CLDec 13, 2018

Joint Entity Extraction and Assertion Detection for Clinical Text

arXiv:1812.05270v51100 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of accurately identifying negative medical findings in clinical reports, which is crucial for information extraction in healthcare, though it is incremental as it builds on existing hierarchical encoder-decoder models.

The paper tackled the problem of jointly extracting entities and detecting negations in clinical text, presenting an end-to-end neural model that outperformed previous rule-based and machine learning systems, achieving state-of-the-art results on the 2010 i2b2/VA challenge dataset and a proprietary clinical dataset.

Negative medical findings are prevalent in clinical reports, yet discriminating them from positive findings remains a challenging task for information extraction. Most of the existing systems treat this task as a pipeline of two separate tasks, i.e., named entity recognition (NER) and rule-based negation detection. We consider this as a multi-task problem and present a novel end-to-end neural model to jointly extract entities and negations. We extend a standard hierarchical encoder-decoder NER model and first adopt a shared encoder followed by separate decoders for the two tasks. This architecture performs considerably better than the previous rule-based and machine learning-based systems. To overcome the problem of increased parameter size especially for low-resource settings, we propose the Conditional Softmax Shared Decoder architecture which achieves state-of-art results for NER and negation detection on the 2010 i2b2/VA challenge dataset and a proprietary de-identified clinical dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes