选择性预测因子可用性下嵌套预测模型的非不变性
Non-Invariance in Nested Prediction Models under Selective Predictor Availability
AI总结：
本研究以嵌套预测模型为框架，剖析选择性测量预测因子对临床预测模型的影响，阐明受限模型非不变性的分解机制及插补偏差的传递规律，并以肾衰风险方程为例验证该框架。
AI中文摘要：
预测因子的选择性测量在常规收集的健康数据中十分常见。本研究采用嵌套预测模型作为框架，以表征选择性测量预测因子的后果：受限模型定义于目标人群，扩展模型则纳入选择性测量的预测因子，定义于选定人群。研究表明，选定患者与目标人群之间受限模型的非不变性可分解为三个部分：额外预测因子的遗漏、潜在残留非不变性，以及二者的交互作用。研究将该框架扩展至通过多重选择途径测量的预测因子，此类预测因子会产生碰撞结构。进一步研究显示，基于选定人群中额外预测因子的条件分布进行的插补，会将受限模型的非不变性以插补偏差的形式传递至经插补的扩展模型。本研究以肾衰风险方程（Kidney Failure Risk Equation）为例进行说明，该方程中白蛋白-肌酐比值（albumin-to-creatinine ratio）在常规临床实践中为选择性测量指标。该框架为理解选择性预测因子测量如何影响使用常规收集健康数据开发和验证临床预测模型提供了正式基础。
英文摘要：
We used nested models as a framework for characterising the consequences of a selectively measured predictor in clinical prediction models. In this framework, a model containing predictors available in the target population is referred to as the restricted model, while the extended model additionally includes a selectively measured predictor. We show that non-invariance in the restricted model between selected patients and the target population decomposes into components due to omission of the additional predictor, potential residual non-invariance, and their interaction. This framework is extended to a predictor measured via multiple routes of selection resulting in collider structures. We further show that imputation based on the conditional distribution of the additional predictor in the selected population transfers the restricted-model non-invariance to the imputed extended model as imputation bias. We illustrate the proposed framework using the Kidney Failure Risk Equation, where albumin-to-creatinine ratio (ACR) is selectively measured in routine clinical practice. In this application, ACR availability was associated with age, sex, eGFR and diabetes, and the restricted three-variable model showed evidence of non-invariance. The framework provides a formal basis for understanding how selective predictor measurement affects generalisability of clinical prediction models using routinely collected health data.
