Recommendations for diabetic macular edema management by retina specialists and large language model-based artificial intelligence platforms

Ayushi Choudhary; Nikhil Gopalakrishnan; Aishwarya Joshi; Divya Balakrishnan; Jay Chhablani; Naresh Kumar Yadav; Nikitha Gurram Reddy; Padmaja Kumari Rani; Priyanka Gandhi; Rohit Shetty; Rupak Roy; Snehal Bavaskar; Vishma Prabhu; Ramesh Venkatesh

doi:10.1186/s40942-024-00544-6

Recommendations for diabetic macular edema management by retina specialists and large language model-based artificial intelligence platforms

Int J Retina Vitreous. 2024 Feb 28;10(1):22. doi: 10.1186/s40942-024-00544-6.

Affiliations

¹ Dept. of Retina and Vitreous, Narayana Nethralaya, #121/C, 1st R Block, Chord Road, Rajaji Nagar, 560010, Bengaluru, Karnataka, India.
² Dept of Retina and Vitreous, Little Flower Hospital and Research Centre, 683572, Angamaly, Kerala, India.
³ Medical Retina and Vitreoretinal Surgery, University of Pittsburgh School of Medicine, 203 Lothrop Street, Suite 800, 15213, Pittsburg, PA, USA.
⁴ Anant Bajaj Retina Institute, L V Prasad Eye Institute, Kallam Anji Reddy Campus, 500034, Hyderabad, Telangana, India.
⁵ Dept. of Cornea and Refractive Services, Narayana Nethralaya, #121/C, 1st R Block, Chord Road, Rajaji Nagar, 560010, Bengaluru, Karnataka, India.
⁶ Dept. of Vitreo-Retina, Aditya Birla Sankara Nethralaya, 700099, Kolkata, India.
⁷ Dept. of Retina and Vitreous, Narayana Nethralaya, #121/C, 1st R Block, Chord Road, Rajaji Nagar, 560010, Bengaluru, Karnataka, India. vramesh80@yahoo.com.

^# Contributed equally.

Abstract

Purpose: To study the role of artificial intelligence (AI) in developing diabetic macular edema (DME) management recommendations by creating and comparing responses to clinicians in hypothetical AI-generated case scenarios. The study also examined whether its joint recommendations followed national DME management guidelines.

Methods: The AI hypothetically generated 50 ocular case scenarios from 25 patients using keywords like age, gender, type, duration and control of diabetes, visual acuity, lens status, retinopathy stage, coexisting ocular and systemic co-morbidities, and DME-related retinal imaging findings. For DME and ocular co-morbidity management, we calculated inter-rater agreements (kappa analysis) separately for clinician responses, AI-platforms, and the "majority clinician response" (the maximum number of identical clinician responses) and "majority AI-platform" (the maximum number of identical AI responses). Treatment recommendations for various situations were compared to the Indian national guidelines.

Results: For DME management, clinicians (ĸ=0.6), AI platforms (ĸ=0.58), and the 'majority clinician response' and 'majority AI response' (ĸ=0.69) had moderate to substantial inter-rate agreement. The study showed fair to substantial agreement for ocular co-morbidity management between clinicians (ĸ=0.8), AI platforms (ĸ=0.36), and the 'majority clinician response' and 'majority AI response' (ĸ=0.49). Many of the current study's recommendations and national clinical guidelines agreed and disagreed. When treating center-involving DME with very good visual acuity, lattice degeneration, renal disease, anaemia, and a recent history of cardiovascular disease, there were clear disagreements.

Conclusion: For the first time, this study recommends DME management using large language model-based generative AI. The study's findings could guide in revising the global DME management guidelines.

Keywords: Artificial intelligence; Diabetic macular edema; Diabetic retinopathy; Guidelines; Management.