Janssen Research and Development, LLC, 920 Route 202, Raritan, NJ, 08869, USA.
OHDSI Collaborators, Observational Health Data Sciences and Informatics (OHDSI), 622 West 168th Street, PH-20, New York, NY, 10032, USA.
Drug Saf. 2020 May;43(5):447-455. doi: 10.1007/s40264-020-00906-7.
In observational studies with mortality endpoints, one needs to consider how to account for subjects whose interventions appear to be part of 'end-of-life' care.
The objective of this study was to develop a diagnostic predictive model to identify those in end-of-life care at the time of a drug exposure.
We used data from four administrative claims datasets from 2000 to 2017. The index date was the date of the first prescription for the last new drug subjects received during their observation period. The outcome of end-of-life care was determined by the presence of one or more codes indicating terminal or hospice care. Models were developed using regularized logistic regression. Internal validation was through examination of the area under the receiver operating characteristic curve (AUC) and through model calibration in a 25% subset of the data held back from model training. External validation was through examination of the AUC after applying the model learned on one dataset to the three other datasets.
The models showed excellent performance characteristics. Internal validation resulted in AUCs ranging from 0.918 (95% confidence interval [CI] 0.905-0.930) to 0.983 (95% CI 0.978-0.987) for the four different datasets. Calibration results were also very good, with slopes near unity. External validation also produced very good to excellent performance metrics, with AUCs ranging from 0.840 (95% CI 0.834-0.846) to 0.956 (95% CI 0.952-0.960).
These results show that developing diagnostic predictive models for determining subjects in end-of-life care at the time of a drug treatment is possible and may improve the validity of the risk profile for those treatments.
在以死亡率为终点的观察性研究中，需要考虑如何处理那些干预措施似乎属于“临终关怀”的患者。
本研究旨在开发一种诊断预测模型，以识别在药物暴露时处于临终关怀状态的患者。
我们使用了来自四个行政索赔数据集的数据，这些数据的时间范围从 2000 年到 2017 年。索引日期是最后一次新药物处方的日期，是在观察期间患者接受的。临终关怀的结果通过存在一个或多个表示终末期或临终关怀的代码来确定。使用正则逻辑回归方法开发模型。内部验证是通过检查接收者操作特征曲线（ROC）下的面积（AUC）和在从模型训练中保留的 25%数据子集进行模型校准来实现的。外部验证是通过将在一个数据集中学习的模型应用于其他三个数据集来检查 AUC 来实现的。
模型表现出了优异的性能特征。内部验证产生的 AUC 值范围为 0.918（95%置信区间[CI]为 0.905-0.930）至 0.983（95% CI 为 0.978-0.987），适用于四个不同的数据集。校准结果也非常好，斜率接近 1。外部验证也产生了非常好到优秀的性能指标，AUC 值范围为 0.840（95% CI 为 0.834-0.846）至 0.956（95% CI 为 0.952-0.960）。
这些结果表明，开发用于确定药物治疗时处于临终关怀状态的患者的诊断预测模型是可能的，并且可能会提高这些治疗方法的风险概况的有效性。
