预测心力衰竭30天和1年的死亡率,使用保存的喷射分数 (HFpEF)
Ikgyu Shin1, Nilay Bhatt1, Alaa Alashi2
1Yale School of Public Health, New Haven, CT, USA.
medRxiv : the preprint server for health sciences
|November 1, 2024
概括
使用电子健康记录 (EHR) 数据的预测模型可以准确预测心力衰竭患者的死亡率. 年龄和NT-proBNP是关键预测因素,显示出临床使用的潜力.
科学领域:
- 心脏病学 心脏病学
- 医疗信息学 医疗信息学
- 医疗保健服务研究 医疗服务研究
背景情况:
- 保存喷射分数 (HFpEF) 的心力衰竭占所有心力衰竭病例的一半.
- 对于HFpEF的预测模型,特别是那些使用电子健康记录 (EHR) 数据的模型,并不成熟.
研究的目的:
- 开发和比较HFpEF患者30天和1年死亡率的预测模型.
- 用EHR数据利用传统和机器学习 (ML) 技术.
主要方法:
- 使用了MIMIC-IV EHR数据 (2008-2019) 对于患有HFpEF诊断的患者.
- 开发并交叉验证了七个ML模型 (SVC,物流回归,拉索,弹性网,随机森林,HGBC,XGBoost).
- 通过AUC和通过SHAP分析评估模型性能和特征重要性.
主要成果:
- 在研究队列中,30天死亡率为6.3%,一年死亡率为29.2%.
- 后勤回归显示了30天死亡率的强表现 (AUC 0.83).
- 随机森林 (AUC 0.79) 和HGBC (AUC 0.78) 在1年死亡率方面表现良好. 年龄和NT-proBNP被确定为关键预测因素.
结论:
- 来自EHR的模型可以预测HFpEF患者的死亡率,其表现与注册表或试验数据相比.
- 这些发现表明,基于EHR的HFpEF预测模型的临床实施具有重大潜力.
相关概念视频
Pathophysiology of Heart Failure
1.5K
Heart failure (HF) is a progressive syndrome involving ventricles that leads to inadequate cardiac output. It can be classified based on location and output or ejection fraction. Ejection fraction (EF) is an essential measurement in the diagnosis and surveillance of HF. Reduced EF corresponds to systolic heart failure (HFrEF). However, HF with preserved ejection fraction (HFpEF) is becoming increasingly prevalent. Also known as diastolic HF, this form of HF is related to aging. The...
1.5K
Actuarial Approach
63
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,...
63
Kaplan-Meier Approach
102
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,...
102


