临床实用且可解释的 ICU 死亡率预测深度学习模型及其外部验证。
A Clinically Practical and Interpretable Deep Model for ICU Mortality Prediction with External Validation.
机构信息
PingAn Health Technology, Beijing, China.
The General Hospital of the People's Liberation Army of China, Beijing, China.
出版信息
AMIA Annu Symp Proc. 2021 Jan 25;2020:629-637. eCollection 2020.
Deep learning models are increasingly studied in the field of critical care. However, due to the lack of external validation and interpretability, it is difficult to generalize deep learning models in critical care senarios. Few works have validated the performance of the deep learning models with external datasets. To address this, we propose a clinically practical and interpretable deep model for intensive care unit (ICU) mortality prediction with external validation. We use the newly published dataset Philips eICU to train a recurrent neural network model with two-level attention mechanism, and use the MIMIC III dataset as the external validation set to verify the model performance. This model achieves a high accuracy (AUC = 0.855 on the external validation set) and have good interpretability. Based on this model, we develop a system to support clinical decision-making in ICUs.
深度学习模型在重症监护领域的研究越来越多。然而，由于缺乏外部验证和可解释性，很难将深度学习模型推广到重症监护场景中。很少有工作使用外部数据集来验证深度学习模型的性能。为了解决这个问题，我们提出了一种具有临床实用性和可解释性的深度学习模型，用于重症监护病房（ICU）死亡率预测，并进行了外部验证。我们使用新发布的 Philips eICU 数据集来训练具有两级注意力机制的循环神经网络模型，并使用 MIMIC III 数据集作为外部验证集来验证模型性能。该模型具有较高的准确性（外部验证集的 AUC = 0.855）和良好的可解释性。基于该模型，我们开发了一个系统，以支持 ICU 中的临床决策。
Zotero 插件