Training of an ophthalmologist in concepts and practice of community eye health

Deep learning algorithms for detection of diabetic retinopathy in retinal fundus photographs: A systematic review and meta-analysis

BACKGROUND

Diabetic retinopathy (DR) is one of the leading causes of blindness globally. Earlier detection and timely treatment of DR are desirable to reduce the incidence and progression of vision loss. Currently, deep learning (DL) approaches have offered better performance in detecting DR from retinal fundus images. We, therefore, performed a systematic review with a meta-analysis of relevant studies to quantify the performance of DL algorithms for detecting DR.

METHODS

A systematic literature search on EMBASE, PubMed, Google Scholar, Scopus was performed between January 1, 2000, and March 31, 2019. The search strategy was based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guidelines, and DL-based study design was mandatory for articles inclusion. Two independent authors screened abstracts and titles against inclusion and exclusion criteria. Data were extracted by two authors independently using a standard form and the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used for the risk of bias and applicability assessment.

RESULTS

Twenty-three studies were included in the systematic review; 20 studies met inclusion criteria for the meta-analysis. The pooled area under the receiving operating curve (AUROC) of DR was 0.97 (95%CI: 0.95-0.98), sensitivity was 0.83 (95%CI: 0.83-0.83), and specificity was 0.92 (95%CI: 0.92-0.92). The positive- and negative-likelihood ratio were 14.11 (95%CI: 9.91-20.07), and 0.10 (95%CI: 0.07-0.16), respectively. Moreover, the diagnostic odds ratio for DL models was 136.83 (95%CI: 79.03-236.93). All the studies provided a DR-grading scale, a human grader (e.g. trained caregivers, ophthalmologists) as a reference standard.

CONCLUSION

The findings of our study showed that DL algorithms had high sensitivity and specificity for detecting referable DR from retinal fundus photographs. Applying a DL-based automated tool of assessing DR from color fundus images could provide an alternative solution to reduce misdiagnosis and improve workflow. A DL-based automated tool offers substantial benefits to reduce screening costs, accessibility to healthcare and ameliorate earlier treatments.

When and How to Incorporate Steroids for Persistent Diabetic Macular Edema: A Discussion of Real-World Treatment Optimization Strategies

In the United States, diabetic macular edema (DME) is the leading cause of vision loss among people with diabetic retinopathy. Despite the availability of different therapies for DME, up to half of patients with DME show some persistent edema after anti-vascular endothelial growth factor (VEGF) treatment alone, leaving these patients at high risk for vision loss. However, dosing in a similar fashion to that of pivotal anti-VEGF trials is difficult because of real-life challenges faced in clinical practice. This is particularly true for DME, in that the frequency and burden of anti-VEGF injections are a major challenge to patient care. Research evaluating anti-VEGF therapies has shaped the treatment paradigms for patients with DME, and similar benefits have also been noted in clinical trials evaluating the use of intravitreal steroids. Treatment with a long-term intravitreal corticosteroid, which requires fewer injections than treatment with most short-acting therapies, has been found to reduce inflammation and improve vision in a percentage of patients. This roundtable discussion, which took place during the 2018 annual meeting of the Vit-Buckle Society, reviews the current treatment paradigms for DME and evaluates how to customize and optimize treatment strategies geared toward individualized patient care. [Ophthalmic Surg Lasers Imaging Retina. 2018;49:S5-S15.].

Low Vision Rehabilitation in Older Adults

OBJECTIVES

To evaluate the diagnosis distribution, low vision rehabilitation methods and utilization of low vision rehabilitation in partially sighted persons over 65 years old.

MATERIALS AND METHODS

One hundred thirty-nine partially sighted geriatric patients aged 65 years or older were enrolled to the study between May 2012 and September 2013. Patients' age, gender and the distribution of diagnosis were recorded. The visual acuity of the patients both for near and distance were examined with and without low vision devices and the methods of low vision rehabilitation were evaluated.

RESULTS

The mean age of the patients was 79.7 years and the median age was 80 years. Ninety-six (69.1%) of the patients were male and 43 (30.9%) were female. According to the distribution of diagnosis, the most frequent diagnosis was senile macular degeneration for both presenile and senile age groups. The mean best corrected visual acuity for distance was 0.92±0.37 logMAR and 4.75±3.47 M for near. The most frequently used low vision rehabilitation methods were telescopic glasses (59.0%) for distance and hyperocular glasses (66.9%) for near vision. A significant improvement in visual acuity both for distance and near vision were determined with low vision aids.

CONCLUSION

The causes of low vision in presenile and senile patients in our study were similar to those of patients from developed countries. A significant improvement in visual acuity can be achieved both for distance and near vision with low vision rehabilitation in partially sighted geriatric patients. It is important to guide them to low vision rehabilitation.

Strategies for reducing visual impairment and blindness in rural and remote areas of Africa

The prevalence of visual impairment (VI) and blindness in Africa is one of the highest in the world; a large proportion of the causes are preventable. The prevalence is particularly high in rural and remote areas, where many of the continent’s inhabitants live. This is of great concern because of the low number and poor distribution of primary eye care practitioners, as well as poor eye care infrastructure services in those areas. Uncorrected refractive errors are a major cause of avoidable VI and blindness, and optometrists play a major role in refractive error correction on the continent. However, as with other healthcare providers in Africa, optometrists are few and tend to be mainly in major cities. This paper highlights possible strategies, in alignment with the Ottawa Charter for Health Promotion, that can reduce VI in rural and remote areas of the continent. The strategies include increasing the eye care workforce, attracting them to rural areas and retaining them there, improving the eye care infrastructure, service improvement such as equitable distribution of eye care practitioners, implementing preventive measures such as vision screening and affordable spectacles, and eye health education such as eye health promotions, school health programmes and eye care awareness campaigns. Such strategies could drastically reduce the prevalence of VI and blindness in rural and remote areas of Africa.