Cargando…
Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports
The automatic identification of relations between medical concepts in a large corpus of Electroencephalography (EEG) reports is an important step in the development of an EEG-specific patient cohort retrieval system as well as in the acquisition of EEG-specific knowledge from this corpus. EEG-specif...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Medical Informatics Association
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5961777/ https://www.ncbi.nlm.nih.gov/pubmed/29888063 |
_version_ | 1783324778107502592 |
---|---|
author | Maldonado, Ramon Goodwin, Travis R. Harabagiu, Sanda M. |
author_facet | Maldonado, Ramon Goodwin, Travis R. Harabagiu, Sanda M. |
author_sort | Maldonado, Ramon |
collection | PubMed |
description | The automatic identification of relations between medical concepts in a large corpus of Electroencephalography (EEG) reports is an important step in the development of an EEG-specific patient cohort retrieval system as well as in the acquisition of EEG-specific knowledge from this corpus. EEG-specific relations involve medical concepts that are not typically mentioned in the same sentence or even the same section of a report, thus requiring extraction techniques that can handle such long-distance dependencies. To address this challenge, we present a novel frame work which combines the advantages of a deep learning framework employing Dynamic Relational Memory (DRM) with active learning. While DRM enables the prediction of long-distance relations, active learning provides a mechanism for accurately identifying relations with minimal training data, obtaining an 5-fold cross validationF1 score of 0.7475 on a set of 140 EEG reports selected with active learning. The results obtained with our novel framework show great promise. |
format | Online Article Text |
id | pubmed-5961777 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | American Medical Informatics Association |
record_format | MEDLINE/PubMed |
spelling | pubmed-59617772018-06-08 Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports Maldonado, Ramon Goodwin, Travis R. Harabagiu, Sanda M. AMIA Jt Summits Transl Sci Proc Articles The automatic identification of relations between medical concepts in a large corpus of Electroencephalography (EEG) reports is an important step in the development of an EEG-specific patient cohort retrieval system as well as in the acquisition of EEG-specific knowledge from this corpus. EEG-specific relations involve medical concepts that are not typically mentioned in the same sentence or even the same section of a report, thus requiring extraction techniques that can handle such long-distance dependencies. To address this challenge, we present a novel frame work which combines the advantages of a deep learning framework employing Dynamic Relational Memory (DRM) with active learning. While DRM enables the prediction of long-distance relations, active learning provides a mechanism for accurately identifying relations with minimal training data, obtaining an 5-fold cross validationF1 score of 0.7475 on a set of 140 EEG reports selected with active learning. The results obtained with our novel framework show great promise. American Medical Informatics Association 2018-05-18 /pmc/articles/PMC5961777/ /pubmed/29888063 Text en ©2018 AMIA - All rights reserved. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose |
spellingShingle | Articles Maldonado, Ramon Goodwin, Travis R. Harabagiu, Sanda M. Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports |
title | Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports |
title_full | Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports |
title_fullStr | Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports |
title_full_unstemmed | Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports |
title_short | Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports |
title_sort | memory-augmented active deep learning for identifying relations between distant medical concepts in electroencephalography reports |
topic | Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5961777/ https://www.ncbi.nlm.nih.gov/pubmed/29888063 |
work_keys_str_mv | AT maldonadoramon memoryaugmentedactivedeeplearningforidentifyingrelationsbetweendistantmedicalconceptsinelectroencephalographyreports AT goodwintravisr memoryaugmentedactivedeeplearningforidentifyingrelationsbetweendistantmedicalconceptsinelectroencephalographyreports AT harabagiusandam memoryaugmentedactivedeeplearningforidentifyingrelationsbetweendistantmedicalconceptsinelectroencephalographyreports |