Assertion Detection in Multi-Label Clinical Text using Scope Localization
This addresses a significant challenge in clinical text processing for healthcare professionals, enabling more accurate multi-label assertion detection, though it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of assertion detection in multi-label clinical text, where existing methods are limited to single-label sentences, and developed a convolutional neural network architecture that localizes multiple labels and their scopes end-to-end, achieving at least 12% better performance than state-of-the-art methods.
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.