基于ICD-10的机器学习方法可以预测伊朗COVID-19患者在重症监护室的入院需求:一个横截面研究
Zahra Karimi1, Jaleh S Malak2, Amirhossein Aghakhani1
1Department of Epidemiology and Biostatistics, School of Public Health Tehran University of Medical Sciences Tehran Iran.
Health science reports
|September 4, 2024
概括
机器学习模型可以预测COVID-19患者的重症监护室 (ICU) 入院情况. 纯粹的贝叶斯模型表现最好,有助于早期识别高风险个体,以减少死亡率.
科学领域:
- 医疗信息学 医疗信息学
- 计算生物学 计算生物学
- 流行病学 流行病学
背景情况:
- 及时识别需要进入重症监护室 (ICU) 的患者对于管理COVID-19至关重要.
- 预测模型可以帮助在流行病期间进行资源配置和患者管理.
研究的目的:
- 为了比较各种机器学习算法在预测COVID-19患者ICU入院的有效性.
- 为了确定关键预测因子与ICU入院在这个患者队列.
主要方法:
- 分析了来自六家学术医院的44112名COVID-19患者的队列.
- 随机森林被用于特征选择,确定年龄和并发症作为重要的预测因素.
- 开发和评估了六种机器学习模型 (支持向量机,天真贝叶斯,逻辑回归,轻GBM,决策树,K-最近邻居).
主要成果:
- 年龄,心脏病,高血压,糖尿病和其他并发症是ICU入院的重要预测因素.
- 所有评估的模型都实现了曲线下的面积 (AUC) 大于0.60.
- 原始贝叶斯模型表现出最高的预测性能,AUC为0.71.
结论:
- 机器学习模型,特别是Naïve Bayes和轻GBM,在预测COVID-19患者的ICU入院方面表现有希望.
- 使用这些模型早期识别高风险患者可能会降低死亡率和发病率.
- 这些计算工具可以在紧急情况下支持临床决策.
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
7.0K
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
14.4K
相关概念视频
01:29Nursing Interventions II: Selecting and Classifying the Nursing Interventions
2.1K
Creating and executing a nursing diagnosis helps nurses plan care and guide patient, family, and community interventions. They are developed based on a patient's physical evaluation and support measuring the outcomes. It is not recommended to select random interventions throughout the planning process. Instead, consider the following six essential factors when choosing interventions:
2.1K
01:18Steps in Outbreak Investigation
114
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:
114