开发和验证一个Nomogram预测模型用于心脏骤停患者的住院死亡率:一个回顾性研究
Peifeng Ni1,2, Shurui Xu1,2, Weidong Zhang2,3
1Department of Critical Care Medicine, Zhejiang University School of Medicine, 310058 Hangzhou, Zhejiang, China.
Reviews in cardiovascular medicine
|May 12, 2025
概括
这项研究开发了一个名图表来预测心脏骤停患者的死亡风险. 该模型使用LASSO回归,显示出强大的准确性和改善患者结果的临床实用性.
科学领域:
- 心脏病学 心脏病学
- 关键护理医学 关键护理医学
- 医疗信息学 医疗信息学
背景情况:
- 心脏骤停 (CA) 具有很高的死亡率,需要准确的预后评估,以有效的临床管理.
- 开发预测工具对于优化CA患者治疗策略至关重要.
研究的目的:
- 开发和验证一种临床上适用的名谱,用于预测心脏骤停患者在医院内死亡风险.
- 确定导致CA患者死亡的独立风险因素.
主要方法:
- 从两个医院的996名CA患者的临床数据回顾性收集.
- 使用LASSO回归,RFE和XGBoost进行变量选择和模型开发.
- 使用培训,内部和外部队列的验证预测模型,通过ROC曲线和AUC评估区分能力.
主要成果:
- 拉索回归模型表现出优异的性能,AUC为0.81 (训练) 和0.85 (内部验证),表现优于RFE和XGBoost.
- 对LASSO模型的外部验证结果为AUC为0.84.
- 最终的诺米图包含了关键预测指标:年龄,高血压,停血原因,初始心律,血管活性药物,CRRT,温度,BUN,乳酸盐和SOFA分数.
结论:
- 使用LASSO回归开发了一个强大的名图,用于预测CA患者的住院死亡率.
- 诺米图表表现出强大的区分能力和实际的临床实用性.
- 这种工具可以帮助优化临床决策和心脏骤停后的患者管理.
相关概念视频
01:23Dosage Regimen Designs: Nomograms and Tabulations
Nomograms and tabulations are vital tools used by clinicians to design accurate and individualized dosage regimens. These instruments provide a straightforward method for adjusting dosages based on individual patient characteristics, including age, weight, and physiological condition. The foundation of a drug's nomogram is population pharmacokinetic data collected and analyzed using specific models. This data simplifies complex equations, presenting them diagrammatically or tabularly for easy...
01:20Comparing the Survival Analysis of Two or More Groups
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 Cox...