RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism
Edward Choi∗, Mohammad Taha Bahadori∗, Joshua A. Kulas∗, Andy Schuetz†, Walter F. Stewart†, Jimeng Sun∗ ∗ Georgia Institute of Technology † Sutter Health
Abstract
Accuracy and interpretability are two dominant features of successful predictive models. Typically, a choice must be made in favor of complex black box models such as recurrent neural networks (RNN) for accuracy versus less accurate but more interpretable traditional models such as logistic regression. This tradeoff poses challenges in medicine where both accuracy and interpretability are important. We addressed this challenge by developing the REverse Time AttentIoN model (RETAIN) for application to Electronic Health Records (EHR) data. RETAIN achieves high accuracy while remaining clinically interpretable and is based on a two-level neural attention model that detects influential past visits and significant clinical variables within those visits (e.g. key diagnoses). RETAIN mimics physician practice by attending the EHR data in a reverse time order so that recent clinical visits are likely to receive higher attention. RETAIN was tested on a large health system EHR dataset with 14 million visits completed by 263K patients over an 8 year period and demonstrated predictive accuracy and computational scalability comparable to state-of-the-art methods such as RNN, and ease of interpre
中文速览
医生在看病时既需要准确判断又需要清晰的推理依据，但现有的深度学习模型（如循环神经网络 RNN）虽然预测准确却像"黑盒"一样难以解释，而传统可解释模型（如逻辑回归）又牺牲了预测精度。为此，研究者提出了 RETAIN（REverse Time AttentIoN）模型——一种双层神经注意力机制，它用两个反向时序 RNN 分别生成"就诊级别"和"变量级别"的注意力权重，让模型在做预测时能自动聚焦于最关键的历史就诊记录和具体临床指标（如关键诊断），同时反向时序设计使得近期就诊天然获得更高权重，贴近医生的临床思维方式。在包含 263,000 名患者、1400 万次就诊记录的大型电子病历数据集上，RETAIN 预测心力衰竭的准确率和计算效率均与最先进的 RNN 相当，同时提供了与传统模型媲美的可解释性。这一工作证明准确性与可解释性并非不可兼得，为在临床场景中安全、透明地部署深度学习模型提供了切实可行的方案。
原文 arXiv:1608.05745;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1608.05745v4