Effective free-text medical record processing and information
retrieval.

D 2012

Effective free-text medical record processing and information retrieval.

BURŠA, M., L. LHOTSKÁ, V. CHUDÁČEK, J. SPILKA, Petr JANKŮ et. al.

Základní údaje

Originální název

Effective free-text medical record processing and information retrieval.

Autoři

BURŠA, M. (203 Česká republika, garant), L. LHOTSKÁ (203 Česká republika), V. CHUDÁČEK (203 Česká republika), J. SPILKA (203 Česká republika), Petr JANKŮ (203 Česká republika, domácí) a Martin HUSER (203 Česká republika, domácí)

Vydání

Berlin, IFMBE Proceedings: World Congress on Medical Physics and Biomedical Engineering, od s. 1305-1308, 4 s. 2012

Nakladatel

Springer

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

30214 Obstetrics and gynaecology

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Kód RIV

RIV/00216224:14110/12:00064004

Organizační jednotka

Lékařská fakulta

ISBN

978-3-642-29304-7

Klíčová slova anglicky

Swarm Intelligence; Ant Colony; Textual Data Mining; Medical Record Processing; Hospital Information System

Změněno: 13. 10. 2013 13:24, prof. MUDr. Martin Huser, Ph.D., MBA

Anotace

V originále

Information mining from textual data becomes a very challenging task when the structure of the text record is very loose without any rules. The task becomes even more difficult when natural language is used and no apriori knowledge is available. The medical environment itself is also very specific: the natural language used in textual description varies with the personality creating the record (there are many personalized approaches), however it is restricted by terminology (i.e. medical terms, medical standards, etc.). Moreover, the typical patient record is filled with typographical errors, duplicates, ambiguities, syntax errors and many (nonstandard) abbreviations. This paper describes the process of mining information from loosely structured medical textual records with no apriori knowledge. In the paper we depict the process of mining a large dataset of 50,000–120,000 records 20 attributes in database tables, originating from the hospital information system (thanks go to the University Hospital in Brno, Czech Republic) recording over 11 years. This paper concerns only textual attributes with free text input, that means 620,000 text fields in 16 attributes. Each attribute item contains ~800–1,500 characters (diagnoses, medications, etc.). The output of this task is a set of ordered/nominal attributes suitable for rule discovery mining and automated processing that can help in asphyxia prediction during delivery. The proposed technique has an important impact on reduction of the processing time of loosely structured textual records for experts. Note that this project is an ongoing process (and research) and new data are irregularly received from the medical facility, justifying the need for robust and fool-proof algorithms

Citovat

BURŠA, M., L. LHOTSKÁ, V. CHUDÁČEK, J. SPILKA, Petr JANKŮ a Martin HUSER. Effective free-text medical record processing and information retrieval. In Mian Long. IFMBE Proceedings: World Congress on Medical Physics and Biomedical Engineering. Berlin: Springer, 2012, s. 1305-1308. ISBN 978-3-642-29304-7.

@inproceedings{1088420,
   author = {Burša, M. and Lhotská, L. and Chudáček, V. and Spilka, J. and Janků, Petr and Huser, Martin},
   address = {Berlin},
   booktitle = {IFMBE Proceedings: World Congress on Medical Physics and Biomedical Engineering},
   editor = {Mian Long},
   keywords = {Swarm Intelligence; Ant Colony; Textual Data Mining; Medical Record Processing; Hospital Information System},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Berlin},
   isbn = {978-3-642-29304-7},
   pages = {1305-1308},
   publisher = {Springer},
   title = {Effective free-text medical record processing and information retrieval.},
   year = {2012}
}

TY  - JOUR
ID  - 1088420
AU  - Burša, M. - Lhotská, L. - Chudáček, V. - Spilka, J. - Janků, Petr - Huser, Martin
PY  - 2012
TI  - Effective free-text medical record processing and information retrieval.
PB  - Springer
CY  - Berlin
SN  - 9783642293047
KW  - Swarm Intelligence
KW  - Ant Colony
KW  - Textual Data Mining
KW  - Medical Record Processing
KW  - Hospital Information System
N2  - Information mining from textual data becomes a very challenging task when the structure of the text record is very loose without any rules. The task becomes even more difficult when natural language is used and no apriori knowledge is available. The medical environment itself is also very specific: the natural language used in textual description varies with the personality creating the record (there are many personalized approaches), however it is restricted by terminology (i.e. medical terms, medical standards, etc.). Moreover, the typical patient record is filled with typographical errors, duplicates, ambiguities, syntax errors and many (nonstandard) abbreviations. This paper describes the process of mining information from loosely structured medical textual records with no apriori knowledge. In the paper we depict the process of mining a large dataset of 50,000–120,000 records 20 attributes in database tables, originating from the hospital information system (thanks go to the University Hospital in Brno, Czech Republic) recording over 11 years. This paper concerns only textual attributes with free text input, that means 620,000 text fields in 16 attributes. Each attribute item contains ~800–1,500 characters (diagnoses, medications, etc.). The output of this task is a set of ordered/nominal attributes suitable for rule discovery mining and automated processing that can help in asphyxia prediction during delivery. The proposed technique has an important impact on reduction of the processing time of loosely structured textual records for experts. Note that this project is an ongoing process (and research) and new data are irregularly received from the medical facility, justifying the need for robust and fool-proof algorithms
ER  -

BURŠA, M., L. LHOTSKÁ, V. CHUDÁČEK, J. SPILKA, Petr JANKŮ a Martin HUSER. Effective free-text medical record processing and information retrieval. In Mian Long. \textit{IFMBE Proceedings: World Congress on Medical Physics and Biomedical Engineering}. Berlin: Springer, 2012, s.~1305-1308. ISBN~978-3-642-29304-7.

Podrobný výpis o publikaci