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 Lorenza Muiesan, Stefano Magrini, Maurizio Castellano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Health Informatics
Place of PublicationAngers, France
Pages447-452
Number of pages6
Volume1
DOIs
Publication statusPublished - 2014
Event7th International Conference on Health Informatics - ESEO, Angers, France
Duration: 3 Mar 20146 Mar 2014
http://www.healthinf.biostec.org/?y=2014 (Link to Conference Website)

Conference

Conference7th International Conference on Health Informatics
Abbreviated titleHEALTHINF 2014
CountryFrance
CityAngers
Period3/03/146/03/14
Internet address

Fingerprint

Information retrieval
Medicine
Obsolescence
Classifiers
Entropy
Chemical analysis

Cite this

Gatta, R., Vallati, M., De Bari, B., Pasinetti, N., Cappelli, C., Pirola, I., ... Castellano, M. (2014). Information Retrieval in Medicine: An Extensive Experimental Study. In Proceedings of the International Conference on Health Informatics (Vol. 1, pp. 447-452). Angers, France. https://doi.org/10.5220/0004909904470452
Gatta, Roberto ; Vallati, Mauro ; De Bari, Berardino ; Pasinetti, Nadia ; Cappelli, Carlo ; Pirola, Ilenia ; Salvetti, Massimo ; Buglione, Michela ; Muiesan, Maria Lorenza ; Magrini, Stefano ; Castellano, Maurizio. / Information Retrieval in Medicine : An Extensive Experimental Study. Proceedings of the International Conference on Health Informatics. Vol. 1 Angers, France, 2014. pp. 447-452
@inproceedings{74c9a3305e364e6f9e1e7990e32fe145,
title = "Information Retrieval in Medicine: An Extensive Experimental Study",
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.",
keywords = "Information retrieval, text categorization, document classification",
author = "Roberto Gatta and Mauro Vallati and {De Bari}, Berardino and Nadia Pasinetti and Carlo Cappelli and Ilenia Pirola and Massimo Salvetti and Michela Buglione and Muiesan, {Maria Lorenza} and Stefano Magrini and Maurizio Castellano",
year = "2014",
doi = "10.5220/0004909904470452",
language = "English",
isbn = "9789897580109",
volume = "1",
pages = "447--452",
booktitle = "Proceedings of the International Conference on Health Informatics",

}

Gatta, R, Vallati, M, De Bari, B, Pasinetti, N, Cappelli, C, Pirola, I, Salvetti, M, Buglione, M, Muiesan, ML, Magrini, S & Castellano, M 2014, Information Retrieval in Medicine: An Extensive Experimental Study. in Proceedings of the International Conference on Health Informatics. vol. 1, Angers, France, pp. 447-452, 7th International Conference on Health Informatics, Angers, France, 3/03/14. https://doi.org/10.5220/0004909904470452

Information Retrieval in Medicine : An Extensive Experimental Study. / Gatta, Roberto; Vallati, Mauro; De Bari, Berardino; Pasinetti, Nadia; Cappelli, Carlo; Pirola, Ilenia; Salvetti, Massimo; Buglione, Michela; Muiesan, Maria Lorenza; Magrini, Stefano; Castellano, Maurizio.

Proceedings of the International Conference on Health Informatics. Vol. 1 Angers, France, 2014. p. 447-452.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Information Retrieval in Medicine

T2 - An Extensive Experimental Study

AU - Gatta, Roberto

AU - Vallati, Mauro

AU - De Bari, Berardino

AU - Pasinetti, Nadia

AU - Cappelli, Carlo

AU - Pirola, Ilenia

AU - Salvetti, Massimo

AU - Buglione, Michela

AU - Muiesan, Maria Lorenza

AU - Magrini, Stefano

AU - Castellano, Maurizio

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

KW - Information retrieval

KW - text categorization

KW - document classification

U2 - 10.5220/0004909904470452

DO - 10.5220/0004909904470452

M3 - Conference contribution

SN - 9789897580109

VL - 1

SP - 447

EP - 452

BT - Proceedings of the International Conference on Health Informatics

CY - Angers, France

ER -

Gatta R, Vallati M, De Bari B, Pasinetti N, Cappelli C, Pirola I et al. Information Retrieval in Medicine: An Extensive Experimental Study. In Proceedings of the International Conference on Health Informatics. Vol. 1. Angers, France. 2014. p. 447-452 https://doi.org/10.5220/0004909904470452