Objective To evaluate answers to typical clinical questions related to neuro-ophthalmology generated by Artificial Intelligence(AI)Large Language Models(LLM)and to explore the performance of neuro-ophthalmology-related questions on LLM in a multidimensional manner using objective and expert assessment.Methods Multicenter,random-ized,cross-sectional pilot study.Thirty typical questions related to neuro-ophthalmology were selected based on four per-spectives:definition,etiology,clinical manifestations and signs,and treatment and prognosis,and were analyzed quantita-tively using Deepseek,Wenxin Yiyin 4.0,Doubao,and Kimi 1.5,which are four open-source LLMs in China,and quantita-tively analyzed with objective assessment;and quantitatively rated by three ophthalmologists using expert assessment for 120 answer texts.Three ophthalmology experts quantitatively scored the 120 answer texts.Three ophthalmologists quantita-tively scored the 120 answer texts.Level 3,5,and 4 Likert scales were developed according to the completeness,accura-cy,professionalism,relevance,and criticality of the question texts,respectively.The best-performing LLM was selected,and its performance was observed across the four types of questions.Additionally,three other experts assessed whether the best-performing one could be evaluated as a substitute for real-world doctor-patient communication.Results In the objective Chinese text reading difficulty analysis,the differences in total word count among the four LLMs were statistically significant(all P＜0.001).Of the four LLMs,Kimi 1.5 performed the best,with frequencies of 61％,29％,and 41％for the highest scores in completeness(3),accuracy and professionalism(5),and relevance and usefulness(4),respective-ly.Kimi 1.5 performed more consistently on the questions on the four areas of neuro-ophthalmologic disorders:definition,etiology,clinical manifestations and signs,treatment,and prognosis,with no between-group differences(P＞0.05).Con-clusion Chinese language LLMs have great potential in the clinical application of neuro-ophthalmology.Kimi 1.5 outper-forms other LLMs in terms of completeness,accuracy,professionalism,relevance,and usefulness,but it still cannot re-place real-world doctor-patient communication.There is a need to explore new diagnostic and therapeutic model of AI+physician in the future.

Objective To evaluate answers to typical clinical questions related to neuro-ophthalmology generated by Artificial Intelligence(AI)Large Language Models(LLM)and to explore the performance of neuro-ophthalmology-related questions on LLM in a multidimensional manner using objective and expert assessment.Methods Multicenter,random-ized,cross-sectional pilot study.Thirty typical questions related to neuro-ophthalmology were selected based on four per-spectives:definition,etiology,clinical manifestations and signs,and treatment and prognosis,and were analyzed quantita-tively using Deepseek,Wenxin Yiyin 4.0,Doubao,and Kimi 1.5,which are four open-source LLMs in China,and quantita-tively analyzed with objective assessment;and quantitatively rated by three ophthalmologists using expert assessment for 120 answer texts.Three ophthalmology experts quantitatively scored the 120 answer texts.Three ophthalmologists quantita-tively scored the 120 answer texts.Level 3,5,and 4 Likert scales were developed according to the completeness,accura-cy,professionalism,relevance,and criticality of the question texts,respectively.The best-performing LLM was selected,and its performance was observed across the four types of questions.Additionally,three other experts assessed whether the best-performing one could be evaluated as a substitute for real-world doctor-patient communication.Results In the objective Chinese text reading difficulty analysis,the differences in total word count among the four LLMs were statistically significant(all P＜0.001).Of the four LLMs,Kimi 1.5 performed the best,with frequencies of 61％,29％,and 41％for the highest scores in completeness(3),accuracy and professionalism(5),and relevance and usefulness(4),respective-ly.Kimi 1.5 performed more consistently on the questions on the four areas of neuro-ophthalmologic disorders:definition,etiology,clinical manifestations and signs,treatment,and prognosis,with no between-group differences(P＞0.05).Con-clusion Chinese language LLMs have great potential in the clinical application of neuro-ophthalmology.Kimi 1.5 outper-forms other LLMs in terms of completeness,accuracy,professionalism,relevance,and usefulness,but it still cannot re-place real-world doctor-patient communication.There is a need to explore new diagnostic and therapeutic model of AI+physician in the future.

ABSTRACT:In this study ,we elucidated the predictors of progression to liver failure during severe acute exacerbation .We analyzed 69 consecutive patients with severe acute exacerbation of chronic hepatitis B for clinical outcome and factors that influ‐enced the development of liver failure ,including viral genotype ,PC (G1896A) and BCP (A1762T/G1764A) mutants .Thirty‐three (47 .8% ) severe acute exacerbation patients progressed to liver failure .Multivariate analysis identified serum bilirubin (TB>256 μmol/dL ,P=0 .008) and prothrombin activity (PTA<40% ,P<0 .001) as significant determinants of progression to liver failure .HBeAg negativity (P=0 .065) and PC mutant (P=0 .090) were associated with the progression to hepatic de‐compensation .Serum total bilirubin ,prothrombin activities ,HBeAg status and PC mutant were predictors of clinical outcome in patients with severe acute exacerbation of chronic hepatitis B .