T2D group.

CONCLUSIONS

This study underscores the need for implementing a systematic DR screening program in the Oslo region, Norway, to better reach out to patients with DM and improve their screening adherence. Timely and proper treatment can prevent or mitigate vision loss and improve the prognosis. A considerable number of patients were referred from general practitioners for not being followed by an ophthalmologist.Among patients not newly diagnosed with DM, 62.8% had never had an eye exam, and the duration of DM for these patients was up to 18 years (median: 8 years).

Macular Layer Thickness and Effect of BMI, Body Fat, and Traditional Cardiovascular Risk Factors: The Tromsø Study

Purpose

The purpose of this study was to investigate associations between cardiovascular risk factors and the thickness of retinal nerve fiber layer (RNFL), ganglion cell-inner plexiform layer (GCIPL), and outer retina layers (ORL).

Methods

In this population-based study, we included participants from the Tromsø Study: Tromsø6 (2007 to 2008) and Tromsø7 (2015 to 2016). Persons with diabetes and/or diagnosed glaucoma were excluded from this study. Retinal thickness was measured on optical coherence tomography (Cirrus HD-OCT) macula-scans, segmented on RNFL, GCIPL, and ORL and associations were analyzed cross-sectionally (N = 8288) and longitudinally (N = 2595). We used directed acyclic graphs (DAGs) for model selection, and linear regression to adjust for confounders and mediators in models assessing direct effects. Factors examined were age, sex, blood pressure, daily smoking, serum lipids, glycated hemoglobin, body mass index (BMI), total body fat percentage (BFP), and the adjustment variables refraction and height.

Results

The explained variance of cardiovascular risk factors was highest in GCIPL (0.126). GCIPL had a strong negative association with age. Women had thicker GCIPL than men at higher age and thinner ORL at all ages (P < 0.001). Systolic blood pressure was negatively associated with RNFL/GCIPL (P = 0.001/0.004), with indication of a U-shaped relationship with GCIPL in women. The negative association with BMI was strongest in men, with significant effect for RNFL/GCIPL/ORL (P = 0.001/<0.001/0.019) and in women for GCIPL/ORL (P = 0.030/0.037). BFP was negatively associated with GCIPL (P = 0.01). Higher baseline BMI was associated with a reduction in GCIPL over 8 years (P = 0.03).

Conclusions

Cardiovascular risk factors explained 12.6% of the variance in GCIPL, with weight and blood pressure the most important modifiable factors.

Increased High-Density Lipoprotein Levels Associated with Age-Related Macular Degeneration: Evidence from the EYE-RISK and European Eye Epidemiology Consortia

PURPOSE

Genetic and epidemiologic studies have shown that lipid genes and high-density lipoproteins (HDLs) are implicated in age-related macular degeneration (AMD). We studied circulating lipid levels in relationship to AMD in a large European dataset.

DESIGN

Pooled analysis of cross-sectional data.

PARTICIPANTS

Individuals (N = 30 953) aged 50 years or older participating in the European Eye Epidemiology (E3) consortium and 1530 individuals from the Rotterdam Study with lipid subfraction data.

METHODS

AMD features were graded on fundus photographs using the Rotterdam classification. Routine blood lipid measurements, genetics, medication, and potential confounders were extracted from the E3 database. In a subgroup of the Rotterdam Study, lipid subfractions were identified by the Nightingale biomarker platform. Random-intercepts mixed-effects models incorporating confounders and study site as a random effect were used to estimate associations.

MAIN OUTCOME MEASURES

AMD features and stage; lipid measurements.

RESULTS

HDL was associated with an increased risk of AMD (odds ratio [OR], 1.21 per 1-mmol/l increase; 95% confidence interval [CI], 1.14-1.29), whereas triglycerides were associated with a decreased risk (OR, 0.94 per 1-mmol/l increase; 95% CI, 0.91-0.97). Both were associated with drusen size. Higher HDL raised the odds of larger drusen, whereas higher triglycerides decreases the odds. LDL cholesterol reached statistical significance only in the association with early AMD (P = 0.045). Regarding lipid subfractions, the concentration of extra-large HDL particles showed the most prominent association with AMD (OR, 1.24; 95% CI, 1.10-1.40). The cholesteryl ester transfer protein risk variant (rs17231506) for AMD was in line with increased HDL levels (P = 7.7 × 10-7), but lipase C risk variants (rs2043085, rs2070895) were associated in an opposite way (P = 1.0 × 10-6 and P = 1.6 × 10-4).

CONCLUSIONS

Our study suggested that HDL cholesterol is associated with increased risk of AMD and that triglycerides are negatively associated. Both show the strongest association with early AMD and drusen. Extra-large HDL subfractions seem to be drivers in the relationship with AMD, and variants in lipid genes play a more ambiguous role in this association. Whether systemic lipids directly influence AMD or represent lipid metabolism in the retina remains to be answered.

Increasing Prevalence of Myopia in Europe and the Impact of Education

Purpose

To investigate whether myopia is becoming more common across Europe and explore whether increasing education levels, an important environmental risk factor for myopia, might explain any temporal trend.

Design

Meta-analysis of population-based, cross-sectional studies from the European Eye Epidemiology (E³) Consortium.

Participants

The E³ Consortium is a collaborative network of epidemiological studies of common eye diseases in adults across Europe. Refractive data were available for 61 946 participants from 15 population-based studies performed between 1990 and 2013; participants had a range of median ages from 44 to 78 years.

Methods

Noncycloplegic refraction, year of birth, and highest educational level achieved were obtained for all participants. Myopia was defined as a mean spherical equivalent ≤−0.75 diopters. A random-effects meta-analysis of age-specific myopia prevalence was performed, with sequential analyses stratified by year of birth and highest level of educational attainment.

Main Outcome Measures

Variation in age-specific myopia prevalence for differing years of birth and educational level.

Results

There was a significant cohort effect for increasing myopia prevalence across more recent birth decades; age-standardized myopia prevalence increased from 17.8% (95% confidence interval [CI], 17.6–18.1) to 23.5% (95% CI, 23.2–23.7) in those born between 1910 and 1939 compared with 1940 and 1979 (P = 0.03). Education was significantly associated with myopia; for those completing primary, secondary, and higher education, the age-standardized prevalences were 25.4% (CI, 25.0–25.8), 29.1% (CI, 28.8–29.5), and 36.6% (CI, 36.1–37.2), respectively. Although more recent birth cohorts were more educated, this did not fully explain the cohort effect. Compared with the reference risk of participants born in the 1920s with only primary education, higher education or being born in the 1960s doubled the myopia prevalence ratio–2.43 (CI, 1.26–4.17) and 2.62 (CI, 1.31–5.00), respectively—whereas individuals born in the 1960s and completing higher education had approximately 4 times the reference risk: a prevalence ratio of 3.76 (CI, 2.21–6.57).

Conclusions

Myopia is becoming more common in Europe; although education levels have increased and are associated with myopia, higher education seems to be an additive rather than explanatory factor. Increasing levels of myopia carry significant clinical and economic implications, with more people at risk of the sight-threatening complications associated with high myopia.

Prevalence of refractive error in Europe: the European Eye Epidemiology (E(3)) Consortium

To estimate the prevalence of refractive error in adults across Europe. Refractive data (mean spherical equivalent) collected between 1990 and 2013 from fifteen population-based cohort and cross-sectional studies of the European Eye Epidemiology (E(3)) Consortium were combined in a random effects meta-analysis stratified by 5-year age intervals and gender. Participants were excluded if they were identified as having had cataract surgery, retinal detachment, refractive surgery or other factors that might influence refraction. Estimates of refractive error prevalence were obtained including the following classifications: myopia ≤-0.75 diopters (D), high myopia ≤-6D, hyperopia ≥1D and astigmatism ≥1D. Meta-analysis of refractive error was performed for 61,946 individuals from fifteen studies with median age ranging from 44 to 81 and minimal ethnic variation (98 % European ancestry). The age-standardised prevalences (using the 2010 European Standard Population, limited to those ≥25 and <90 years old) were: myopia 30.6 % [95 % confidence interval (CI) 30.4-30.9], high myopia 2.7 % (95 % CI 2.69-2.73), hyperopia 25.2 % (95 % CI 25.0-25.4) and astigmatism 23.9 % (95 % CI 23.7-24.1). Age-specific estimates revealed a high prevalence of myopia in younger participants [47.2 % (CI 41.8-52.5) in 25-29 years-olds]. Refractive error affects just over a half of European adults. The greatest burden of refractive error is due to myopia, with high prevalence rates in young adults. Using the 2010 European population estimates, we estimate there are 227.2 million people with myopia across Europe.

Cognitive function, drusen, and age-related macular degeneration: a cross-sectional study

PURPOSE

To examine the cross-sectional relationship between drusen, late age-related macular degeneration (AMD), and cognitive function. METHODS; We included 2149 stroke-free participants from the population-based Tromsø Study in Norway. Retinal photographs were graded for presence of drusen and AMD. Cognitive function was assessed using the verbal memory test (short verbal memory), digit-symbol coding test (processing speed), and the tapping test (psychomotor tempo). We assessed the relationship between drusen, late AMD, and cognitive test scores, adjusted for potential confounders.

RESULTS

Late AMD was associated with decreased performance in the verbal memory test (standardized β=-0.23, 95% confidence interval (CI): -0.51 to -0.01). Intermediate and large drusen were associated with decreased performance in the digit-symbol coding test (standardized β=-0.14 and -0.19, 95% CIs: -0.23 to -0.05 and -0.29 to -0.09, respectively). Participants with large drusen were more likely to have test scores in the lowest quartile of the digit-symbol coding test (odds ratio (OR)=1.9, 95% CI: 1.1-3.5) and the tapping test (OR=1.6, 95% CI: 1.0-2.6), but not in the verbal memory test (OR=1.0, 95% CI: 0.6-1.6).

CONCLUSIONS

The findings suggest a relationship between drusen deposition and reduced cognitive function. Although the relationships between drusen, late AMD, and the cognitive test results varied in strength and significance across the types of cognitive test, and may partly have been caused by residual confounding, it is not unlikely that a genuine but weaker relationship exists between drusen deposition and cognitive decline.

Projected prevalence of age-related macular degeneration in Scandinavia 2012-2040

PURPOSE

To project the number of persons with late age-related macular degeneration (AMD) in Scandinavia through 2040.

METHODS

Age- and sex-specific prevalence rates of late AMD (choroidal neovascularization and geographic atrophy) from the European Eye Study and the Eye Diseases Prevalence Research Group were applied to the projected Danish, Norwegian and Swedish population from 2012 to 2040.

RESULTS

A total of 187 000 persons aged ≥65 years in Scandinavia are currently affected by late AMD: 47 000 in Denmark, 43 000 in Norway and 97 000 in Sweden. Owing to an ageing population, the number of persons affected by late AMD will increase 75% to 328 000 in 2040.

CONCLUSION

The number of patients with late AMD in Scandinavia is expected to increase substantially over the next three decades, resulting in increased demand for ophthalmic health services.