Abstract:

The frequency distribution of International Classification of Diseases （ICD） codes is long tail， resulting in it is challenging to perform multi-label text classification for few-shot code. An MNIC （Meta Network-based automatic ICD Coding model） was proposed to solve the problem of insufficient training data in few-shot code classification. Firstly， instances in the feature space and features in the semantic space were fitted to the same space for mapping， and the feature representations of many-shot codes were mapped to their classifier weights， thus learning meta-knowledge through meta-network. Secondly， the learned meta-knowledge was transferred from data-abundant many-shot codes to data-poor few-shot codes. Finally， a reasonable explanation was provided for the transferability and generality of meta-knowledge. Experimental results on MIMIC-Ⅲ dataset show that MNIC improves the Micro-F1 and Micro Area Under Curve （Micro-AUC） of few-shot codes by 3.77 and 3.82 percentage points respectively compared to the suboptimal AGM-HT （Adversarial Generative Model conditioned on code descriptions with Hierarchical Tree structure） model， indicating that the proposed model improves the performance of few-shot code classification significantly.

Key words: automatic International Classification of Diseases (ICD) coding, few-shot learning, meta-learning, Natural Language Processing (NLP), interpretability

摘要：

国际疾病分类（ICD）编码的频率分布呈现出长尾的情况，因此，对少样本编码进行多标签文本分类极具挑战性。针对少样本编码分类中训练数据不足的问题，提出了一种基于元网络的自动ICD编码模型（MNIC）。首先，将特征空间中的实例和语义空间中的特征拟合到同一个空间进行映射，并将频繁编码的特征表示映射到它的分类器权重上，从而通过元网络学习到元知识；然后将学习到的元知识从数据丰富的频繁编码转移到数据贫乏的少样本编码；最后，为元知识的可转移性和通用性提供了合理的解释。在MIMIC-Ⅲ数据集上的实验结果表明，与次优的AGM-HT（Adversarial Generative Model conditioned on code descriptions with Hierarchical Tree structure）模型相比，MNIC将少样本编码的Micro-F1与曲线下面积（Micro-AUC）分别提高了3.77和3.82个百分点，显著提高了少样本编码分类的性能。

关键词: 自动国际疾病分类编码, 少样本学习, 元学习, 自然语言处理, 可解释性