Recurrent Neural Networks for Classifying Relations in Clinical Notes

By Yuan Luo. 2017

153 citations recorded by the source corpus.

We proposed the first models based on recurrent neural networks (more specifically Long Short-Term Memory - LSTM) for classifying relations from clinical notes. We tested our models on the i2b2/VA relation classification challenge dataset. We showed that our segment LSTM model, with only word embedding feature and no manual feature engineering, achieved a micro-averaged f-measure of 0.661 for classifying medical problem-treatment relations, 0.800 for medical problem-test relations, and 0.683 for medical problem-medical problem relations. These results are comparable to those of the state-of-the-art systems on the i2b2/VA relation classification challenge. We compared the segment LSTM model with the sentence LSTM model, and demonstrated the benefits of exploring the difference between concept text and context text, and between different contextual parts in the sentence. We also evaluated the impact of word embedding on the performance of LSTM models and showed that medical domain word embedding help improve the relation classification. These results support the use of LSTM models for classifying relations between medical concepts, as they show comparable performance to previously published systems while requiring no manual feature engineering.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yuan Luo
2. Zexian Zeng
3. Tristan Naumann
4. Ozlem Uzuner
5. Xiaoyu Li
6. Yu Deng
7. Peter Szolovits
8. Liang Yao

In Molecular Biology

1. Yuan Luo
2. Zexian Zeng
3. Ozlem Uzuner
4. Tristan Naumann
5. Peter Szolovits
6. Liang Yao
7. Chengsheng Mao
8. Justin B. Starren

In Natural Language Processing

1. Liang Yao
2. Chengsheng Mao
3. Peter Szolovits
4. Ozlem Uzuner
5. Yu Cheng
6. Yuan Luo
7. Justin B. Starren
8. Tristan Naumann

In Medical & Health AI

1. Ozlem Uzuner
2. Yuan Luo
3. Liang Yao
4. Chengsheng Mao
5. Peter Szolovits
6. Zexian Zeng
7. Justin B. Starren
8. Tristan Naumann

Citations in the corpus

• Graph Convolutional Networks for Text Classification (2018, methodology): “We use t-SNE tool (Maaten and Hinton 2008) to visualize the learned document embeddings.”
• Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “tion [146], semantic analysis [147], [148], information retrieval [149], [150], entity recognition [151], [152], relation extraction [153], [154], [155], [156], and event detection [157], [158].”
• Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes (2018, result): “This is inconsistent with the observation that the 5 segments of text have different roles in determining the relation class.(31,32) Thus the motivating question for this study is whether we can design CNNs with only wordembedding features and no manual feature engineering to effectively classify th”