Assertion Detection in Multi-Label Clinical Text using Scope Localization

TL;DR

This paper introduces a CNN-based approach for multi-label assertion detection in clinical text, effectively localizing multiple labels and their scopes in a single stage, outperforming existing methods by at least 12%.

Contribution

The authors propose a novel CNN architecture that simultaneously detects and localizes multiple assertion labels and their scopes in multi-label clinical sentences.

Findings

Model performs at least 12% better than state-of-the-art.

Effective multi-label scope localization in clinical text.

Single-stage end-to-end assertion detection approach.

Abstract

Multi-label sentences (text) in the clinical domain result from the rich description of scenarios during patient care. The state-of-theart methods for assertion detection mostly address this task in the setting of a single assertion label per sentence (text). In addition, few rules based and deep learning methods perform negation/assertion scope detection on single-label text. It is a significant challenge extending these methods to address multi-label sentences without diminishing performance. Therefore, we developed a convolutional neural network (CNN) architecture to localize multiple labels and their scopes in a single stage end-to-end fashion, and demonstrate that our model performs atleast 12% better than the state-of-the-art on multi-label clinical text.