Please use this identifier to cite or link to this item:
Title: A study of convolutional neural networks for clinical document classification in systematic reviews: Sysreview at CLEF eHealth 2017
Authors: Lee, Grace Eunkyung
Keywords: Document Classification
Systematic Review
Issue Date: 2017
Source: Lee, G. E. (2017). A Study of Convolutional Neural Networks for Clinical Document Classification in Systematic Reviews: SysReview at CLEF eHealth 2017. CEUR Workshop Proceedings.
Series/Report no.: CEUR Workshop Proceedings
Abstract: Identifying eligible documents for systematic reviews is one of the most time-consuming steps in writing the reviews. From retrieving numerous clinical documents to manually checking the documents with detailed criteria requires a tremendous amount of time and skilled workforce. In this paper, to increase the efficiency of the process we examine the role of convolutional neural networks for classifying medical documents for systematic reviews. The analysis is carried out in the context of the CLEF 2017 eHealth Task 2 as a participant. The evaluation demonstrates that the suggested methods show slightly better performance for full document screening than abstract screening.
ISSN: 1613-0073
Rights: © 2017 The Author(s). This paper was published in CEUR Workshop Proceedings and is made available as an electronic reprint (preprint) with permission of The Author(s). The published version is available at: []. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
A Study of Convolutional Neural Networks for.pdf194.01 kBAdobe PDFThumbnail

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.