相关实验视频

Updated: May 21, 2025

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

基于大型语言模型的早期败血症预测系统的开发和未来实施

Supreeth P Shashikumar¹, Sina Mohammadi¹, Rishivardhan Krishnamoorthy¹

¹Division of Biomedical Informatics, UC San Diego, San Diego, USA.

medRxiv : the preprint server for health sciences

|March 31, 2025

概括

一个新的AI模型,COMPOSER-LLM,使用临床笔记来改善早期败血症预测. 这种方法通过分析非结构化数据来提高准确性,从而使重症监护机构的患者获得更好的治疗结果.

科学领域:

医疗信息学医疗信息学
人工智能在医学中的应用
关键护理医学关键护理医学

背景情况:

败血症是一种危及生命的疾病,死亡率高.
早期检测和干预对于改善患者的治疗结果至关重要.
现有的计算模型往往缺乏来自非结构化临床笔记的上下文信息.

研究的目的:

引入 COMPOSER-LLM,这是一个与 COMPOSER 模型集成的开源大型语言模型 (LLM).
通过利用非结构化临床数据来增强早期败血症预测.
通过评估高不确定性病例中的败血症模仿者来提高败血症预测的准确性.

主要方法:

大型语言模型 (LLM) 与 COMPOSER 模型的集成.
使用非结构化的临床笔记来提取上下文信息.
对2500名患者接触的评估和前性验证.

主要成果:

COMPOSER-LLM获得了72.1%的灵敏度,52.9%的PPV和61.0%的F1得分.
证明了低误报率为0.0087每患者小时.
在败血症预测准确性方面表现优于独立的作曲家模型.

结论:

将LLM与传统模型集成,显著提高了败血症的预测性能.
从临床笔记中利用非结构化数据是改善医疗分析的关键.
COMPOSER-LLM显示出潜在的临床实用性,其中62%的假阳性结果表明细菌感染.

更多相关视频

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

相关概念视频

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis: