🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Large language models are generating a lot of hype for #AI 🤖️, but can they assist patients and practitioners in #ophthalmology? Arun James Thirunavukarasu @arunjthiru explores the answer in this new article in #EyeNews 📚 👇Read more： eyenews.uk.com/features/ophth… #eyenews

OpenAI’s model all but matches doctors in assessing eye problems on.ft.com/3w7ctLg

"Large language models (LLMs) are approaching expert-level ophthalmological knowledge and reasoning" journals.plos.org/digitalhealth/… PLOS Digital Health

👁️ #AI is much better than non-specialist doctors at assessing eye problems and providing advice, Cambridge researchers have found. GPT-4 could triage patients and decide which #ophthalmology issues are emergencies that need immediate attention👇 bit.ly/3W29ZbL

#AI rivalling doctors in assessing eye problems 👁️ What could #artificialintelligence be used for in the #NHS ❓ Read Cambridge University’s perspective on the future ⏩ nationalhealthexecutive.com/articles/ai-be… Thirumasu #ophthalmology #digitalhealth #digitaltransformation #chatgpt

TECH: OpenAI's ChatGPT-4 has surpassed or matched the performance of eye specialist ophthalmologists in assessing ocular problems and suggesting treatments, according a paper published in PLOS Digital Health journal.

GPT-4 Significantly Exceeds Doctors In Assessing Eye Problems linkedin.com/pulse/gpt-4-si… Cambridge University Thirumasu #ArtificialIntelligence #GPT4

nature.com/articles/s4422…

pubs.acs.org/doi/abs/10.102…

nature.com/articles/s4174…

doi.org/10.1167/tvst.1…

cuh.nhs.uk/news/high-tech…

"We're hoping that it is deployed" Dr Arun Thirunavukarasu from Cambridge University Hospitals NHS told That's TV about the web based tool he's help create, to change the way glaucoma patients are treated.

Progress on the Chatbot Assessment Reporting Tool - #CHART! Panel Consensus 2/3 co-chaired with Gordon Guyatt Pictured: our global, multi-d expert panel - apologies to those missed #MedTwitter #AI Julio Mayol Tim Feeney Elizabeth Loder, MD, MPH Annette Flanagin Dr Riaz Agha Stavros Antoniou Gary Collins Nan Liu, Duke-NUS

This systematic review of 137 chatbot health advice services found that key features were often reported insufficiently. ja.ma/3Q3lgV3 Bright Huo Julio Mayol Thirumasu Gordon Guyatt

Just in JAMA Network Open: reporting gaps in studies on #genAI-driven #chatbots for health advice: bit.ly/CHARTReview ➡️ Poor reporting of #LLMs used ➡️ Subjective performance evaluation Items will inform the #CHART reporting guideline Gordon H. Guyatt @sa_antoniou Julio Mayol

doi.org/10.1093/jamia/…

bjo.bmj.com/content/early/…

More optical innovation from Corpus Alum Thirumasu and colleagues. #glaucoma

doi.org/10.1038/s41433…