[论文解读] Attention-based Multi-instance Neural Network for Medical Diagnosis from Incomplete and Low Quality Data

Zeyuan Wang, Josiah Poon+2 more|arXiv (Cornell University)|Apr 9, 2019

Traditional Chinese Medicine Studies参考文献 31被引用 10

一句话总结

本文提出 AMI-Net，一种基于注意力机制的多实例神经网络，通过将患者病历建模为症状实例的集合（即“包”），实现从不完整且质量较低的临床数据中进行端到端医疗诊断。该方法采用多头注意力机制、实例级别和包级别池化操作，优先关注具有信息量的症状，在来自中医和西医领域的两个真实世界、高度不平衡的数据集上达到最先进性能。

ABSTRACT

One way to extract patterns from clinical records is to consider each patient record as a bag with various number of instances in the form of symptoms. Medical diagnosis is to discover informative ones first and then map them to one or more diseases. In many cases, patients are represented as vectors in some feature space and a classifier is applied after to generate diagnosis results. However, in many real-world cases, data is often of low-quality due to a variety of reasons, such as data consistency, integrity, completeness, accuracy, etc. In this paper, we propose a novel approach, attention based multi-instance neural network (AMI-Net), to make the single disease classification only based on the existing and valid information in the real-world outpatient records. In the context of a patient, it takes a bag of instances as input and output the bag label directly in end-to-end way. Embedding layer is adopted at the beginning, mapping instances into an embedding space which represents the individual patient condition. The correlations among instances and their importance for the final classification are captured by multi-head attention transformer, instance-level multi-instance pooling and bag-level multi-instance pooling. The proposed approach was test on two non-standardized and highly imbalanced datasets, one in the Traditional Chinese Medicine (TCM) domain and the other in the Western Medicine (WM) domain. Our preliminary results show that the proposed approach outperforms all baselines results by a significant margin.

研究动机与目标

• 解决在真实门诊环境中，从不完整且质量较低的临床记录中诊断疾病所面临的挑战。
• 开发一种深度学习模型，能够有效处理高度不平衡且非标准化的医疗数据集。
• 实现在无需完整或一致数据的前提下，从患者级别的症状“包”中进行端到端学习。
• 通过注意力机制聚焦最具信息量的症状，提升诊断准确率。

提出的方法

• 该模型将每个患者记录视为症状实例的集合（即“包”），每个实例在特征空间中表示为一个向量。
• 嵌入层将原始症状向量映射到稠密表示空间，以反映个体患者的病情状态。
• 多头自注意力机制捕捉实例间的相关性，并分配注意力权重以突出重要症状。
• 实例级别多实例池化将加权后的实例聚合为包级别的表示。
• 包级别多实例池化进一步优化表示，用于最终疾病分类。
• 整个网络端到端训练，直接从输入的实例集合预测包级别的诊断标签。

实验结果

研究问题

• RQ1 基于注意力机制的多实例神经网络是否能有效从真实医疗环境中不完整且质量较低的临床数据中学习？
• RQ2 AMI-Net 在非标准化、高度不平衡的医疗数据集上与现有基线模型相比表现如何？
• RQ3 注意力机制在多大程度上通过聚焦最具信息量的症状来提升诊断性能？
• RQ4 所提出的模型是否能在不同医学领域（如中医与西医）之间实现良好泛化？

主要发现

• AMI-Net 在中医和西医数据集上的诊断准确率均显著优于所有基线模型。
• 该模型在两个高度不平衡且非标准化的数据集上达到最先进性能，展现出对数据质量问题的强鲁棒性。
• 注意力机制能有效识别并优先关注最具信息量的症状，提升模型可解释性。
• 端到端训练框架实现了从患者“包”到疾病标签的直接映射，无需数据预处理或特征工程。