Clinical diagnosis processes can result in many cases very complicated. A misdiagnosis is expensive and potentially life-threatening for patients. Diagnosis problems are mainly in the scope of the classification problems. Multi-classifier approaches can improve accuracy in classification task. In this work, we propose Multi-classifier approaches based on dynamic classifier selection techniques. These approaches have been tested on datasets known in the literature and representative of important diagnostic problems. Experimental results show that a suitable pool of different classifiers increases accuracy in classification task. This suggests that the proposed approaches can improve performance of diagnostic decision support systems.

Multi-Classifier Approaches for Supporting Clinical Diagnosis

Groccia, Maria Carmela;Guido, Rosita;Conforti, Domenico
2017-01-01

Abstract

Clinical diagnosis processes can result in many cases very complicated. A misdiagnosis is expensive and potentially life-threatening for patients. Diagnosis problems are mainly in the scope of the classification problems. Multi-classifier approaches can improve accuracy in classification task. In this work, we propose Multi-classifier approaches based on dynamic classifier selection techniques. These approaches have been tested on datasets known in the literature and representative of important diagnostic problems. Experimental results show that a suitable pool of different classifiers increases accuracy in classification task. This suggests that the proposed approaches can improve performance of diagnostic decision support systems.
2017
9783319673073
Diagnostic decision support systems; Machine learning; Multi-classifier systems; Mathematics (all)
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/277079
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact