193 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author김이석-
dc.date.accessioned2019-10-11T00:28:45Z-
dc.date.available2019-10-11T00:28:45Z-
dc.date.issued2019-04-
dc.identifier.citationAMERICAN JOURNAL OF ROENTGENOLOGY, v. 212, NO 4, Page. 734-740en_US
dc.identifier.issn0361-803X-
dc.identifier.issn1546-3141-
dc.identifier.urihttps://www.ajronline.org/doi/10.2214/AJR.18.19869-
dc.identifier.urihttps://repository.hanyang.ac.kr/handle/20.500.11754/110968-
dc.description.abstractOBJECTIVE. Radiology reports are rich resources for biomedical researchers. Before utilization of radiology reports, experts must manually review these reports to identify the categories. In fact, automatically categorizing electronic medical record (EMR) text with key annotation is difficult because it has a free-text format. To address these problems, we developed an automated system for disease annotation. MATERIALS AND METHODS. Reports of musculoskeletal radiography examinations performed from January 1, 2016, through December 31, 2016, were exported from the database of Hanyang University Medical Center. After sentences not written in English and sentences containing typos were excluded, 3032 sentences were included. We built a system that uses a recurrent neural network (RNN) to automatically identify fracture and nonfracture cases as a preliminary study. We trained and tested the system using orthopedic surgeon-classified reports. We evaluated the system for the number of layers in the following two ways: the word error rate of the output sentences and performance as a binary classifier using standard evaluation metrics including accuracy, precision, recall, and F1 score. RESULTS. The word error rate using Levenshtein distance showed the best performance in the three-layer model at 1.03%. The three-layer model also showed the highest overall performance with the highest precision (0.967), recall (0.967), accuracy (0.982), and F1 score (0.967). CONCLUSION. Our results indicate that the RNN-based system has the ability to classify important findings in radiology reports with a high F1 score. We expect that our system can be used in cohort construction such as for retrospective studies because it is efficient for analyzing a large amount of data.en_US
dc.description.sponsorshipThis study was supported by a grant from the National Research Foundation (NRF) of Korea that was funded by the Ministry of Science and ICT (grant no. 2011-0030075) and a grant through the NRF's Basic Science Research Program that was funded by the Ministry of Education (grant no. 2018R1D1A1B07048957).en_US
dc.language.isoenen_US
dc.publisherAMER ROENTGEN RAY SOCen_US
dc.subjectautomatic annotationen_US
dc.subjectdeep learningen_US
dc.subjectnatural language processingen_US
dc.subjectradiology reportsen_US
dc.subjectrecurrent neural networken_US
dc.titleAutomatic Disease Annotation From Radiology Reports Using Artificial Intelligence Implemented by a Recurrent Neural Networken_US
dc.typeArticleen_US
dc.relation.no4-
dc.relation.volume212-
dc.identifier.doi10.2214/AJR.18.19869-
dc.relation.page734-740-
dc.relation.journalAMERICAN JOURNAL OF ROENTGENOLOGY-
dc.contributor.googleauthorLee, Changhwan-
dc.contributor.googleauthorKim, Yeesuk-
dc.contributor.googleauthorKim, Young Soo-
dc.contributor.googleauthorJang, Jongseong-
dc.relation.code2019000395-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF MEDICINE[S]-
dc.sector.departmentDEPARTMENT OF MEDICINE-
dc.identifier.pidestone96-
Appears in Collections:
COLLEGE OF MEDICINE[S](의과대학) > MEDICINE(의학과) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE