Comparing generative and retrieval-based chatbots in answering patient questions regarding age-related macular degeneration and diabetic retinopathy.
Kai Xiong CheongChenxi ZhangTien-En TanBeau J FennerWendy Meihua WongKelvin Yc TeoYa-Xing WangSobha SivaprasadPearse A KeaneCecilia Sungmin LeeAaron Y LeeGemmy Cheung Chui MingTien Yin WongYun-Gyung CheongSu Jeong SongYih-Chung ThamPublished in: The British journal of ophthalmology (2024)
ChatGPT-4 and ChatGPT-3.5 demonstrated superior performance, followed by Google Bard and OcularBERT. Generative chatbots are potentially capable of answering domain-specific questions outside their original training. Further validation studies are still required prior to real-world implementation.