使用大型语言模型来选择用于元分析的文献显示工作量减少,同时保持与手动策划相似的回忆水平
Xiangming Cai1, Yuanming Geng2,3, Yiming Du4
1Department of Molecular Cell Biology & Immunology, Amsterdam Infection & Immunity Institute and Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands. x.cai@amsterdamumc.nl.
BMC medical research methodology
|April 28, 2025
概括
大型语言模型 (LLM) 可以自动化用于元分析的文献选,在保持高回忆率的同时,显著减少超过40%的工作负载. 这个管道,LARS-GPT,证明了LLM辅助的基于证据的医学研究的可行性.
科学领域:
- 人工智能在医学中的应用
- 计算生物学 计算生物学
- 医疗信息学 医疗信息学
背景情况:
- 大型语言模型 (LLM) 对医学研究有希望,但它们在基于证据的医学中的应用,特别是元分析,尚未得到充分探索.
- 在元分析中选文献记录是一个劳动密集的过程.
- 很少有研究研究了LLM的使用,以协助这一关键的选步骤.
研究的目的:
- 探索多个LLM的整合,以简化元分析中的记录选过程.
- 开发和评估标题和摘要选的自动化策略.
主要方法:
- 评估了各种LLM,包括GPT-3.5,GPT-4,Deepseek-R1-Distill,Qwen-2.5,Phi-4,Llama-3.1,Gemma-2和Claude-2.2,其中包括GPT-3.5,GPT-4,Deepseek-R1-Distill,Qwen-2.5,Phi-4,Llama-3.1,Gemma-2和Claude-2.2等等.
- 开发了一个名为LARS-GPT的四步策略,用于自动记录选择.
- 通过回忆,工作负载减少,精度和F1评分对选定的元分析进行绩效评估.
主要成果:
- 单次提示的LLM表现各不相同,平均回忆率为0.800.
- 提示的组合提高了超出预设值的性能.
- 拉斯-GPT实现了平均工作量减少40.1%,召回超过0.9.
结论:
- 使用LLMs进行元分析的自动文献选择是可行的.
- 在LARS-GPT管道有效地减少工作量,同时保持高回忆.
- 这种方法为基于证据的医学研究提供了重大进展.
更多相关视频
相关概念视频
01:27Language and Cognition
287
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
287
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
25
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
25
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
13
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
13
02:20Longitudinal Research
11.8K
Sometimes we want to see how people change over time, as in studies of human development and lifespan. When we test the same group of individuals repeatedly over an extended period of time, we are conducting longitudinal research. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time. For example, we may survey a group of individuals about their dietary habits at age 20, retest them a decade later at age 30, and then again...
11.8K
02:01Group Design
8.8K
The most basic experimental design involves two groups: the experimental group and the control group. The two groups are designed to be the same except for one difference— experimental manipulation. The experimental group gets the experimental manipulation—that is, the treatment or variable being tested—and the control group does not. Since experimental manipulation is the only difference between the experimental and control groups, we can be sure that any differences between...
8.8K