The Laura P. and Leland K. Whittier Virtual Pediatric Intensive Care Unit, Children's Hospital Los Angeles, 4650 Sunset Blvd, Los Angeles, CA 90027, United States.
J Biomed Inform. 2021 Feb;114:103672. doi: 10.1016/j.jbi.2021.103672. Epub 2021 Jan 7.
Deep learning has demonstrated success in many applications; however, their use in healthcare has been limited due to the lack of transparency into how they generate predictions. Algorithms such as Recurrent Neural Networks (RNNs) when applied to Electronic Medical Records (EMR) introduce additional barriers to transparency because of the sequential processing of the RNN and the multi-modal nature of EMR data. This work seeks to improve transparency by: 1) introducing Learned Binary Masks (LBM) as a method for identifying which EMR variables contributed to an RNN model's risk of mortality (ROM) predictions for critically ill children; and 2) applying KernelSHAP for the same purpose. Given an individual patient, LBM and KernelSHAP both generate an attribution matrix that shows the contribution of each input feature to the RNN's sequence of predictions for that patient. Attribution matrices can be aggregated in many ways to facilitate different levels of analysis of the RNN model and its predictions. Presented are three methods of aggregations and analyses: 1) over volatile time periods within individual patient predictions, 2) over populations of ICU patients sharing specific diagnoses, and 3) across the general population of critically ill children.
深度学习在许多应用中已经取得了成功；然而，由于缺乏对其生成预测的透明度，它们在医疗保健中的应用受到了限制。例如，递归神经网络（RNN）等算法在应用于电子病历（EMR）时，由于 RNN 的顺序处理和 EMR 数据的多模态性质，引入了额外的透明度障碍。这项工作旨在通过以下方法来提高透明度：1）引入学习二进制掩码（LBM）作为一种方法，用于确定哪些 EMR 变量有助于 RNN 模型对危重病儿童死亡率（ROM）的预测；2）为达到相同目的而应用核 SHAP。对于单个患者，LBM 和 KernelSHAP 都会生成一个归因矩阵，该矩阵显示每个输入特征对 RNN 对该患者的预测序列的贡献。归因矩阵可以通过多种方式聚合，以促进对 RNN 模型及其预测的不同层次的分析。本文提出了三种聚合和分析方法：1）在个体患者预测的易变时间段内，2）在共享特定诊断的 ICU 患者群体中，3）在整个危重病儿童群体中。
