向艾宁堃, 田靖雪, 胡德华, 刘海霞. 生成式人工智能对于老年糖尿病应答效能的比较研究. 2025. biomedRxiv.202503.00019
生成式人工智能对于老年糖尿病应答效能的比较研究
通讯作者: 刘海霞, 742631571@qq.com
DOI:10.12201/bmr.202503.00019
Comparative Study on Response Efficacy of Generative Artificial Intelligence for Elderly Diabetes Mellitus
Corresponding author: LIU HAIXIA, 742631571@qq.com
-
摘要:目的/意义:评估不同生成式人工智能(GAI)聊天机器人对于老年糖尿病常见问题的应答准确性,从而比较各人工智能大型语言模型在医疗信息服务质量方面的表现差异。方法/过程:构建包含10个老年糖尿病相关问题的标准化评估题库,随后使用四个GAI聊天机器人对回答的准确性进行评分。此外,将问题归纳为“诊断与评估”、“控制与治疗”两个维度,对上述4个GAI在这两个维度的情况进行分析。结果/结论:综合来看,Kimi与豆包AI对于老年糖尿病常见问题应答效能显著优于DeepSeek和讯飞星火AI,具有更高的准确性且稳定性强,但Kimi与豆包AI的应答性能无显著差异。此外,在“诊断与评估”、“控制与治疗”维度,kimi、豆包AI相比于DeepSeek、讯飞星火AI有更优秀的表现。
Abstract: Objective/significance To evaluate the response accuracy of different generative artificial intelligence (GAI) chat robots to the common problems of elderly diabetes, so as to compare the performance differences of various AI large-scale language models in the quality of medical information service. Methods/Process A standardized assessment question bank containing 10 elderly diabetes related questions was constructed, and then four GAI chat robots were used to score the accuracy of the answers. In addition, the problem is summarized into two dimensions of "diagnosis and evaluation" and "control and treatment", and the situation of the above four GAI in these two dimensions is analyzed. Results/Conclusion In general, Kimi and Doubao AI have significantly better response performance than DeepSeek and iFLYTEK spark AI for common problems of elderly diabetes, with higher accuracy and stability, but there is no significant difference in response performance between Kimi and Doubao AI. In addition, in the dimensions of "diagnosis and evaluation", "control and treatment", kimi and Doubao AI has better performance than DeepSeek and iFLYTEK spark AI.
Key words: generative artificial intelligence; chat robot; large language model; senile diabetes; medical informatics提交时间:2025-05-26
版权声明:作者本人独立拥有该论文的版权,预印本系统仅拥有论文的永久保存权利。任何人未经允许不得重复使用。 -
图表
-
史森中. 生成式人工智能(GAI)基层医疗应用风险及治理策略分析. 2024. doi: 10.12201/bmr.202408.00053
马傲, 葛小玲. 人工智能大模型在医疗健康领域应用的研究. 2024. doi: 10.12201/bmr.202408.00039
郑琰莉, 韩福海, 李舒玉, 苏文星. 人工智能大模型在医疗领域的应用现状与前景展望. 2023. doi: 10.12201/bmr.202312.00027
颜文城, 李俊震, 陈玫, 卢艳红. 人工智能助力口腔医学:在牙体牙髓病学领域的应用. 2021. doi: 10.12201/bmr.202102.00003
吴思静, 许彬彬, 黄凤. 浙江省医学人工智能发展现状与政策建议. 2021. doi: 10.12201/bmr.202101.00015
牛宇翔, 葛珊衫, 王力华. 从传统NLP到大语言模型电子病历生成技术的探索与研究. 2024. doi: 10.12201/bmr.202412.00080
司唯, 徐婷, 林家玥, 曹文婷, 朱爱勇. 人工智能技术在老年认知症筛查中的应用现状. 2024. doi: 10.12201/bmr.202407.00048
胡博越, 史继红. 人工智能技术在医学图书馆应用的发展趋势与展望. 2025. doi: 10.12201/bmr.202505.00024
李明. 医生对医疗人工智能使用意愿性以及影响因素分析. 2023. doi: 10.12201/bmr.202312.00020
黄春玲, 韩彤妍, 张娟. 人工智能学习APP结合思维导图对培养儿科实习生临床思维能力的效果研究. 2024. doi: 10.12201/bmr.202412.00023
-
序号 提交日期 编号 操作 1 2025-03-06 bmr.202503.00019V1
下载 -
-
公开评论 匿名评论 仅发给作者
引用格式
访问统计
- 阅读量:28
- 下载量: 0
- 评论数:0