论文标题
开发电子健康记录标签的视觉相互作用接口：可解释的机器学习方法
Developing A Visual-Interactive Interface for Electronic Health Record Labeling: An Explainable Machine Learning Approach
论文作者
论文摘要
标记大量电子健康记录是昂贵且耗时的，并且拥有标签助手工具可以大大减少医学专家的工作量。但是，要获得专家的信任，该工具必须能够解释其产出的原因。在此激励的情况下，我们介绍了可解释的标签助手（Xlabel）一种用于数据标记的新型视觉相互作用工具。在高水平上，Xlabel使用可解释的提升机（EBM）来对每个数据点的标签进行分类，并可视化EBM解释的热图。作为案例研究，我们使用Xlabel帮助医学专家用四种常见的非通信疾病（NCD）标记电子健康记录。我们的实验表明，1）Xlabel有助于减少标签动作的数量，2）EBM作为可解释的分类器与其他知名机器学习模型一样准确，胜过NCD专家使用的规则模型，而3）即使有40％以上的记录有意地错误地标记，EBM可能会回忆起超过90％的这些记录的正确标签。
Labeling a large number of electronic health records is expensive and time consuming, and having a labeling assistant tool can significantly reduce medical experts' workload. Nevertheless, to gain the experts' trust, the tool must be able to explain the reasons behind its outputs. Motivated by this, we introduce Explainable Labeling Assistant (XLabel) a new visual-interactive tool for data labeling. At a high level, XLabel uses Explainable Boosting Machine (EBM) to classify the labels of each data point and visualizes heatmaps of EBM's explanations. As a case study, we use XLabel to help medical experts label electronic health records with four common non-communicable diseases (NCDs). Our experiments show that 1) XLabel helps reduce the number of labeling actions, 2) EBM as an explainable classifier is as accurate as other well-known machine learning models outperforms a rule-based model used by NCD experts, and 3) even when more than 40% of the records were intentionally mislabeled, EBM could recall the correct labels of more than 90% of these records.
