Search

In recent years, research in artificial intelligence (AI) has experienced an unprecedented surge in the field of ophthalmology, in particular glaucoma. The diagnosis and follow-up of glaucoma is complex and relies on a body of clinical evidence and ancillary tests. This large amount of information from structural and functional testing of the optic nerve and macula makes glaucoma a particularly appropriate field for the application of AI. In this paper, we will review work using AI in the field of glaucoma, whether for screening, diagnosis or detection of progression. Many AI strategies have shown promising results for glaucoma detection using fundus photography, optical coherence tomography, or automated perimetry. The combination of these imaging modalities increases the performance of AI algorithms, with results comparable to those of humans. We will discuss potential applications as well as obstacles and limitations to the deployment and validation of such models. While there is no doubt that AI has the potential to revolutionize glaucoma management and screening, research in the coming years will need to address unavoidable questions regarding the clinical significance of such results and the explicability of the predictions., (Copyright © 2021 Elsevier Masson SAS. All rights reserved.)

Purpose: The purpose of this paper is to collect data describing the implication of intraocular pressure (IOP) and arterial blood pressure in the progression of glaucoma., Method: The literature selection for this Article was based on MEDLINE searches covering the last 20 Years and relevant Articles. Topics covered were ambulatory blood pressure monitoring, IOP fluctuations, arterial hypotension, and glaucoma., Results: Hypoperfusion of the optic nerve head is among the significant factors relating to glaucoma damage. The physiological decrease in nocturnal blood pressure is more pronounced in some glaucoma patients, particularly in those presenting normal pressure glaucoma or with progressive visual field loss. Normal human subjects have a circadian variation in their IOP and these fluctuations are related to the sleep-wake cycle. In glaucoma patients, unappreciated IOP fluctuations may explain many cases of glaucoma progression., Discussion and Conclusion: Eyes with advanced glaucomatous optic neuropathy were associated with more marked alterations in the optic nerve vascular supply circulation than eyes with less nerve damage. Numerous findings suggest that circadian IOP variations and arterial blood pressure may play a role in the progression of glaucoma., (Copyright 2004 Masson)

Refractory types of glaucoma continue to present a therapeutic challenge to ophthalmologists. Approaches toward the management of these difficult glaucomas are addressed in this paper. The first part devotes special attention to understand the cause(s) of the failure of previous filtering surgery(ies). The next part emphasizes filtration surgery with intraoperative application of antimetabolites: 5-fluorouracil or mitomycin C and the surgical and pharmacological management of failing filtration. In case of failure of multiple filtering surgery with application of antimetabolites, surgeons have to consider cyclodestructive procedures (transscleral diode laser or endoscopic cyclophotocoagulation) to reduce aqueous production, or fistulizing procedures with tube implants or other drainage devices (valves).

With laser iridotomy, argon laser trabeculoplasties, cyclophotocoagulations with diode laser and Nd: YAG goniopunctures after deep sclerectomy, among other procedures, the laser has offered a very wide range of treatments for managing glaucomatous patients for roughly twenty years. In this paper we provide a general review of the present applications of lasers in the treatment of glaucoma, focusing on the indications, results and complications of the most frequently used procedures in daily clinical practice.

Computer Aided Diagnosis by Identification packages are expert systems which proceed by iterative comparisons sign by sign between patient's cases and data encased in their clinical memory. They draw straight forward inference from thought processes analyses that lead to diagnosis: comparison between patient's own case report and acquired identified situation, error factors: ignorance or non-performance and, lastly rules to subscribe to: perfect knowledge of every kind of glaucoma and for every kind, perfect knowledge of every sign. Formalization of the problem specifies the algorithm, the miscellaneous solutions: single hypothesis and multiple hypothesis, and their respective values. In order to build up the clinical library, literature search is required to be comprehensive: treaty, reviews, papers, communications and personal case-reports. Outputs are retrieved in an average time-lag of 15 seconds, and are expressed as a list from which only the physician can make out the meaning.