Benchmarking Four Large Language Models’ Performance of Addressing Chinese Patients' Inquiries About Dry Eye Disease: A Two-Phase Study

PurposeTo evaluate the performance of four large language models (LLMs)—GPT-4, PaLM 2, Qwen, and Baichuan 2—in generating responses to inquiries from Chinese patients about dry eye disease (DED).DesignTwo-phase study, including a cross-sectional test in the first phase and a real-world clinical assessment in the second phase.SubjectsEight board-certified ophthalmologists and 46 patients with DED.MethodsThe chatbots' responses to Chinese patients' inquiries about DED were assessed by the evaluation. In the first phase, six senior ophthalmologists subjectively rated the chatbots' responses using a 5-point Likert scale across five domains: correctness, completeness, readability, helpfulness, and safety. Objective readability analysis was performed using a Chinese readability analysis platform. In the second phase, 46 representative patients with DED asked the two language models (GPT-4 and Baichuan 2) that performed best in the in the first phase questions and then rated the answers for satisfaction and readability. Two senior ophthalmologists then assessed the responses across the five domains.Main outcome measuresSubjective scores for the five domains and objective readability scores in the first phase. The patient satisfaction, readability scores, and subjective scores for the five-domains in the second phase.ResultsIn the first phase, GPT-4 exhibited superior performance across the five domains (correctness: 4.47; completeness: 4.39; readability: 4.47; helpfulness: 4.49; safety: 4.47, p < 0.05). However, the readability analysis revealed that GPT-4's responses were highly complex, with an average score of 12.86 (p < 0.05) compared to scores of 10.87, 11.53, and 11.26 for Qwen, Baichuan 2, and PaLM 2, respectively. In the second phase, as shown by the scores for the five domains, both GPT-4 and Baichuan 2 were adept in answering questions posed by patients with DED. However, the completeness of Baichuan 2's responses was relatively poor (4.04 vs. 4.48 for GPT-4, p < 0.05). Nevertheless, Baichuan 2's recommendations more comprehensible than those of GPT-4 (patient readability: 3.91 vs. 4.61, p < 0.05; ophthalmologist readability: 2.67 vs. 4.33).ConclusionsThe findings underscore the potential of LLMs, particularly that of GPT-4 and Baichuan 2, in delivering accurate and comprehensive responses to questions from Chinese patients about DED.