Emerging evidence suggests that clinical prediction models that use repeated (time-varying) measurements within each patient may have higher predictive accuracy than models that use patient information from a single measurement. To determine the breadth of the published literature reporting the development of clinical prediction models in children that use time-varying predictors. MEDLINE, EMBASE and Cochrane databases. We included studies reporting the development of a multivariable clinical prediction model in children, with or without validation, to predict a repeatedly measured binary or time-to-event outcome and utilizing at least one repeatedly measured predictor. We categorized included studies by the method used to model time-varying predictors. Of 99 clinical prediction model studies that had a repeated measurements data structure, only 27 (27%) used methods that incorporated the repeated measurements as time-varying predictors in a single model. Among these 27 time-varying prediction model studies, we grouped model types into nine categories: time-dependent Cox regression, generalized estimating equations, random effects model, landmark model, joint model, neural network, K-nearest neighbor, support vector machine and tree-based algorithms. Where there was comparison of time-varying models to single measurement models, using time-varying predictors improved predictive accuracy. Various methods have been used to develop time-varying prediction models in children, but there is a paucity of pediatric time-varying models in the literature. Incorporating time-varying covariates in pediatric prediction models may improve predictive accuracy. Future research in pediatric prediction model development should further investigate whether incorporation of time-varying covariates improves predictive accuracy. Of 99 clinical prediction model studies that had a repeated measurements data structure, only 27% used analytical methods that incorporated time-varying covariates. Future research in pediatric prediction model development should further investigate whether incorporation of time-varying covariates improves predictive accuracy. We summarized methods used to develop pediatric clinical prediction models that incorporate repeated measurements with time-varying covariates. Researchers may use the findings of this review to identify appropriate analytical methods for developing a time-varying prediction model in pediatric care.

中文翻译：

---

使用时变协变量重复测量的儿童临床预测模型：范围界定审查

新的证据表明，使用每个患者重复（随时间变化）测量的临床预测模型可能比使用单次测量的患者信息的模型具有更高的预测准确性。确定报告使用时变预测因子的儿童临床预测模型开发的已发表文献的广度。 MEDLINE、EMBASE 和 Cochrane 数据库。我们纳入了报告儿童多变量临床预测模型开发的研究，无论是否经过验证，以预测重复测量的二元或事件时间结果，并利用至少一个重复测量的预测因子。我们根据用于模拟时变预测变量的方法对纳入的研究进行了分类。在 99 项具有重复测量数据结构的临床预测模型研究中，只有 27 项 (27%) 使用将重复测量作为时变预测因子合并到单个模型中的方法。在这27个时变预测模型研究中，我们将模型类型分为九类：时变Cox回归、广义估计方程、随机效应模型、地标模型、联合模型、神经网络、K近邻、支持向量机和基于树的算法。在将时变模型与单一测量模型进行比较的情况下，使用时变预测变量可以提高预测准确性。人们已经使用各种方法来开发儿童时变预测模型，但文献中很少有儿科时变模型。在儿科预测模型中纳入时变协变量可能会提高预测准确性。儿科预测模型开发的未来研究应进一步研究时变协变量的结合是否可以提高预测准确性。在 99 项具有重复测量数据结构的临床预测模型研究中，只有 27% 使用包含时变协变量的分析方法。儿科预测模型开发的未来研究应进一步研究时变协变量的结合是否可以提高预测准确性。我们总结了用于开发儿科临床预测模型的方法，该模型将重复测量与时变协变量结合起来。研究人员可以利用本次综述的结果来确定适当的分析方法，以开发儿科护理中的时变预测模型。