Xiaoqing: A Q&A model for glaucoma based on LLMs.

Glaucoma is one of the leading cause of blindness worldwide. Individuals affected by glaucoma, including patients and their family members, frequently encounter a deficit in dependable support beyond the confines of clinical environments. Seeking advice via the internet can be a difficult task due to the vast amount of disorganized and unstructured material available on these sites, nevertheless. This research explores how Large Language Models (LLMs) can be leveraged to better serve medical research and benefit glaucoma patients. We introduce Xiaoqing, a Natural Language Processing (NLP) model specifically tailored for the glaucoma field, detailing its development and deployment. To evaluate its effectiveness, we conducted two forms of experiments: comparative and experiential. In the comparative analysis, we presented 22 glaucoma-related questions in simplified Chinese to three medical NLP models (Xiaoqing LLMs, HuaTuo, Ivy GPT) and two general models (ChatGPT-3.5 and ChatGPT-4), covering a range of topics from basic glaucoma knowledge to treatment, surgery, research, management standards, and patient lifestyle. Responses were assessed for informativeness and readability. The experiential experiment involved glaucoma patients and non-patients interacting with Xiaoqing, collecting and analyzing their questions and feedback on the same criteria. The findings demonstrated that Xiaoqing notably outperformed the other models in terms of informativeness and readability, suggesting that Xiaoqing is a significant advancement in the management and treatment of glaucoma in China. We also provide a Web-based version of Xiaoqing, allowing readers to directly experience its functionality. The Web-based Xiaoqing is available at https://qa.glaucoma-assistant.com//qa.

Recombinant adenovirus expressing vesicular stomatitis virus G proteins induce both humoral and cell-mediated immune responses in mice and goats.

BACKGROUND: Vesicular stomatitis (VS) is an acute, highly contagious and economically important zoonotic disease caused by the vesicular stomatitis virus (VSV). There is a need for effective and safe stable recombinant vaccine for the control of the disease. The human type 5 replication-defective adenovirus expression vector is a good way to construct recombinant vaccines. RESULTS: Three recombinant adenoviruses (rAd) were successfully constructed that expressed the VSV Indiana serotype glycoprotein (VSV-IN-G), VSV New Jersey serotype glycoprotein (VSV-NJ-G), and the G fusion protein (both serotypes of G [VSV-IN-G-NJ-G]) with potentiality to induce protective immunity. G proteins were successfully expressed with good immunogenicity. The rAds could induce the production of VSV antibodies in mice, and VSV neutralizing antibodies in goats, respectively. The neutralizing antibody titers could reach 1:32 in mice and 1:64 in goats. The rAds induced strong lymphocyte proliferation in mice and goats, which was significantly higher compared to the negative control groups. CONCLUSIONS: The three rAds constructed in the study expressed VSV-G proteins and induced both humoral and cellular immune responses in mice and goats. These results lay the foundation for further studies on the use of rAds in vaccines expressing VSV-G.