可解释的机器学习和在线计算器可以预测重症监护室心力衰竭死亡率
An-Tian Chen1,2,3, Yuhui Zhang2, Jian Zhang2,4
1Department of Cardiology, Fuwai Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing, China.
ESC heart failure
|September 20, 2024
概括
这项研究开发了可解释的机器学习模型,包括线性判别分析和名图,以预测重症监护室 (ICU) 心力衰竭 (HF) 患者的死亡率. 这些工具增强了临床决策,以获得更好的患者结果.
科学领域:
- * 计算医学和人工智能
- * 心血管医学和重症监护
背景情况:
- *预测心力衰竭患者在重症监护室 (ICU) 的死亡率对于及时干预和资源分配至关重要.
- *现有的预测模型往往缺乏透明度,阻碍了临床信任和采用.
研究的目的:
- * 开发和验证可解释的机器学习模型,用于预测患有HF的ICU患者的28天死亡率.
- *根据这些模型创建用户友好的临床工具,以便在实践中应用.
主要方法:
- *利用密集护理IV (MIMIC-IV) 数据库的医疗信息中心进行模型开发和eICU数据库进行外部验证.
- * 采用最小绝对收缩和选择运算符 (LASSO) 回归来进行特征选择,从最初的75个中确定了44个关键预测因素.
- * 开发并比较了15个机器学习模型,其中线性差异分析 (LDA) 显示出卓越的性能,并利用Shapley添加式解释 (SHAP) 进行模型解释.
主要成果:
- * LDA模型在外部验证中实现了高精度 (0.8354培训,0.8563测试) 和0.79的曲线下面面积 (AUC).
- *一个基于逻辑回归的名图,包含14个特征,表现出强大的预测性能,AUC为0.852 (训练) 和0.770 (外部验证).
- *SHAP分析提供了对驱动死亡率预测的因素的见解,提高了模型的透明度.
结论:
- * 开发了一种强大且可解释的LDA模型和临床名谱,用于预测ICU心力衰竭患者的死亡率.
- * 通过SHAP值来解释LDA模型的可解释性增加了其临床实用性和可靠性.
- *这些预测工具的在线可访问性有助于将其整合到常规临床实践中,以改善患者管理.
更多相关视频
06:16Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
372
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
01:24Kaplan-Meier Approach
107
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
107
01:20Actuarial Approach
64
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
64
01:11Hazard Rate
92
The hazard rate, also known as the hazard function or failure rate, is a statistical measure used to describe the instantaneous rate at which an event occurs, given that the event has not yet happened. From a probabilistic perspective, it represents the likelihood that a subject will experience the event in a very small time interval, conditional on surviving up to the beginning of that interval. In terms of frequency, the hazard rate can be viewed as the ratio of the number of events to the...
92
01:18Introduction To Survival Analysis
189
Survival analysis is a statistical method used to study time-to-event data, where the "event" might represent outcomes like death, disease relapse, system failure, or recovery. A unique feature of survival data is censoring, which occurs when the event of interest has not been observed for some individuals during the study period. This requires specialized techniques to handle incomplete data effectively.
The primary goal of survival analysis is to estimate survival time—the time...
The primary goal of survival analysis is to estimate survival time—the time...
189
01:20Comparing the Survival Analysis of Two or More Groups
158
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
158