This paper presents an automatic de-identification system for Serbian, grounded on a rapid adaptation of the existing named entity recognition system. Based on a finite-state methodology and lexical resources, the system is designed to detect and replace all explicit personal protected health information present in the medical narrative texts, while still preserving all the relevant medical concepts. The results of a preliminary evaluation demonstrate the usefulness of this method both in preserving patient privacy and the de- identified document interoperability.
Source:
Proceedings of the 17th International Multiconference INFORMATION SOCIETY – IS 2014, Language Technologies, October 9th−10th, 2014, Ljubljana, Slovenia, 2014, G, 73-78
TY - CONF
AU - Jaćimović, Jelena
AU - Krstev, Cvetana
AU - Jelovac, Drago
PY - 2014
UR - https://smile.stomf.bg.ac.rs/handle/123456789/2533
AB - This paper presents an automatic de-identification system for Serbian, grounded on a rapid adaptation of the existing named entity recognition system. Based on a finite-state methodology and lexical resources, the system is designed to detect and replace all explicit personal protected health information present in the medical narrative texts, while still preserving all the relevant medical concepts. The results of a preliminary evaluation demonstrate the usefulness of this method both in preserving patient privacy and the de- identified document interoperability.
PB - Jožef Stefan Institute, Ljubljana, Slovenia
C3 - Proceedings of the 17th International Multiconference INFORMATION SOCIETY – IS 2014, Language Technologies, October 9th−10th, 2014, Ljubljana, Slovenia
T1 - Automatic de-identification of protected health information
VL - G
SP - 73
EP - 78
UR - https://hdl.handle.net/21.15107/rcub_smile_2533
ER -
@conference{
author = "Jaćimović, Jelena and Krstev, Cvetana and Jelovac, Drago",
year = "2014",
abstract = "This paper presents an automatic de-identification system for Serbian, grounded on a rapid adaptation of the existing named entity recognition system. Based on a finite-state methodology and lexical resources, the system is designed to detect and replace all explicit personal protected health information present in the medical narrative texts, while still preserving all the relevant medical concepts. The results of a preliminary evaluation demonstrate the usefulness of this method both in preserving patient privacy and the de- identified document interoperability.",
publisher = "Jožef Stefan Institute, Ljubljana, Slovenia",
journal = "Proceedings of the 17th International Multiconference INFORMATION SOCIETY – IS 2014, Language Technologies, October 9th−10th, 2014, Ljubljana, Slovenia",
title = "Automatic de-identification of protected health information",
volume = "G",
pages = "73-78",
url = "https://hdl.handle.net/21.15107/rcub_smile_2533"
}
Jaćimović, J., Krstev, C.,& Jelovac, D.. (2014). Automatic de-identification of protected health information. in Proceedings of the 17th International Multiconference INFORMATION SOCIETY – IS 2014, Language Technologies, October 9th−10th, 2014, Ljubljana, Slovenia
Jožef Stefan Institute, Ljubljana, Slovenia., G, 73-78.
https://hdl.handle.net/21.15107/rcub_smile_2533
Jaćimović J, Krstev C, Jelovac D. Automatic de-identification of protected health information. in Proceedings of the 17th International Multiconference INFORMATION SOCIETY – IS 2014, Language Technologies, October 9th−10th, 2014, Ljubljana, Slovenia. 2014;G:73-78.
https://hdl.handle.net/21.15107/rcub_smile_2533 .
Jaćimović, Jelena, Krstev, Cvetana, Jelovac, Drago, "Automatic de-identification of protected health information" in Proceedings of the 17th International Multiconference INFORMATION SOCIETY – IS 2014, Language Technologies, October 9th−10th, 2014, Ljubljana, Slovenia, G (2014):73-78,
https://hdl.handle.net/21.15107/rcub_smile_2533 .
