Electronic Healthcare. 4th International Conference, eHealth 2011, Málaga, Spain, November 21-23, 2011, Revised Selected Papers

Research Article

Obstetric Medical Record Processing and Information Retrieval

Download
315 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-29262-0_4,
        author={Miroslav Bursa and Lenka Lhotska and Vaclav Chudacek and Michal Huptych and Jiri Spilka and Petr Janku and Martin Huser},
        title={Obstetric Medical Record Processing and Information Retrieval},
        proceedings={Electronic Healthcare. 4th International Conference, eHealth 2011, M\^{a}laga, Spain, November 21-23, 2011, Revised Selected Papers},
        proceedings_a={E-HEALTH},
        year={2012},
        month={5},
        keywords={Swarm Intelligence Ant Colony Textual Data Mining Medical Record Processing Hospital Information System},
        doi={10.1007/978-3-642-29262-0_4}
    }
    
  • Miroslav Bursa
    Lenka Lhotska
    Vaclav Chudacek
    Michal Huptych
    Jiri Spilka
    Petr Janku
    Martin Huser
    Year: 2012
    Obstetric Medical Record Processing and Information Retrieval
    E-HEALTH
    Springer
    DOI: 10.1007/978-3-642-29262-0_4
Miroslav Bursa1,*, Lenka Lhotska1, Vaclav Chudacek1, Michal Huptych1, Jiri Spilka1, Petr Janku2, Martin Huser2
  • 1: Czech Technical University
  • 2: University Hospital in Brno
*Contact email: miroslav.bursa@fel.cvut.cz

Abstract

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 10 years. This paper concerns only textual attributes with free text input, that means 613,000 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.