深度搜索和聊天GPT在中国卫生专业和技术考试上的表现:一项比较研究
Xu Li1,2, Xu Hu1, Huiting Xu2,3
1Department of Central ICU, The First Affiliated Hospital of Soochow University, Suzhou, China.
PloS one
|January 22, 2026
概括
在护理考试准确度方面,DeepSeek-R1显著超过了GPT-4o API,显示出超越一致的准确性. 这突出了DeepSeek-R1的功能.
科学领域:
- 医疗教育中的人工智能
- 在医疗保健评估中的自然语言处理.
- 大型语言模型 (LLM) 绩效评估
背景情况:
- 大型语言模型 (LLM) 在中国卫生专业技术考试等高风险的医疗评估中的可靠性尚未得到充分证实.
- DeepSeek-R1是一种新的推理增强的LLM,显示出潜力,但其在护理考试环境中的有效性需要经验验证.
- 现有的研究缺乏在专业医疗保健认证考试中对高级LLM进行全面比较.
研究的目的:
- 量化比较DeepSeek-R1和GPT-4o API在中国卫生专业技术考试 (中级护理) 的表现.
- 评估和对比模型准确性,响应一致性和在不同护理能力领域的一致性准确性.
- 确定每个LLM在模拟标准化护理执照考试中的表现方面表现出色或失败的特定领域.
主要方法:
- 利用了中国卫生专业技术考试 (中等护理) 的400个官方多选题实践问题.
- 将问题分为四个能力单元和两种类型 (A/B) 进行分层分析.
- 评估了DeepSeek-R1和GPT-4o API的整体准确性,响应一致性和一致性准确性,采用基平方测试和霍尔姆-邦费罗尼对统计意义的校正.
主要成果:
- 与GPT-4o API (67.9%,P < 0.001) 相比,DeepSeek-R1的整体准确度 (88.5%) 显著提高.
- GPT-4o API显示出更高的响应一致性 (96.5%),但比DeepSeek-R1 (84.0%) 更低的一致性准确性 (66.7%).
- 校正后的分析显示了显著的差异,有利于DeepSeek-R1在关键护理知识领域和问题类型中保持一致的准确性.
结论:
- 与GPT-4o API相比,DeepSeek-R1在护理能力评估准确度和一致准确度方面表现出卓越的表现.
- GPT-4o API的高一致性与较低的准确性表明潜在的系统错误,需要谨慎地解释其输出.
- 对复杂的临床推理任务和现实数据的LLM能力的进一步调查对于安全融入医学教育至关重要.
相关概念视频
01:29Professional Values
10.5K
Nurses are responsible for caring for patients during birth, death, illness, and healing. Professional values guide the decisions and actions that nurses make in their careers. If nurses know the decisions and actions to take, providing patients with exceptional care is possible.
The values that are the foundation of the nursing profession are altruism, autonomy, human dignity, and social justice.
First, altruism refers to the concern for the welfare and well-being of others without personal...
The values that are the foundation of the nursing profession are altruism, autonomy, human dignity, and social justice.
First, altruism refers to the concern for the welfare and well-being of others without personal...
10.5K
01:22The Professional Nurse
6.3K
Professional nurses are not limited to bedside care and are taking roles of greater responsibility. A nurse should have a knowledge-based practice, including personal, theoretical, procedural, cultural, and reflexive knowledge. Additionally, nurses must be competent in cognitive, technical, interpersonal, and ethical/legal skills. Some of the best attributes of successful nurses include the following:
Communication skills: These are critical characteristics, especially speaking and listening.
Communication skills: These are critical characteristics, especially speaking and listening.
6.3K
01:21Health Literacy
5.2K
Health literacy is an individual's or a community's capacity to comprehend, receive, read, and use relevant healthcare information and services. The World Health Organization (WHO, 2018) defines health literacy as the cognitive and social skills that determine the ability of individuals to gain access to, understand, and use information in ways that promote and maintain good health. As a result, the WHO helps individuals manage long-term health concerns, participate in preventative...
5.2K
02:26Comparing Copy Number Variations and SNPs
18.6K
Sequencing of the human genome has opened up several best-kept secrets of the genome. Scientists have identified thousands of genome variations that exist within a population. These variations can be a single nucleotide or a larger chromosomal variation.
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
18.6K
01:30Health Information Technology and Healthcare Information System
3.3K
Health Information Technology (HIT)
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
3.3K
01:29Concepts of Health and Illness
17.5K
Health is a condition of the body, mind, and spirit where an individual remains free from illness. Similarly, wellness is an active state, including living a lifestyle that promotes physical, mental, and emotional health. Physical health is critical for the overall well-being and can be affected by lifestyle, activity level, diet, and behavior. The highest attainable standard of health is a fundamental and universal human right. Consider Lisa, a fifteen-year-old born with congenital...
17.5K