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.
翻译:每年全世界都会有数亿个外科手术程序,这产生了一种流行的电子健康记录(EHR)数据,包括时间序列生理信号。在这里,我们提出了一个可转移的嵌入方法(即将时间序列信号转换成预测机器学习模型投入功能的方法),名为PHASE(PHSE)(PHSiologicAl信号嵌入器),使我们能够根据生理信号更准确地预测不良外科手术结果。我们根据两个手术室(OR)的50 000多个手动手术数据逐分钟地对EHR数据进行评估。我们从两个手术室(OR)数据集和病人留在一个强化护理单位(ICU)数据集中的50 000多个手动手术数据进行实时评价。PHASE比其他最先进的嵌入方法(即将时间序列信号转换成预测机器学习模型的输入功能)要好得多,例如经过原始数据培训的长期短期记忆网络和按手动特征训练的梯状增生树等,从而使我们能够更准确地预测五个不同的结果:低血氧、低卡本、低血压、高血压和苯激素管理。在转移学习环境中将模型嵌入一个数据集,然后将信号输入,预测在看不见数据中预测中,最后通过可测算方法,我们对常规数据进行高的精确度进行更高的分析。