Marko Popovic

Jul 18, 2024 | jamanetwork.com | Andrew Mihalache |Marko Popovic |Rajeev H. Muni

Need for Custom Artificial Intelligence Chatbots in Ophthalmology Retrieval-Augmented Large Language Model for Ophthalmology Ming-Jie Luo, MD; Jianyu Pang, MSc; Shaowei Bi, MD; Yunxi Lai, MD; Jiaman Zhao, BE; Yuanrui Shang, BM; Tingxin Cui, MD; Yahan Yang, PhD, MD; Zhenzhe Lin, MEng; Lanqin Zhao, MSc; Xiaohang Wu, PhD, MD; Duoru Lin, PhD, MD; Jingjing Chen, MD; Haotian Lin, PhD, MD The utility of publicly accessible artificial intelligence (AI) chatbots such as ChatGPT (Open AI) has been...

Apr 22, 2024 | nature.com | Andrew Mihalache |Ryan Huang |Nikhil Patil |Marko Popovic

The integration of artificial intelligence (AI) within ophthalmology represents a paradigm shift that can redefine patient interactions and healthcare delivery [1]. The large language model ChatGPT-4 (OpenAI) has been recognized for its rapidly advancing proficiency in medical prompt analysis [2, 3]. While earlier iterations of this chatbot were confined to text-based input, our recent work has documented a remarkable expansion in its ophthalmic applications [4,5,6].

Apr 13, 2024 | nature.com | Andrew Mihalache |Nikhil Patil |Ryan Huang |Marko Popovic |Peter Kertes |Justin Grad

AbstractWith the popularization of ChatGPT (Open AI, San Francisco, California, United States) in recent months, understanding the potential of artificial intelligence (AI) chatbots in a medical context is important. Our study aims to evaluate Google Gemini and Bard’s (Google, Mountain View, California, United States) knowledge in ophthalmology.

Nov 16, 2023 | jamanetwork.com | Andrew Mihalache |Temerty Faculty |Marko Popovic |Rajeev H. Muni

Advances in Artificial Intelligence Chatbot Technology in Ophthalmology—Reply In Reply We sincerely thank Lin and colleagues for their comments on our article.1 Using a free trial of OphthoQuestions, a popular question bank for ophthalmology board certification preparation, we found that ChatGPT-3.5 correctly answered 58 of 125 questions in January 2023 (46%) and 73 of 125 questions in February 2023 (58%).1 Lin and colleagues2 make the argument that since this time, the accuracy of ChatGPT...

Oct 15, 2023 | tandfonline.com | Andrew Mihalache |Ryan Huang |Marko Popovic |Rajeev H. Muni

AbstractPurpose: ChatGPT-4 is an upgraded version of an artificial intelligence chatbot. The performance of ChatGPT-4 on the United States Medical Licensing Examination (USMLE) has not been independently characterized. We aimed to assess the performance of ChatGPT-4 at responding to USMLE Step 1, Step 2CK, and Step 3 practice questions. Method: Practice multiple-choice questions for the USMLE Step 1, Step 2CK, and Step 3 were compiled.