Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.

<h4>Introduction</h4>Case-based reasoning (CBR) is an emerging decision making paradigm in medical research where new cases are solved relying on previously solved similar cases. Usually, a database of solved cases is provided, and every case is described through a set of attributes (inp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Boris Campillo-Gimenez, Wassim Jouini, Sahar Bayat, Marc Cuggia
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2013
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c6d6be3900ea458ca4a7d09e7091ade6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c6d6be3900ea458ca4a7d09e7091ade6
record_format	dspace
spelling	oai:doaj.org-article:c6d6be3900ea458ca4a7d09e7091ade62021-11-18T08:56:25ZImproving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.1932-620310.1371/journal.pone.0071991https://doaj.org/article/c6d6be3900ea458ca4a7d09e7091ade62013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24039730/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Introduction</h4>Case-based reasoning (CBR) is an emerging decision making paradigm in medical research where new cases are solved relying on previously solved similar cases. Usually, a database of solved cases is provided, and every case is described through a set of attributes (inputs) and a label (output). Extracting useful information from this database can help the CBR system providing more reliable results on the yet to be solved cases.<h4>Objective</h4>We suggest a general framework where a CBR system, viz. K-Nearest Neighbour (K-NN) algorithm, is combined with various information obtained from a Logistic Regression (LR) model, in order to improve prediction of access to the transplant waiting list.<h4>Methods</h4>LR is applied, on the case database, to assign weights to the attributes as well as the solved cases. Thus, five possible decision making systems based on K-NN and/or LR were identified: a standalone K-NN, a standalone LR and three soft K-NN algorithms that rely on the weights based on the results of the LR. The evaluation was performed under two conditions, either using predictive factors known to be related to registration, or using a combination of factors related and not related to registration.<h4>Results and conclusion</h4>The results show that our suggested approach, where the K-NN algorithm relies on both weighted attributes and cases, can efficiently deal with non relevant attributes, whereas the four other approaches suffer from this kind of noisy setups. The robustness of this approach suggests interesting perspectives for medical problem solving tools using CBR methodology.Boris Campillo-GimenezWassim JouiniSahar BayatMarc CuggiaPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 9, p e71991 (2013)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Boris Campillo-Gimenez Wassim Jouini Sahar Bayat Marc Cuggia Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
description	<h4>Introduction</h4>Case-based reasoning (CBR) is an emerging decision making paradigm in medical research where new cases are solved relying on previously solved similar cases. Usually, a database of solved cases is provided, and every case is described through a set of attributes (inputs) and a label (output). Extracting useful information from this database can help the CBR system providing more reliable results on the yet to be solved cases.<h4>Objective</h4>We suggest a general framework where a CBR system, viz. K-Nearest Neighbour (K-NN) algorithm, is combined with various information obtained from a Logistic Regression (LR) model, in order to improve prediction of access to the transplant waiting list.<h4>Methods</h4>LR is applied, on the case database, to assign weights to the attributes as well as the solved cases. Thus, five possible decision making systems based on K-NN and/or LR were identified: a standalone K-NN, a standalone LR and three soft K-NN algorithms that rely on the weights based on the results of the LR. The evaluation was performed under two conditions, either using predictive factors known to be related to registration, or using a combination of factors related and not related to registration.<h4>Results and conclusion</h4>The results show that our suggested approach, where the K-NN algorithm relies on both weighted attributes and cases, can efficiently deal with non relevant attributes, whereas the four other approaches suffer from this kind of noisy setups. The robustness of this approach suggests interesting perspectives for medical problem solving tools using CBR methodology.
format	article
author	Boris Campillo-Gimenez Wassim Jouini Sahar Bayat Marc Cuggia
author_facet	Boris Campillo-Gimenez Wassim Jouini Sahar Bayat Marc Cuggia
author_sort	Boris Campillo-Gimenez
title	Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
title_short	Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
title_full	Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
title_fullStr	Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
title_full_unstemmed	Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
title_sort	improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.
publisher	Public Library of Science (PLoS)
publishDate	2013
url	https://doaj.org/article/c6d6be3900ea458ca4a7d09e7091ade6
work_keys_str_mv	AT boriscampillogimenez improvingcasebasedreasoningsystemsbycombiningknearestneighbouralgorithmwithlogisticregressioninthepredictionofpatientsregistrationontherenaltransplantwaitinglist AT wassimjouini improvingcasebasedreasoningsystemsbycombiningknearestneighbouralgorithmwithlogisticregressioninthepredictionofpatientsregistrationontherenaltransplantwaitinglist AT saharbayat improvingcasebasedreasoningsystemsbycombiningknearestneighbouralgorithmwithlogisticregressioninthepredictionofpatientsregistrationontherenaltransplantwaitinglist AT marccuggia improvingcasebasedreasoningsystemsbycombiningknearestneighbouralgorithmwithlogisticregressioninthepredictionofpatientsregistrationontherenaltransplantwaitinglist
_version_	1718421164703875072

Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list.

Ejemplares similares