相关实验视频

Updated: Jun 11, 2025

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide

Published on: January 15, 2017

一个基于大型语言模型的临床决策支持系统,用于在急诊室识别昏迷:临床工作流集成框架

Alessandro Giaj Levra¹, Mauro Gatti², Roberto Mene³

¹Department of Cardiovascular Medicine, Humanitas Research Hospital, IRCCS, Rozzano, Milan, Italy; Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy.

European journal of internal medicine

|September 28, 2024

概括

大型语言模型 (LLM) 可以通过分析电子医疗记录来识别急诊室的昏迷. 这些模型在区分昏迷和其他暂时失去意识事件方面表现出很高的准确性.

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
临床决策支持临床决策支持

背景情况:

区分昏迷和暂时失去意识 (TLoC) 在急诊室 (ED) 提出了诊断挑战.
自然语言处理 (NLP) 提供了一种方法来分析电子医疗记录 (EMR) 中的非结构化自由文本.

研究的目的:

开发和评估大型语言模型 (LLM) 以在ED中准确识别同步.
提出一个框架,将这些LLM整合到临床工作流程中,以改善诊断支持.

主要方法:

在连续EMR上使用意大利语和多语言双向编码器表示 (BERT) 的两个模型的开发.
训练一个仅使用分拣笔记的"分拣"模型和一个包含病史数据的"记忆录"模型.
在15098个 (意大利BERT) 和15222个 (多个BERT) EMR上测试模型,使用AUC和校准图表评估性能.

主要成果:

与"选"模型相比",解剖学"模型实现了更高的AUC (0.98为意大利BERT,0.97为多个BERT),而"选"模型 (0.95为意大利BERT,0.94为多个BERT).
即使在EMR中没有明确声明,LLM也成功地识别了昏迷,并识别了前兆症状.
这两种模型都表现出高的辨别能力,从临床笔记中识别昏患者.

结论:

基于LLM的眼识别模型,特别是"遗传记"模型,在ED环境中表现出高精度和辨别能力.
这些模型可以作为有价值的工具,帮助医生从TLoC的其他原因中区分昏睡.
将LLM整合到临床工作流程中,有望提高诊断效率和对评估的准确性.

关键词:

人工智能的人工智能是人工智能.临床决策支持系统机器学习是机器学习.自然语言处理自然语言处理.昏迷症 (Syncope) 是一种昏迷的情况.

更多相关视频

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Published on: September 26, 2018

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

相关概念视频

Cardiopulmonary Resuscitation IV: Pharmacological Management

Cardiopulmonary Resuscitation IV: Pharmacological Management

Pharmacologic intervention is crucial in treating cardiac arrest patients during ACLS or Advanced Cardiovascular Life Support. The ACLS algorithms guide the administration of specific drugs based on the patient's cardiac arrest rhythm, which includes pulseless ventricular tachycardia (VT), ventricular fibrillation (VF), asystole, and pulseless electrical activity (PEA).EpinephrineIndication: Epinephrine is the first-line drug for all cardiac arrest rhythms.Mechanism of Action: Epinephrine...

Cardiopulmonary Resuscitation II: ACLS Airway Management

Cardiopulmonary Resuscitation II: ACLS Airway Management

Airway management is a key skill in emergency and critical care settings, as maintaining a clear airway is essential for adequate oxygenation and ventilation.Head Tilt-Chin Lift TechniqueThe head tilt-chin lift maneuver is an essential technique primarily used in patients without suspected cervical spine injuries. To perform this maneuver, one hand is placed on the patient’s forehead, and gentle pressure is applied backward to tilt the head. The fingertips of the other hand are positioned...