论文标题
使用自学转移学习的生理信号预测不良手术事件
Forecasting adverse surgical events using self-supervised transfer learning for physiological signals
论文作者
论文摘要
每年每年在世界各地进行数亿外科手术程序，该程序产生了包括时间序列的生理信号的普遍类型的电子健康记录（EHR）数据。在这里，我们提出了一种可转移的嵌入方法（即一种将时间序列信号转换为预测机器学习模型的输入特征的方法）命名阶段（生理信号嵌入），使我们能够更准确地预测基于生理信号的不良外科手术结果。我们在两个手术室（OR）数据集（OR）数据集（ICU）数据集中的50,000多个手术中，通过一分钟的EHR数据评估了阶段。阶段优于其他最先进的方法，例如在原始数据和梯度增强的树木中训练的长期术语记忆网络，以预测五种不同的结果：低氧血症，低脑，低血压，低血压，高血压和苯肾上腺素的给药。在转移学习环境中，我们在一个数据集中训练嵌入模型，然后嵌入信号并预测看不见的数据中的不良事件，与常规方法相比，相比，相比，相比，相比，相比，以较低的计算成本实现了更高的预测准确性。最后，鉴于在临床应用中理解模型的重要性，我们证明可以使用局部特征归因方法来解释阶段，并验证我们的预测模型。
Hundreds of millions of surgical procedures take place annually across the world, which generate a prevalent type of electronic health record (EHR) data comprising time series physiological signals. Here, we present a transferable embedding method (i.e., a method to transform time series signals into input features for predictive machine learning models) named PHASE (PHysiologicAl Signal Embeddings) that enables us to more accurately forecast adverse surgical outcomes based on physiological signals. We evaluate PHASE on minute-by-minute EHR data of more than 50,000 surgeries from two operating room (OR) datasets and patient stays in an intensive care unit (ICU) dataset. PHASE outperforms other state-of-the-art approaches, such as long-short term memory networks trained on raw data and gradient boosted trees trained on handcrafted features, in predicting five distinct outcomes: hypoxemia, hypocapnia, hypotension, hypertension, and phenylephrine administration. In a transfer learning setting where we train embedding models in one dataset then embed signals and predict adverse events in unseen data, PHASE achieves significantly higher prediction accuracy at lower computational cost compared to conventional approaches. Finally, given the importance of understanding models in clinical applications we demonstrate that PHASE is explainable and validate our predictive models using local feature attribution methods.
