评估人工智能聊天机器人在夜间信息中:可读性,可靠性和质量的比较分析
Kemal Gumus1, Ahmet Burak Yilmaz1, Ali Furkan Cinbek1
1Department of Urology, Sincan Training and Research Hospital, Ankara, Turkey.
The French journal of urology
|December 5, 2025
概括
人工智能聊天机器人提供难以阅读的关于儿童夜间尿尿症的信息,这限制了它们对父母的有用性. 需要进一步开发以确保这种常见疾病的清晰度和临床可靠性.
科学领域:
- 医疗保健中的人工智能
- 儿科泌尿外科 儿科泌尿外科
- 数字健康工具 数字健康工具
背景情况:
- 夜间尿泡症影响全球数百万儿童,造成严重的社会心理困扰.
- 人工智能聊天机器人正在成为健康信息工具,但它们的可靠性尚未被证明.
研究的目的:
- 系统地比较领先的人工智能聊天机器人关于童年夜间尿尿症的反应的质量,可读性和临床可靠性.
- 评估人工智能聊天机器人是否适合作为家长可访问的健康指导工具.
主要方法:
- 一项横截面的观察性研究评估了OpenAI GPT-4o,Google Gemini 2.5 Pro和DeepSeek R1对40个关于夜间尿的常见问题的答案.
- 使用弗莱什阅读易度得分 (FRES) 和弗莱什-金凯德等级水平 (FKGL) 评估可读性.
- 信息质量使用"为患者提供质量信息" (EQIP) 和修改后的DISCERN (mDISCERN) 工具进行评估.
主要成果:
- 所有聊天机器人都产生了"难以阅读"范围内的文本 (FRES: 33.6-40.9),需要大学水平的理解 (FKGL: 20.3-21.9).
- 与双子座 (57.8±6.3) 和GPT-4o (54.7±4.8) 相比,DeepSeek R1的EQIP分数显著更好 (70.4±9.2).
- 在所有模型中,修改后的DISCERN评分都很低,这表明临床可靠性不佳.
结论:
- 目前的人工智能聊天机器人作为可靠和可访问的夜间尿尿信息来源的潜力有限.
- 人工智能聊天机器人还不足以在儿科泌尿病学中临床使用.
- 未来的人工智能开发必须侧重于简单的语言,结构化的信息,并遵守儿科泌尿病学指南.
相关概念视频
Stereotype Content Model
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence categorization, a person will feel...
Non-equilibrium in the Cell
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
