生成型大语言模型驱动的对话性AI应用程序用于个性化风险评估:COVID-19的案例研究
Mohammad Amin Roshani1, Xiangyu Zhou1, Yao Qiang2
1Department of Computer Science, Wayne State University, Detroit, MI, United States.
JMIR AI
|March 27, 2025
概括
生成型大语言模型 (LLM) 为实时疾病风险评估提供了一个无代码解决方案,在低数据场景中优于传统方法. 这种人工智能方法通过对话互动来增强临床决策.
科学领域:
- 医疗保健中的人工智能
- 自然语言处理自然语言处理.
- 机器学习用于临床决策支持
背景情况:
- 大型语言模型 (LLM) 对疾病风险评估等医疗保健任务具有前景,提供了超越传统结构化数据方法的灵活性.
- 生成型的LLM可以在不需要编程专业知识的情况下应用于临床环境.
- 由LLM驱动的对话式人工智能为疾病风险分层提供了一种新的方法.
研究的目的:
- 评估生成的LLM (LLaMA2-7b,Flan-T5-xl) 用于预测COVID-19的严重程度.
- 开发使用聊天机器人交互的实时无代码风险评估解决方案.
- 将LLM性能与传统的机器学习分类器 (逻辑回归,XGBoost,随机森林) 进行比较.
主要方法:
- 从儿科COVID-19数据集中精细调整LLM,使用一些自然语言示例.
- 开发一个移动应用程序,通过临床医生与患者对话进行实时,无代码的风险评估.
- 使用曲线下的区域 (AUC) 与传统分类器进行LLM性能比较,并分析LLM注意层的可解释性.
主要成果:
- 生成型LLM表现出强的表现,特别是在低数据设置中 (例如,T0-3b-T在零射击中实现了AUC 0.75).
- 随着数据的增加,LLM与传统模型相比显示出具有竞争力或优异的性能 (例如,Flan-T5-xl-T在32次射击时达到AUC0.70).
- 移动应用程序通过基于注意力的功能重要性提供了实时评估和个性化见解.
结论:
- 生成型LLM是传统分类器的强有力的替代方案,特别是有限的标记数据.
- 基于LLM的交谈式人工智能为临床环境提供了适应性,可实现实时,个性化的评估,无需编码.
- 对疾病风险评估和临床决策支持的LLM应用进行进一步的研究是有必要的.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
07:14Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
Published on: December 23, 2025
相关概念视频
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...
Coronavirus
Coronaviruses, including the severe acute respiratory syndrome coronavirus (SARS-CoV), are enveloped viruses characterized by their single-stranded, positive-sense RNA genome and helical nucleocapsid structure. The hallmark of these viruses is their club-shaped spike (S) glycoproteins that protrude from the viral envelope, facilitating attachment to host cells. Typically, coronaviruses infect the upper respiratory tract, often causing mild or asymptomatic disease. However, certain strains like...
