Live
- Thila Taila Abhishekah Pooja to Lord Shaneswara
- Priyanka Gandhi says BJP talking of 'tinkering' with Constitution with PM’s nod
- LS polls: PM Modi says BJP-NDA leading 2-0 after first two phases
- Plea in Madras HC seeks special polling arrangement for names 'missing' from Coimbatore voter list
- Ex CM KCR Bus tour on 4 th day
- Youth National Games 2024 kick-start in Delhi; over 5,000 athletes from 15 states vying for top honours
- TN Police warn people against fraudsters using AI-based voice cloning
- L-G office blames Saurabh Bharadwaj for delay in enhancing MCD Commissioner's financial powers
- ICICI Bank posts 17 per cent rise in Q4 net profit at Rs 10,707cr; declares dividend of Rs 10 per share
- 26/11 prosecutor to Mumbai North Central candidate - Ujjwal Nikam all set for 'new innings' with BJP
GPT-4 better than eye specialists in retina & glaucoma management: Study
OpenAI's based GPT-4 can match and in some cases outperform human ophthalmologists in the diagnosis and treatment of patients with glaucoma and retina disease, according to a research.
New York: OpenAI's based GPT-4 can match and in some cases outperform human ophthalmologists in the diagnosis and treatment of patients with glaucoma and retina disease, according to a research.
The study, published in JAMA Ophthalmology, suggests that advanced tools like Artificial Intelligence-(AI) based large language models (LLM), which are trained on vast amounts of data, text, and images, could play an important role in providing decision-making support to ophthalmologists in the diagnosis and management of cases involving glaucoma and retina disorders, which afflict millions of patients.
"The performance of GPT-4 in our study was quite eye-opening," said lead author Andy Huang, ophthalmology resident at New York Eye and Ear Infirmary of Mount Sinai Hospital, US.
"We recognised the enormous potential of this AI system from the moment we started testing it and were fascinated to observe that GPT-4 could not only assist but in some cases match or exceed, the expertise of seasoned ophthalmic specialists," Huang added.
Researchers matched the knowledge of the GPT-4 (Generative Pre-Training–Model 4) with 12 attending specialists and three senior trainees from the Department of Ophthalmology at the Icahn School of Medicine at Mount Sinai.
A basic set of 20 questions (10 each for glaucoma and retina) from the American Academy of Ophthalmology’s list of commonly asked questions by patients was randomly selected, along with 20 de-identified patient cases culled from Mount Sinai-affiliated eye clinics.
The results showed that AI matched or outperformed human specialists in both accuracy and completeness of its medical advice and assessments.
More specifically, AI demonstrated superior performance in response to glaucoma questions and case-management advice, while reflecting a more balanced outcome in retina questions, where AI matched humans in accuracy but exceeded them in completeness.
"AI was particularly surprising in its proficiency in handling both glaucoma and retina patient cases, matching the accuracy and completeness of diagnoses and treatment suggestions made by human doctors in a clinical note format," said Louis R. Pasquale, Deputy Chair for Ophthalmology Research for the Department of Ophthalmology.
The findings "could serve as a reliable assistant to eye specialists by providing diagnostic support and potentially easing their workload, especially in complex cases or areas of high patient volume", Dr. Huang said.
"For patients, the integration of AI into mainstream ophthalmic practice could result in quicker access to expert advice, coupled with more informed decision-making to guide their treatment."
