Evaluation of a glaucoma patient

Performance of perimetric glaucoma staging systems and their preference patterns among the Indian eye care practitioners

CONTEXT

Various systems are available to stage glaucomatous field defects into different severity grades. Still, the preference for such systems among Indian eye care practitioners (ECPs) and the consensus between them are not explored.

PURPOSE

To compare the clinical performance of perimetric glaucoma staging systems and to assess their preference patterns among Indian ECPs.

SETTING AND DESIGN

Retro-prospective cross-sectional study.

METHODS

Three investigators stratified 400 perimetry reports using four systems: Hodapp Anderson Parrish (HAP), enhanced Glaucoma Severity Staging (eGSS), Advanced Glaucoma Intervention Study (AGIS), and Collaborative Initial Glaucoma Treatment Study (CIGTS). Their performance was compared in terms of agreement and association. Following this, 30 ECPs from across the country segregated a subset of reports (n = 20) into different stages based on their system of choice, and their preferences/perceptions about the available perimetry staging systems were enquired and documented.

STATISTICAL ANALYSIS USED

Descriptive statistics, Kruskal-Wallis, Cohen's kappa, and Spearman's correlation.

RESULTS

For the consolidated severity stages, substantial agreements (K ranging from 0.61 to 0.75) were found between all the systems, except for HAP-CIGTS (K = 0.58) and AGIS-CIGTS (K = 0.51). All ECPs were aware of perimetry staging systems, and a high preference was reported for HAP (97%) due to ease of implementation and interpretation.

CONCLUSION

Among the four staging systems, the highest agreement was found between HAP and eGSS. A majority of ECPs proposed the need for a uniform classification system across the practices for clinical comparisons and patient education.

Impact of comprehensive eye examination in identifying the ocular co-morbidities in patients screened for cataract surgery through the out-reach activities

Purpose

To evaluate the impact of comprehensive eye examination in identifying the ocular co-morbidities in patients presenting for cataract surgery through the community screening program.

Methods

This was a hospital-based retrospective cross-sectional descriptive study in a tertiary eye care institute. Comprehensive eye examination was performed for all patients screened for cataract surgery through the out-reach activities. Patients suspected to have any ocular co-morbidity were revaluated by sub-specialty trained ophthalmologists, and further management was planned. The demographic details of patients, sub-specialty consultation, final diagnosis, and type of the treatment received by these patients were recorded.

Results

During the study period, 4022 patients were referred to the base hospital for cataract surgery, of whom 922 (22.9%) needed a specialist opinion. Glaucoma (238) and retinal disorders (232) constituted half (51%) of these referrals. There were 313 (33.9%) patients having co-morbidities because of corneal, oculoplastic, and neuro-ophthalmic conditions. After specialist review, 397 (43.1%) patients underwent only cataract surgery, 55 patients (5.9%) underwent combined surgeries, and 168 (18.2%) patients underwent other procedures. Cataract surgery was not performed in 470 (50.9%) patients, of which 302 were prescribed glasses or managed medically.

Conclusion

All patients screened for cataract surgery through out-reach programs require a comprehensive eye examination to identify ocular diseases other than cataract. Provisions must be made for providing alternative or additional treatment in those with various ocular co-morbidities.

Review of Machine Learning Applications Using Retinal Fundus Images

Automating screening and diagnosis in the medical field saves time and reduces the chances of misdiagnosis while saving on labor and cost for physicians. With the feasibility and development of deep learning methods, machines are now able to interpret complex features in medical data, which leads to rapid advancements in automation. Such efforts have been made in ophthalmology to analyze retinal images and build frameworks based on analysis for the identification of retinopathy and the assessment of its severity. This paper reviews recent state-of-the-art works utilizing the color fundus image taken from one of the imaging modalities used in ophthalmology. Specifically, the deep learning methods of automated screening and diagnosis for diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma are investigated. In addition, the machine learning techniques applied to the retinal vasculature extraction from the fundus image are covered. The challenges in developing these systems are also discussed.

Evaluation of the external validity of a joint structure-function model for monitoring glaucoma progression

The dynamic structure–function (DSF) model was previously shown to have better prediction accuracy than ordinary least square linear regression (OLSLR) for short series of visits. The current study assessed the external validity of the DSF model by testing its performance in an independent dataset (Ocular Hypertension Treatment Study–Confocal Scanning Laser Ophthalmoscopy [OHTS–CSLO] ancillary study; N = 178 eyes), and also on different test parameters in a sample selected from the Diagnostic Innovations in Glaucoma Study or the African Descent and Glaucoma Evaluation Study (DIGS/ADAGES). Each model was used to predict structure–function paired data at visits 4–7. The resulting prediction errors for both models were compared using the Wilcoxon signed-rank test. In the independent dataset, the DSF model predicted rim area and mean sensitivity paired measurements more accurately than OLSLR by 1.8–5.5% (p ≤ 0.004) from visits 4–6. Using the DIGS/ADAGES dataset, the DSF model predicted retinal nerve fiber layer thickness and mean deviation paired measurements more accurately than OLSLR by 1.2–2.5% (p ≤ 0. 007). These results demonstrate the external validity of the DSF model and provide a strong basis to develop it into a useful clinical tool.

Offline computer-aided diagnosis for Glaucoma detection using fundus images targeted at mobile devices

BACKGROUND AND OBJECTIVE

Glaucoma, an eye condition that leads to permanent blindness, is typically asymptomatic and therefore difficult to be diagnosed in time. However, if diagnosed in time, Glaucoma can effectively be slowed down by using adequate treatment; hence, an early diagnosis is of utmost importance. Nonetheless, the conventional approaches to diagnose Glaucoma adopt expensive and bulky equipment that requires qualified experts, making it difficult, costly and time-consuming to diagnose large amounts of people. Consequently, new alternatives to diagnose Glaucoma that suppress these issues should be explored.

METHODS

This work proposes an interpretable computer-aided diagnosis (CAD) pipeline that is capable of diagnosing Glaucoma using fundus images and run offline in mobile devices. Several public datasets of fundus images were merged and used to build Convolutional Neural Networks (CNNs) that perform segmentation and classification tasks. These networks are then used to build a pipeline for Glaucoma assessment that outputs a Glaucoma confidence level and also provides several morphological features and segmentations of relevant structures, resulting in an interpretable Glaucoma diagnosis. To assess the performance of this method in a restricted environment, this pipeline was integrated into a mobile application and time and space complexities were assessed.

RESULTS

Considering the test set, the developed pipeline achieved 0.91 and 0.75 of Intersection over Union (IoU) in the optic disc and optic cup segmentation, respectively. With regards to the classification, an accuracy of 0.87 with a sensitivity of 0.85 and an AUC of 0.93 were attained. Moreover, this pipeline runs on an average Android smartphone in under two seconds.

CONCLUSIONS

The results demonstrate the potential that this method can have in the contribution to an early Glaucoma diagnosis. The proposed approach achieved similar or slightly better metrics than the current CAD systems for Glaucoma assessment while running on more restricted devices. This pipeline can, therefore, be used to construct accurate and affordable CAD systems that could enable large Glaucoma screenings, contributing to an earlier diagnose of this condition.

A comparative study on efficacy of fixed combination timolol/brinzolamide versus travoprost monotherapy in drug-naïve open-angle glaucoma patients

Background

Glaucoma is most common irreversible cause of blindness in India. First line management of open-angle glaucoma is either beta blockers or prostaglandin analogs monotherapy. Monotherapy rarely achieves target intraocular pressure within 2 years and patients are shifted to combination medications, usually fixed-dose combination.

Objective

To compare travoprost monotherapy and timolol/brinzolamide fixed-dose combination for their intraocular pressure lowering efficacy, their effects on hemodynamic parameters and cup disc ratio reversibility in newly diagnosed drug-naïve open-angle glaucoma patients.

Material and methods

In a 12-week, prospective, randomised, single-blind study, patients were randomised to receive twice daily 0.5% timolol and 0.2% brinzolamide fixed-dose combination (n = 52) or once daily travoprost 0.004% (n = 52). Intraocular pressure, blood pressure, pulse rate and cup disc ratio were compared across treatment groups over 3 months.

Results

Significant reduction (p < 0.001) in intraocular pressure by 27.99% and 30.49% at 12th-week visit as compared with baseline was observed in monotherapy and fixed-dose combination group, respectively. Significant changes in pulse rate (9 beats/min) and systolic blood pressure (2.35 mmHg) was observed in fixed-dose combination group. No cup disc ratio reversibility was observed at the end of study. Conjunctival hyperaemia (n = 14) and transient blurring of vision (n = 16) were most commonly reported adverse drug reaction in monotherapy and fixed-dose combination, respectively.

Conclusion

The 0.5% timolol and 0.2% brinzolamide fixed-dose combination produced greater reduction in intraocular pressure than those produced by 0.004% travoprost alone in drug-naïve open-angle glaucoma patients.

Patients' perception of glaucoma diagnosis practice: Results from a survey of glaucoma patients in North India

PURPOSE

This study assesses the practice patterns of diagnosing ophthalmologists, as reported by glaucoma patients attending specialty glaucoma clinics in urban and rural areas of North India, for a second opinion.

METHODS

Prospective cross-sectional study using a structured interview-based survey was conducted from 1 November 2011 to 31 October 2012 on patients attending two specialty glaucoma care facilities in North India. Both clinics were in North India; however, one was rural (Kaithal) and one was urban (Delhi). Patients were asked through descriptions of machines and processes, regarding practice patterns of their glaucoma diagnosing ophthalmologists. The interview was conducted by ophthalmic assistants in tune with the vernacular of the region, in a language understood by the interviewee.

RESULTS

A total of 1506 patients consented to participate in the survey. The majority of patients reported undergoing tests for intraocular pressure measurement; however, 56-60% of these tests were carried out by the non-contact tonometer. More than 90% of patients reported no knowledge regarding the type and severity of the glaucoma they suffered from, and even less reported undergoing gonioscopy (3.6% Karnal and 16% Delhi). 84-86% patients who underwent perimetry reported undergoing at least some digital imaging of the optic disc.

CONCLUSIONS

Better counselling of, and communication with, the patient would help increase their awareness regarding their condition and the care required. This has the potential to enable better compliance with and adherence to treatment. Standardized training of ophthalmologists to improve clinical diagnosis of glaucoma would also go a long way.

Computer-aided diagnosis of glaucoma using fundus images: A review

BACKGROUND AND OBJECTIVES

Glaucoma is an eye condition which leads to permanent blindness when the disease progresses to an advanced stage. It occurs due to inappropriate intraocular pressure within the eye, resulting in damage to the optic nerve. Glaucoma does not exhibit any symptoms in its nascent stage and thus, it is important to diagnose early to prevent blindness. Fundus photography is widely used by ophthalmologists to assist in diagnosis of glaucoma and is cost-effective.

METHODS

The morphological features of the disc that is characteristic of glaucoma are clearly seen in the fundus images. However, manual inspection of the acquired fundus images may be prone to inter-observer variation. Therefore, a computer-aided detection (CAD) system is proposed to make an accurate, reliable and fast diagnosis of glaucoma based on the optic nerve features of fundus imaging. In this paper, we reviewed existing techniques to automatically diagnose glaucoma.

RESULTS

The use of CAD is very effective in the diagnosis of glaucoma and can assist the clinicians to alleviate their workload significantly. We have also discussed the advantages of employing state-of-art techniques, including deep learning (DL), when developing the automated system. The DL methods are effective in glaucoma diagnosis.

CONCLUSIONS

Novel DL algorithms with big data availability are required to develop a reliable CAD system. Such techniques can be employed to diagnose other eye diseases accurately.