# Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment

arXiv: https://arxiv.org/abs/2112.13756 · HTML: https://mlsanity.com/paper/2112.13756/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 27 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [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)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Learning to Diagnose with LSTM Recurrent Neural Networks](https://mlsanity.com/paper/1511.03677/) (2015)
- [De-identification of Patient Notes with Recurrent Neural Networks](https://mlsanity.com/paper/1606.03475/) (2016)
- [Explaining Recurrent Neural Network Predictions in Sentiment Analysis](https://mlsanity.com/paper/1706.07206/) (2017)
- [Text Understanding from Scratch](https://mlsanity.com/paper/1502.01710/) (2015)
- [ktrain: A Low-Code Library for Augmented Machine Learning](https://mlsanity.com/paper/2004.10703/) (2020)
- [Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records](https://mlsanity.com/paper/1606.07953/) (2016)
- [A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries](https://mlsanity.com/paper/2107.10652/) (2021)
- [An Investigation of Recurrent Neural Architectures for Drug Name Recognition](https://mlsanity.com/paper/1609.07585/) (2016)
- [Feature-Augmented Neural Networks for Patient Note De-identification](https://mlsanity.com/paper/1610.09704/) (2016)
- [Classifying medical notes into standard disease codes using Machine Learning](https://mlsanity.com/paper/1802.00382/) (2018)
- [Analysis and Optimization of fastText Linear Text Classifier](https://mlsanity.com/paper/1702.05531/) (2017)

## Abstract (arXiv)

Clinical information systems have become large repositories for semi-structured and partly annotated electronic health record data, which have reached a critical mass that makes them interesting for supervised data-driven neural network approaches. We explored automated coding of 50 character long clinical problem list entries using the International Classification of Diseases (ICD-10) and evaluated three different types of network architectures on the top 100 ICD-10 three-digit codes. A fastText baseline reached a macro-averaged F1-score of 0.83, followed by a character-level LSTM with a macro-averaged F1-score of 0.84. The top performing approach used a downstreamed RoBERTa model with a custom language model, yielding a macro-averaged F1-score of 0.88. A neural network activation analysis together with an investigation of the false positives and false negatives unveiled inconsistent manual coding as a main limiting factor.