A study of convolutional neural networks for clinical document classification in systematic reviews: Sysreview at CLEF eHealth 2017
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 in...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/89461 http://hdl.handle.net/10220/44958 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | 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. |
|---|