相关实验视频
Updated: Apr 15, 2026

Breath Collection from Children for Disease Biomarker Discovery
Published on: February 14, 2019
基于电子健康记录的小儿急性呼吸窘迫综合征亚现型分类器模型的开发和验证
Daniel R Balcarcel1, Mark V Mai2, Sanjiv D Mehta1
1Department of Anesthesiology and Critical Care Medicine, Children's Hospital of Philadelphia and University of Pennsylvania, Philadelphia, PA.
机器学习可以使用电子健康记录 (EHR) 数据识别儿科急性呼吸困扰综合征 (PARDS) 亚现象. 这种方法可以准确区分高炎症和低炎症PARDS,帮助临床决策.
科学领域:
- 儿科重症监护医药 儿科重症监护医药
- 机器学习在医疗保健中的应用.
- 生物标志物的发现和验证.
背景情况:
- 儿科急性呼吸困扰综合征 (PARDS) 是一种具有明显亚现象的严重疾病.
- 基于生物标志物的PARDS亚型表现出临床相关性.
- 仅从电子健康记录 (EHR) 数据中识别这些子类型是具有挑战性的.
研究的目的:
- 评估在EHR数据上使用机器学习来识别PARDS亚型的可行性.
- 为了确定是否可以使用易于获得的EHR变量来分类超炎和低炎PARDS亚型.
主要方法:
- 从2014-2022年对PARDS患者的回顾性分析.
- 使用血清生物标志物来定义衍生队列中的子类型的潜在类别分析.
- 在165个EHR衍生变量上训练机器学习模型,以预测子类型.
- 在单独的队列中使用AUC,灵敏度和特异性等性能指标验证模型.
主要成果:
- 一个机器学习模型成功地高准确地分类了PARDS子类型.
- 基于EHR的分类器在验证队列中实现了0.93的AUC.
- 仅使用五个实验室值的节模型表现出强的性能 (AUC 0.92).
结论:
- 生物标志物定义的PARDS亚类型可以在诊断后24小时内使用EHR数据识别.
- 这种机器学习方法显示出作为PARDS亚型的非侵入性方法的希望.
- 需要进一步的多中心验证才能确定临床效用.
更多相关视频
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
06:22Surfactant Depletion Combined with Injurious Ventilation Results in a Reproducible Model of the Acute Respiratory Distress Syndrome ARDS
Published on: April 7, 2021
相关概念视频
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
Asthma-II: Pathophysiology and Classification
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include: