Can off-the-shelf visual large language models detect and diagnose ocular diseases from retinal photographs?

Journal: BMJ open ophthalmology
PMID:

Abstract

BACKGROUND: The advent of generative artificial intelligence has led to the emergence of multiple vision large language models (VLLMs). This study aimed to evaluate the capabilities of commonly available VLLMs, such as OpenAI's GPT-4V and Google's Gemini, in detecting and diagnosing ocular diseases from retinal images.

Authors

  • Sahana Srinivasan
    Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore.
  • Hongwei Ji
    Tsinghua Medicine, Tsinghua University, Beijing, China.
  • David Ziyou Chen
    Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore.
  • Wendy Wong
    University College London Institute of Ophthalmology, London, UK.
  • Zhi Da Soh
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
  • Jocelyn Hui Lin Goh
    Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore.
  • Krithi Pushpanathan
    Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore.
  • Xiaofei Wang
    Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China.
  • Weizhi Ma
    Institure for AI Industry Research, Tsinghua University, Beijing, China.
  • Tien Yin Wong
    Singapore National Eye Center, Duke-National University of Singapore Medical School, Singapore 168751, Singapore; National Institutes of Health Research Biomedical Research Centre Biomedical Centre, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK.
  • Ya Xing Wang
    Beijing Visual Science and Translational Eye Research Institute (BERI), Eye Center of Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua Medicine, Tsinghua University, Beijing, China.
  • Ching-Yu Cheng
    Singapore National Eye Centre, Singapore Eye Research Institute, Singapore, Singapore.
  • Yih Chung Tham
    Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore. thamyc@nus.edu.sg.