LGCLNEMar 30, 2016

Clinical Information Extraction via Convolutional Neural Network

arXiv:1603.09381v114 citations
Originality Synthesis-oriented
AI Analysis

This work addresses information extraction for healthcare professionals, but it is incremental as it applies existing neural network techniques to clinical data.

The authors tackled the problem of extracting clinical events and attributes from raw notes and reports by implementing a convolutional neural network-based tool, which significantly outperformed baseline methods.

We report an implementation of a clinical information extraction tool that leverages deep neural network to annotate event spans and their attributes from raw clinical notes and pathology reports. Our approach uses context words and their part-of-speech tags and shape information as features. Then we hire temporal (1D) convolutional neural network to learn hidden feature representations. Finally, we use Multilayer Perceptron (MLP) to predict event spans. The empirical evaluation demonstrates that our approach significantly outperforms baselines.

Foundations

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

Your Notes