# An Explainable CNN Approach for Medical Codes Prediction from Clinical Text

arXiv: https://arxiv.org/abs/2101.11430 · HTML: https://mlsanity.com/paper/2101.11430/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [Doctor AI: Predicting Clinical Events via Recurrent Neural Networks](https://mlsanity.com/paper/1511.05942/) (2015)
- [A Convolutional Attention Network for Extreme Summarization of Source Code](https://mlsanity.com/paper/1602.03001/) (2016)
- [Reasoning about Entailment with Neural Attention](https://mlsanity.com/paper/1509.06664/) (2015)
- [ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs](https://mlsanity.com/paper/1512.05193/) (2015)
- [Towards Automated ICD Coding Using Deep Learning](https://mlsanity.com/paper/1711.04075/) (2017)
- [Attentive Pooling Networks](https://mlsanity.com/paper/1602.03609/) (2016)
- [Improving Palliative Care with Deep Learning](https://mlsanity.com/paper/1711.06402/) (2017)
- [Condensed Memory Networks for Clinical Diagnostic Inferencing](https://mlsanity.com/paper/1612.01848/) (2016)
- [RePr: Improved Training of Convolutional Filters](https://mlsanity.com/paper/1811.07275/) (2018)
- [Do Convolutional Networks need to be Deep for Text Classification ?](https://mlsanity.com/paper/1707.04108/) (2017)
- [Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms](https://mlsanity.com/paper/1710.00519/) (2017)
- [What Does a TextCNN Learn?](https://mlsanity.com/paper/1801.06287/) (2018)

## Built on by (most cited first, 9 of 9)

- [MDACE: MIMIC Documents Annotated with Code Evidence](https://mlsanity.com/paper/2307.03859/) (2023)
- [Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding](https://mlsanity.com/paper/2204.10716/) (2022)
- [Automated ICD Coding using Extreme Multi-label Long Text Transformer-based Models](https://mlsanity.com/paper/2212.05857/) (2022)
- [Extend and Explain: Interpreting Very Long Language Models](https://mlsanity.com/paper/2209.01174/) (2022)
- [Medical Code Prediction from Discharge Summary: Document to Sequence BERT using Sequence Attention](https://mlsanity.com/paper/2106.07932/) (2021)
- [A Survey on Human-Centered Evaluation of Explainable AI Methods in Clinical Decision Support Systems](https://mlsanity.com/paper/2502.09849/) (2025)
- [Multi label classification of Artificial Intelligence related patents using Modified D2SBERT and Sentence Attention mechanism](https://mlsanity.com/paper/2303.03165/) (2023)
- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [Generating Explanations in Medical Question-Answering by Expectation Maximization Inference over Evidence](https://mlsanity.com/paper/2310.01299/) (2023)

## Abstract (arXiv)

Method: We develop CNN-based methods for automatic ICD coding based on clinical text from intensive care unit (ICU) stays. We come up with the Shallow and Wide Attention convolutional Mechanism (SWAM), which allows our model to learn local and low-level features for each label. The key idea behind our model design is to look for the presence of informative snippets in the clinical text that correlated with each code, and we infer that there exists a correspondence between "informative snippet" and convolution filter. Results: We evaluate our approach on MIMIC-III, an open-access dataset of ICU medical records. Our approach substantially outperforms previous results on top-50 medical code prediction on MIMIC-III dataset. We attribute this improvement to SWAM, by which the wide architecture gives the model ability to more extensively learn the unique features of different codes, and we prove it by ablation experiment. Besides, we perform manual analysis of the performance imbalance between different codes, and preliminary conclude the characteristics that determine the difficulty of learning specific codes. Conclusions: We present SWAM, an explainable CNN approach for multi-label document classification, which employs a wide convolution layer to learn local and low-level features for each label, yields strong improvements over previous metrics on the ICD-9 code prediction task, while providing satisfactory explanations for its internal mechanics.