Clinical Data Center, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Hangzhou, China.
The College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China.
J Am Med Inform Assoc. 2022 Dec 13;30(1):94-102. doi: 10.1093/jamia/ocac202.
Acute kidney injury (AKI) is a common complication after pediatric cardiac surgery, and the early detection of AKI may allow for timely preventive or therapeutic measures. However, current AKI prediction researches pay less attention to time information among time-series clinical data and model building strategies that meet complex clinical application scenario. This study aims to develop and validate a model for predicting postoperative AKI that operates sequentially over individual time-series clinical data.
A retrospective cohort of 3386 pediatric patients extracted from PIC database was used for training, calibrating, and testing purposes. A time-aware deep learning model was developed and evaluated from 3 clinical perspectives that use different data collection windows and prediction windows to answer different AKI prediction questions encountered in clinical practice. We compared our model with existing state-of-the-art models from 3 clinical perspectives using the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision-recall curve (PR AUC).
Our proposed model significantly outperformed the existing state-of-the-art models with an improved average performance for any AKI prediction from the 3 evaluation perspectives. This model predicted 91% of all AKI episodes using data collected at 24 h after surgery, resulting in a ROC AUC of 0.908 and a PR AUC of 0.898. On average, our model predicted 83% of all AKI episodes that occurred within the different time windows in the 3 evaluation perspectives. The calibration performance of the proposed model was substantially higher than the existing state-of-the-art models.
This study showed that a deep learning model can accurately predict postoperative AKI using perioperative time-series data. It has the potential to be integrated into real-time clinical decision support systems to support postoperative care planning.
急性肾损伤（AKI）是儿科心脏手术后常见的并发症，AKI 的早期检测可能允许及时采取预防或治疗措施。然而，目前的 AKI 预测研究较少关注时间序列临床数据中的时间信息和符合复杂临床应用场景的模型构建策略。本研究旨在开发和验证一种针对术后 AKI 的模型，该模型可对个体时间序列临床数据进行顺序操作。
使用从 PIC 数据库中提取的 3386 名儿科患者的回顾性队列进行训练、校准和测试。从 3 个临床角度开发和评估了一个具有时间意识的深度学习模型，该模型使用不同的数据采集窗口和预测窗口来回答临床实践中遇到的不同 AKI 预测问题。我们从 3 个临床角度使用接收者操作特征曲线下面积（ROC AUC）和精度-召回曲线下面积（PR AUC）比较了我们的模型与现有最先进模型的性能。
我们提出的模型在任何 AKI 预测方面的平均性能均显著优于现有最先进的模型，在 3 个评估角度中，使用术后 24 小时收集的数据预测所有 AKI 发作的平均性能为 91%，ROC AUC 为 0.908，PR AUC 为 0.898。平均而言，我们的模型预测了 3 个评估角度中不同时间窗口内发生的所有 AKI 发作的 83%。与现有最先进的模型相比，该模型的校准性能有了显著提高。
本研究表明，深度学习模型可以使用围手术期时间序列数据准确预测术后 AKI。它有可能集成到实时临床决策支持系统中，以支持术后护理计划。
