The SALT Trial: For #SLT, a short course of post-op topical NSAID or steroid resulted in better IOP compared with placebo. #glaucoma #laser #ophthalmology ow.ly/M8Pp50uDZE2

Expanding the applications of deep learning. Automated detection of geographic atrophy using deep learning demonstrated a high accuracy and was non-inferior to human retina specialists. ow.ly/NPRu50uHoFE

Preprint of our paper to appear in Retina available here: arxiv.org/abs/1907.05164 In this, we show how deep learning software detects abnormalities in 5,588 eyes, acquired at independent sites in five countries, using four different scanner manufacturers, with a 98% AUROC.

In a recent proof-of-concept study, a smartphone app detected middle ear fluid in kids w an accuracy comparable to pneumatic otoscopy and tympanometry. The app chirps, and a machine learning algorithm interprets the sound as showing fluid or not ja.ma/2NKwZuj JAMA Otolaryngology – Head & Neck Surgery

Achieving a milestone in #ArtificialIntelligence by moving beyond settings involving only two players, researchers present in Science an #AI that can outperform top human professionals in six-player no-limit Texas hold'em #poker. fcld.ly/p19heh9

The 2019 ARVO Annual Meeting Abstract issue is available now. Use the advanced search to search by title or author name. The issue is free to read and share! Check it out IOVS Journal tinyurl.com/y2q7b7jh #OpenAccess

Interesting new device to image the angle #glaucoma ophthalmologyglaucoma.org/article/S2589-…

Long term follow-up (>15 years) of EMGT: 97% patients progressed. #glaucoma Journal of Glaucoma ncbi.nlm.nih.gov/pubmed/31567622

Around 60% of low pressure #glaucoma patients progress in 5 years if untreated Ophthalmology ncbi.nlm.nih.gov/pubmed/30605741

I just donated to Wikipedia. Support free knowledge! #iloveWikipedia donate.wikimedia.org/?utm_medium=So…

Great paper showing the potential of training #AI to detect #glaucoma using objective exam results. Amazing work ⁦AJ D’Alessandro⁩ 👏⁦@AmJOphthalmol⁩ ncbi.nlm.nih.gov/pubmed/31730838

“#Science is messy, and the results of research rarely conform fully to plan or expectation. ‘Clean’ narratives are an artefact of inappropriate pressures and the culture they have generated.” 👏👏 Nature Human Behaviour doi.org/10.1038/s41562…

Good reading for everyone that does Goldmann tonometry. We are biased to measure even numbers, but can reduce this bias if we are careful. Journal of Glaucoma pubmed.ncbi.nlm.nih.gov/31764580/ #glaucoma

Quantification of Retinal Nerve Fibre Layer Thickness on Optical Coherence Tomography with a Deep Learning Segmentation-Free Approach. ⁦Scientific Reports⁩ ncbi.nlm.nih.gov/pubmed/31941958

Not using drops correctly will make your #glaucoma worse. Seems obvious, but nice to see #evidence. "The Association between Medication Adherence and Visual Field Progression in the Collaborative Initial Glaucoma Treatment Study." ⁦Ophthalmology⁩ ncbi.nlm.nih.gov/pubmed/31932093

Which vision parameters we can use to get information about visual function in #glaucoma patients. “Vision Parameters Most Important to Functionality in Glaucoma.” ⁦IOVS Journal⁩ ncbi.nlm.nih.gov/pubmed/31675073

With careful evaluatation, structural and functional damage in #glaucoma may agree on most cases. ⁦IOVS Journal⁩ iovs.arvojournals.org/article.aspx?a…

Detecting #glaucoma progression is hard. Different strategies often disagree. “Agreement and Predictors of Discordance of 6 Visual Field Progression Algorithms.” ⁦Ophthalmology⁩ ncbi.nlm.nih.gov/pubmed/30731101

Need for more transparency in #science: Publication of #clinicaltrials are often inconsistent with registered information (ncbi.nlm.nih.gov/pubmed/30946427). Worth reading the commentary too (ncbi.nlm.nih.gov/pubmed/30946428) JAMA Ophthalmology

Share your science, not just the results. Check out PLOS One's new #preregistered article type, #RegisteredReports. plos.io/RegReports