文献速递流行病学与生物统计真实世界研究与卫生经济

纳入病前功能状态的ICU院内死亡预测模型改善了性能与内部效度

Mortality prediction in intensive care units including premorbid functional status improved performance and internal validity.
PubMed 文献 · J Clin Epidemiol · 2021-11-22

研究基于芬兰、爱沙尼亚、瑞士多中心ICU队列2015至2017年61,224例患者数据,构建纳入年龄、改良简化急性生理评分II、入院类型、病前功能状态和诊断的层次logistic回归模型预测院内死亡,模型AUC为0.886(95%CI 0.882-0.890),校准斜率1.01(95%CI 0.99-1.03),平均校准-0.004(95%CI -0.035至0.027),各ICU间性能指标异质性较高(I²=53.4%-84.7%)。

要点

  • 模型纳入病前功能状态等预测因子,AUC为0.886(95%CI 0.882-0.890)。
  • 模型内部效度和地理区分度可迁移性良好,校准斜率1.01。
  • 各ICU间性能指标存在显著异质性(I²=53.4%-84.7%)。

核心结论

  • 新框架评估预测模型性能可为判断模型效度及未来改编使用提供关键信息。

研究设计与样本

  • 国际多中心ICU队列研究,数据来自芬兰、爱沙尼亚、瑞士2015至2017年数据库,纳入61,224例ICU患者。
  • 采用层次logistic回归模型,纳入年龄、改良简化急性生理评分II、入院类型、病前功能状态和诊断作为分组变量。
  • 采用合并与Meta分析交叉验证方法评估时间与地理可迁移性。

主要发现

  • ICU患者院内死亡率为10.6%。
  • 模型AUC为0.886(95%CI 0.882-0.890),校准斜率1.01(95%CI 0.99-1.03),平均校准-0.004(95%CI -0.035至0.027)。
  • 模型内部效度和地理区分度可迁移性很好,但各ICU间性能指标存在显著异质性(I²=53.4%-84.7%)。

临床怎么用

  • 原文未据此给出临床推荐。

局限性

  • 各ICU间性能指标存在显著异质性(I²=53.4%-84.7%)。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: Prognostic models are key for benchmarking intensive care units (ICUs). They require up-to-date predictors and should report transportability properties for reliable predictions. We developed and validated an in-hospital mortality risk prediction model to facilitate benchmarking, quality assurance, and health economics evaluation. STUDY DESIGN AND SETTING: We retrieved data from the database of an international (Finland, Estonia, Switzerland) multicenter ICU cohort study from 2015 to 2017. We used a hierarchical logistic regression model that included age, a modified Simplified Acute Physiology Score-II, admission type, premorbid functional status, and diagnosis as grouping variable. We used pooled and meta-analytic cross-validation approaches to assess temporal and geographical transportability. RESULTS: We included 61,224 patients treated in the ICU (hospital mortality 10.6%). The developed prediction model had an area under the receiver operating characteristic curve 0.886, 95% confidence interval (CI) 0.882-0.890; a calibration slope 1.01, 95% CI (0.99-1.03); a mean calibration -0.004, 95% CI (-0.035 to 0.027). Although the model showed very good internal validity and geographic discrimination transportability, we found substantial heterogeneity of performance measures between ICUs (I-squared: 53.4-84.7%). CONCLUSION: A novel framework evaluating the performance of our prediction model provided key information to judge the validity of our model and its adaptation for future use.

来源:J Clin Epidemiol,查看原文。版权归原作者所有。

引用

  1. Moser A, Reinikainen M, Jakob SM, et al. Mortality prediction in intensive care units including premorbid functional status improved performance and internal validity. J Clin Epidemiol. 2021. PMID: 34823021. doi:10.1016/j.jclinepi.2021.11.028

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。