The majority of clinical data is only available in unstructured text documents. Thus, their automated usage in data-based clinical application scenarios, like quality assurance and clinical decision support by treatment suggestions, is hindered because it requires high manual annotation efforts. In this work, we introduce a system for the automated processing of clinical reports of mamma carcinoma patients that allows for the automatic extraction and seamless processing of relevant textual features. Its underlying information extraction pipeline employs a rule-based grammar approach that is integrated with semantic technologies to determine the relevant information from the patient record. The accuracy of the system, developed with nine thousand clinical documents, reaches accuracy levels of 90 percent for lymph node status and 69 percent for the structurally most complex feature, the hormone status.
%0 Conference Paper
%1 BretschneiderZillnerEtAl17CBMS
%A Bretschneider, Claudia
%A Zillner, Sonja
%A Hammon, Matthias
%A Gass, Paul
%A Sonntag, Daniel
%B 30th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2017, Thessaloniki, Greece, June 22--24, 2017
%C Los Alamitos, CA
%D 2017
%E Bamidis, Panagiotis D.
%E Konstantinidis, Stathis Th.
%E Rodrigues, Pedro Pereira
%E Bamidis, Panagiotis D.
%E Konstantinidis, Stathis Th.
%E Rodrigues, Pedro Pereira
%I IEEE Computer Society
%K 01801 ieee paper dfki ai health information retrieval text language processing
%P 213--218
%R 10.1109/CBMS.2017.138
%T Automatic Extraction of Breast Cancer Information from Clinical Reports
%X The majority of clinical data is only available in unstructured text documents. Thus, their automated usage in data-based clinical application scenarios, like quality assurance and clinical decision support by treatment suggestions, is hindered because it requires high manual annotation efforts. In this work, we introduce a system for the automated processing of clinical reports of mamma carcinoma patients that allows for the automatic extraction and seamless processing of relevant textual features. Its underlying information extraction pipeline employs a rule-based grammar approach that is integrated with semantic technologies to determine the relevant information from the patient record. The accuracy of the system, developed with nine thousand clinical documents, reaches accuracy levels of 90 percent for lymph node status and 69 percent for the structurally most complex feature, the hormone status.
%@ 978-1-5386-1710-6
@inproceedings{BretschneiderZillnerEtAl17CBMS,
abstract = {The majority of clinical data is only available in unstructured text documents. Thus, their automated usage in data-based clinical application scenarios, like quality assurance and clinical decision support by treatment suggestions, is hindered because it requires high manual annotation efforts. In this work, we introduce a system for the automated processing of clinical reports of mamma carcinoma patients that allows for the automatic extraction and seamless processing of relevant textual features. Its underlying information extraction pipeline employs a rule-based grammar approach that is integrated with semantic technologies to determine the relevant information from the patient record. The accuracy of the system, developed with nine thousand clinical documents, reaches accuracy levels of 90 percent for lymph node status and 69 percent for the structurally most complex feature, the hormone status.},
added-at = {2018-03-08T11:19:23.000+0100},
address = {Los Alamitos, CA},
author = {Bretschneider, Claudia and Zillner, Sonja and Hammon, Matthias and Gass, Paul and Sonntag, Daniel},
biburl = {https://www.bibsonomy.org/bibtex/21ef840405ae9216fd25e107ce34ec2d9/flint63},
booktitle = {30th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2017, Thessaloniki, Greece, June 22--24, 2017},
doi = {10.1109/CBMS.2017.138},
editor = {Bamidis, Panagiotis D. and Konstantinidis, Stathis Th. and Rodrigues, Pedro Pereira and Bamidis, Panagiotis D. and Konstantinidis, Stathis Th. and Rodrigues, Pedro Pereira},
file = {IEEE Digital Library:2017/BretschneiderZillnerEtAl17CBMS.pdf:PDF},
groups = {public},
interhash = {bb1b142c7f02939169d40c634960750b},
intrahash = {1ef840405ae9216fd25e107ce34ec2d9},
isbn = {978-1-5386-1710-6},
keywords = {01801 ieee paper dfki ai health information retrieval text language processing},
pages = {213--218},
publisher = {IEEE Computer Society},
timestamp = {2018-04-16T12:21:49.000+0200},
title = {Automatic Extraction of Breast Cancer Information from Clinical Reports},
username = {flint63},
year = 2017
}