在基于PRISMA的医学系统性文献审查中实施和评估基于GPT-4的额外审查员
Assaf Landschaft1, Dario Antweiler2, Sina Mackay2
1Boston Children's Hospital, 300 Longwood Avenue, Boston, MA 02115, USA; Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme (IAIS), Sankt Augustin, Germany.
International journal of medical informatics
|June 29, 2024
概括
在系统性文献审查中,GPT-4 API显示出强大的潜力,作为一个补充的审稿人,在抽象选中与人类审稿人达成高度一致,可能减少人类的努力.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 系统审查方法论 系统审查方法论
背景情况:
- 系统的文献审查需要大量的人力资源来审查数据.
- 坚持PRISMA框架需要仔细的审查过程.
- 自动化审查过程的部分可以提高效率.
研究的目的:
- 评估GPT-4 API在基于PRISMA的系统性审查中作为补充审查者的可行性和可靠性.
- 在文献选中,比较GPT-4 API与人类审查者的性能.
- 探索AI在简化系统审查工作流程方面的潜力.
主要方法:
- 进行了系统的文献审查,重点关注自然语言处理和用于患者试验匹配的大型语言模型.
- 两个人体审查员和GPT-4 API被用于抽象查.
- 使用LangChain的检索增强生成 (RAG) 方法用于全文文章处理和参数提取.
主要成果:
- 在抽象查期间,在GPT-4 API和人类审查者之间观察到近乎完美的一致性 (科恩卡帕>0.9).
- 在比较GPT-4 API和全文参数提取的人类审稿人时,协议水平较低.
- 该研究评估了抽象选和全文数据提取的评审者间可靠性.
结论:
- 在系统性审查的抽象选阶段,GPT-4 API在系统性审查的抽象选阶段表现出与人类审查员相比较的性能.
- 这些发现表明,GPT-4 API可以作为主要查工具,可能取代一个人类审查员.
- 需要进一步的研究来优化AI在系统审查的全文分析中的作用.
更多相关视频
06:05The Participant-Reported Implementation Update and Score PRIUS: A Novel Method for Capturing Implementation-Related Data Over Time
Published on: February 19, 2021
1.3K
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
543
相关概念视频
Proofreading
52.0K
Overview
52.0K
Review and Preview
9.5K
Data are individual items of information obtained from a population or sample. Data may be classified as qualitative (categorical), quantitative continuous, or quantitative discrete. Because it is not practical to measure the entire population in a study, researchers use samples to represent the population. A random sample is a representative group from the population chosen by using a method that gives each individual in the population an equal chance of being included in the sample. Random...
9.5K
Review and Preview
5.9K
In statistics, several tools are used to interpret the data. Measures of central tendency represent the characteristics of the data, such as mean, median, and mode. Additionally, measures of variance like standard deviation and range are used to find the spread of data from the mean. Relative standing measures the distance between data locations. Commonly used measures of relative standings are percentile, z score, and quartiles.
Percentiles are a type of fractile that partition data into...
Percentiles are a type of fractile that partition data into...
5.9K
Methods of Documentation II: POMR
1.4K
The Problem-Oriented Medical Record (POMR) revolutionized medical record-keeping by introducing a systematic approach focusing on the patient's problems rather than merely listing symptoms. Dr. Lawrence Weed's introduction of this method in the 1960s marked a significant advancement in medical documentation. The POMR framework consists of four key components: the database, problem list, plan of care, and progress notes.
1.4K
