Information Retrieval in Medicine - An Extensive Experimental Study

Roberto Gatta, Mauro Vallati, Berardino De Bari, Nadia Pasinetti, Carlo Cappelli, Ilenia Pirola, Massimo Salvetti, Michela Buglione, Maria L. Muiesan, Stefano M. Magrini, Maurizio Castellano

2014

Abstract

The clinical documents stored in a textual and unstructured manner represent a precious source of information that can be gathered by exploiting Information Retrieval techniques. Classification algorithms, and their composition through Ensemble Methods, can be used for organizing this huge amount of data, but are usually tested on standardized corpora, which significantly differ from actual clinical documents that can be found in a modern hospital. In this paper we present the results of a large experimental analysis conducted on 36,000 clinical documents, generated by three different medical Departments. For the sake of this investigation we propose a new classifier, based on the entropy idea, and test four single algorithms and four ensemble methods. The experimental results show the performance of selected approaches in a real-world environment, and highlights the impact of obsolescence on classification.

Paper Citation

in Harvard Style

Gatta R., Vallati M., De Bari B., Pasinetti N., Cappelli C., Pirola I., Salvetti M., Buglione M., Muiesan M., Magrini S. and Castellano M. (2014). Information Retrieval in Medicine - An Extensive Experimental Study . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2014) ISBN 978-989-758-010-9, pages 447-452. DOI: 10.5220/0004909904470452

in Bibtex Style

@conference{healthinf14,
author={Roberto Gatta and Mauro Vallati and Berardino De Bari and Nadia Pasinetti and Carlo Cappelli and Ilenia Pirola and Massimo Salvetti and Michela Buglione and Maria L. Muiesan and Stefano M. Magrini and Maurizio Castellano},
title={Information Retrieval in Medicine - An Extensive Experimental Study},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2014)},
year={2014},
pages={447-452},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004909904470452},
isbn={978-989-758-010-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2014)
TI - Information Retrieval in Medicine - An Extensive Experimental Study
SN - 978-989-758-010-9
AU - Gatta R.
AU - Vallati M.
AU - De Bari B.
AU - Pasinetti N.
AU - Cappelli C.
AU - Pirola I.
AU - Salvetti M.
AU - Buglione M.
AU - Muiesan M.
AU - Magrini S.
AU - Castellano M.
PY - 2014
SP - 447
EP - 452
DO - 10.5220/0004909904470452