GPT-4可以通过韩国国家执照考试为韩国医学医生
Dongyeop Jang1, Tae-Rim Yun1, Choong-Yeol Lee1
1Department of Physiology, College of Korean Medicine, Gachon University, Seongnam, Gyeonggi-do, Korea.
PLOS digital health
|December 15, 2023
概括
像GPT-4这样的大型语言模型 (LLM) 在韩国传统医学 (TKM) 中表现有希望,在全国考试中达到66.18%的准确率. 需要进一步发展,以解决文化偏见和提高特种TKM科目的表现.
科学领域:
- 人工智能在医学中的应用
- 计算语言学 计算语言学
- 韩国传统医学 韩国传统医学
背景情况:
- 传统韩国医学 (TKM) 为人工智能带来了独特的挑战,因为它具有个性化的治疗方法和隐含的知识.
- 大型语言模型 (LLM) 证明了尽管有限的专业培训,但医学推断的潜力.
- 在文化特定的医疗系统中评估LLM能力对于未来的应用至关重要.
研究的目的:
- 评价GPT-4在韩国医学医生的韩国国家许可考试 (K-NLEKMD) 的表现.
- 确定快速优化技术对GPT-4在TKM中的精度的影响.
- 探索在文化适应医疗领域的LLMs的潜力和局限性.
主要方法:
- 在GPT-4中,从2022年的K-NLEKMD中测试了340个问题,涵盖了12个TKM科目.
- 快速优化包括中文术语注释,英语翻译,考试具体说明和自我一致性技术.
- 在不同的科目和问题类型 (诊断,召回,干预) 中分析了表现.
主要成果:
- 通过优化提示,GPT-4实现了66.18%的准确性,超过了K-NLEKMD的合格率 (60%).
- 精度从基本提示的51.82%提高到优化提示的66.18%.
- 在TKM专业和文化局部学科 (例如,公共卫生法,针) 中观察到更低的准确性.
- 与基于干预的问题相比,诊断和回忆问题的准确性更高.
- 发现了响应一致性和准确性之间的正相关性.
结论:
- 像GPT-4这样的LLM显示出在TKM教育,研究和临床任务中提供帮助的巨大潜力.
- 在解决LLM内部的文化偏见以及在现实世界TKM环境中验证其有效性方面仍然存在挑战.
- 需要进一步的研究来开发减轻偏见和提高专业医学领域的LLM绩效的方法.
相关概念视频
Endoscopic Procedures IV: Sigmoidoscopy and Laproscopy
88
Sigmoidoscopy and laparoscopy are distinct medical procedures that enable physicians to internally inspect different parts of the GI tract. Although they serve different purposes, each is essential for diagnosing and, in some cases, treating various medical conditions.
Sigmoidoscopy
Sigmoidoscopy is a diagnostic procedure that uses a flexible sigmoidoscope equipped with a light source and camera to examine the rectum and sigmoid colon. The procedure involves inserting the tube through the anus...
Sigmoidoscopy
Sigmoidoscopy is a diagnostic procedure that uses a flexible sigmoidoscope equipped with a light source and camera to examine the rectum and sigmoid colon. The procedure involves inserting the tube through the anus...
88
Preclinical Development: Overview
4.4K
Preclinical development consists of a series of tests that ensure the safety and efficacy of a new therapeutic compound before it is tested in humans. There are four main phases to this process. First, safety pharmacology tests are conducted to ensure the drug does not produce any acutely harmful effects. These tests examine parameters such as bronchoconstriction, cardiac dysrhythmias, blood pressure changes, and ataxia. Next, preliminary toxicological testing is performed to determine the...
4.4K
Carrier-Mediated Transport
441
Carrier-mediated transport is a pivotal process in drug absorption, particularly for lipid-insoluble drugs, and encompasses facilitated diffusion and active transport. Facilitated diffusion allows drugs to move along their concentration gradient without energy expenditure, while active transport utilizes ATP to drive drug movement against this gradient.
Active transport involves two types of membrane-spanning transporters: uptake and efflux. Uptake transporters are expressed in the small...
Active transport involves two types of membrane-spanning transporters: uptake and efflux. Uptake transporters are expressed in the small...
441
Pulmonary Tuberculosis IV
143
Tuberculosis, more commonly referred to as TB, is an infectious disease stemming from Mycobacterium tuberculosis. While it primarily impacts the lungs, TB can also affect other body areas. Given its severity and global impact, timely and accurate diagnosis is crucial for controlling its spread and improving patient outcomes.
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
143
Clinical Trials: Overview
3.0K
Clinical development focuses on how the drug will interact with the human body and encompasses four key phases of clinical trials, each serving a specific purpose in assessing the safety and effectiveness of new drugs. These phases overlap and build upon one another. Phase I involves a small group of healthy volunteers (typically 20-80 individuals) or, in cases where significant toxicity is expected, patients with the targeted disease, such as cancer or AIDS. The volunteers are tested for...
3.0K


