Active deep learning for the identification of concepts and relations in electroencephalography reports

[Display omitted] •Transformer encoders enable end-to-end, accurate knowledge extraction from EEG reports.•Medical concepts, their attributes and relations between them can be extracted jointly.•Joint learning enables active learning policy that selects based on all 3 tasks.•Active learning policy i...

Full description

Saved in:
Bibliographic Details
Published in:Journal of biomedical informatics 2019-10, Vol.98, p.103265-103265, Article 103265
Main Authors: Maldonado, Ramon, Harabagiu, Sanda M.
Format: Article
Language:English
Subjects:
Active learning
Attribute classification
Concept detection
Deep learning
Electroencephalography
Long-distance relation identification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •Transformer encoders enable end-to-end, accurate knowledge extraction from EEG reports.•Medical concepts, their attributes and relations between them can be extracted jointly.•Joint learning enables active learning policy that selects based on all 3 tasks.•Active learning policy itself can be learned with imitation learning and a seed dataset. The identification of medical concepts, their attributes and the relations between concepts in a large corpus of Electroencephalography (EEG) reports is a crucial step in the development of an EEG-specific patient cohort retrieval system. However, the recognition of multiple types of medical concepts, along with the many attributes characterizing them is challenging, and so is the recognition of the possible relations between them, especially when desiring to make use of active learning. To address these challenges, in this paper we present the Self-Attention Concept, Attribute and Relation (SACAR) identifier, which relies on a powerful encoding mechanism based on the recently introduced Transformer neural architecture (Dehghani et al., 2018). The SACAR identifier enabled us to consider a recently introduced framework for active learning which uses deep imitation learning for its selection policy. Our experimental results show that SACAR was able to identify medical concepts more precisely and exhibited enhanced recall, compared with previous methods. Moreover, SACAR achieves superior performance in attribute classification for attribute categories of interest, while identifying the relations between concepts with performance competitive with our previous techniques. As a multi-task network, SACAR achieves this performance on the three prediction tasks simultaneously, with a single, complex neural network. The learning curves obtained in the active learning process when using the novel Active Learning Policy Neural Network (ALPNN) show a significant increase in performance as the active learning progresses. These promising results enable the extraction of clinical knowledge available in a large collection of EEG reports.
ISSN:1532-0464
1532-0480
DOI:10.1016/j.jbi.2019.103265