临床预测模型中的泛化性:测量指标变量的利与弊
该研究基于两家三级学术医院三个回顾性队列(普通住院和重症监护),构建预测升压药启动的logistic回归模型,比较看似客观的临床变量与反映测量时效的主观变量。普通住院队列升压药使用率0.9%,两个重症队列分别为12.4%和11.5%。联合两类变量在样本内表现最佳,预测4小时内升压药启动的C统计量分别为0.862、0.822和0.889。仅用测量时效变量外部效度差,但校正后有助于调整两院差异并提升临床变量模型的泛化性。
要点
- 普通住院队列升压药使用率仅0.9%,两个重症队列分别为12.4%和11.5%,模型性能需分场景解读。
- 联合临床变量与测量时效变量在样本内预测4小时内升压药启动的C统计量为0.862、0.822和0.889。
- 仅用测量时效变量的模型外部效度差,不能单独用于跨中心预测。
- 测量时效变量可校正医院间实践差异,开发时纳入、验证时舍弃可获得更泛化的模型。
- 该研究为回顾性队列建模,干预为无,结论需前瞻性验证后方可用于床旁决策。
适用人群与场景
- 三个回顾性队列来自两家地理区域不同的三级学术医院,涵盖普通住院和重症监护场景。
- 纳入成人患者(住院时年龄≥18岁),住院或ICU入住时长6至600小时,且住院或ICU入住前6小时内未接受升压药。
诊断标准与关键阈值
- 预测目标为升压药启动,具体评估4小时内升压药启动的预测性能。
- 模型变量分两类:看似客观的临床变量(生命体征和实验室测量)与更主观的表示测量时效的变量。
处置流程与药物剂量
- 原文未提及
红旗征与不能漏的情况
- 原文未提及
研究设计与关键结果
- 研究设计为回顾性队列建模,无干预,在三个队列分别开发模型并在本队列内部验证及在另外两个队列外部验证。
- 升压药使用率:普通住院队列0.9%,两个重症监护队列分别为12.4%和11.5%。
- 联合两类变量的模型样本内表现最佳,预测4小时内升压药启动的C统计量分别为0.862(95%CI 0.844-0.879)、0.822(95%CI 0.793-0.852)和0.889(95%CI 0.880-0.898)。
- 仅使用表示测量时效的主观变量模型外部效度差。
- 测量时效变量有助于校正两家医院间差异,使基于临床变量的模型更泛化。
证据类型、等级与局限
- 证据类型为回顾性队列研究,无干预,非随机对照试验。
- 局限:回顾性设计、仅两家医院三个队列、样本量未在原文摘要中给出、模型需前瞻性验证。
对床旁实践的改变
- 开发跨中心临床预测模型时,应考虑测量时效等实践特异性变量:开发阶段纳入以校正中心间差异,验证阶段舍弃以评估泛化性。
- 仅用测量时效变量的模型不宜直接用于跨中心床旁预测升压药启动。
- 该研究为回顾性建模,模型性能数值不能直接作为床旁决策阈值,需前瞻性验证。
指南或共识出处
- 原文未提及
以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。
英文原文(摘要)· 点击展开
OBJECTIVE: Specific factors affecting generalizability of clinical prediction models are poorly understood. Our main objective was to investigate how measurement indicator variables affect external validity in clinical prediction models for predicting onset of vasopressor therapy.
DESIGN: We fit logistic regressions on retrospective cohorts to predict vasopressor onset using two classes of variables: seemingly objective clinical variables (vital signs and laboratory measurements) and more subjective variables denoting recency of measurements.
SETTING: Three cohorts from two tertiary-care academic hospitals in geographically distinct regions, spanning general inpatient and critical care settings.
PATIENTS: Each cohort consisted of adult patients (age greater than or equal to 18 yr at time of hospitalization), with lengths of stay between 6 and 600 hours, and who did not receive vasopressors in the first 6 hours of hospitalization or ICU admission. Models were developed on each of the three derivation cohorts and validated internally on the derivation cohort and externally on the other two cohorts.
INTERVENTIONS: None.
MEASUREMENTS AND MAIN RESULTS: The prevalence of vasopressors was 0.9% in the general inpatient cohort and 12.4% and 11.5% in the two critical care cohorts. Models utilizing both classes of variables performed the best in-sample, with C-statistics for predicting vasopressor onset in 4 hours of 0.862 (95% CI, 0.844-0.879), 0.822 (95% CI, 0.793-0.852), and 0.889 (95% CI, 0.880-0.898). Models solely using the subjective variables denoting measurement recency had poor external validity. However, these practice-driven variables helped adjust for differences between the two hospitals and led to more generalizable models using clinical variables.
CONCLUSIONS: We developed and externally validated models for predicting the onset of vasopressors. We found that practice-specific features denoting measurement recency improved local performance and also led to more generalizable models if they are adjusted for during model development but discarded at validation. The role of practice-specific features such as measurement indicators in clinical prediction modeling should be carefully considered if the goal is to develop generalizable models.
参考来源
- Futoma J, Simons M, Doshi-Velez F, et al. Generalization in Clinical Prediction Models: The Blessing and Curse of Measurement Indicator Variables. Crit Care Explor. 2021. PMID: 34235453. doi:10.1097/CCE.0000000000000453
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。