Buscar

 

RI UFLA (Universidade Federal de Lavras) >
DEG - Departamento de Engenharia >
DEG - Artigos publicados em periódicos >

Por favor, utilize esse identificador para citar este item ou usar como link: http://repositorio.ufla.br/jspui/handle/1/13132

Título: Non-invasive method to analyse the risk of developing diabetic foot
Autor(es): Silva, Rebeca N.
Ferreira, Ana C. B. H.
Ferreira, Danton D.
Barbosa, Bruno H. G.
Assunto: Diabetic foot
Foot complications
Diabetes mellitus
Foot ulcer
Automatic noninvasive method
Diabetic patients
Health care
Complicações do pé
Úlcera no pé
Método não invasivo automático
Pacientes diabéticos
Cuidados de saúde
Publicador: The Institution of Engineering and Technology
Data de publicação: Out-2014
Referência: SILVA, R. N. et al. Non-invasive method to analyse the risk of developing diabetic foot. Healthcare Technology Letters, [S. l.], v. 1, n. 4, p. 109-113, Oct. 2014.
Abstract: Foot complications (diabetic foot) are among the most serious and costly complications of diabetes mellitus. Amputation of all or part of a lower extremity is usually preceded by a foot ulcer. To prevent diabetic foot, an automatic non-invasive method to identify patients with diabetes who have a high risk of developing diabetic foot is proposed. To design the proposed method, information concerning social scope and self-care of 153 diabetic patients was presented to the K-means clustering algorithm, which divided the data into two groups: high risk and low risk of developing diabetic foot. In the operational stage, the Euclidian distance from the information vector to the centroids of each group of risk is used as criterion for classification. Both real and simulated data were used to evaluate the method in which promising results were achieved with accuracy of 0.97 ± 0.06 for simulated data and 0.68 ± 0.16 considering the classification of specialists as the gold standard for real data. The method requires a simple computational processing and can be useful for basic health units to triage diabetic patients helping the health-care team to reduce the number of cases of diabetic foot.
URI: http://digital-library.theiet.org/content/journals/10.1049/htl.2014.0076
http://repositorio.ufla.br/jspui/handle/1/13132
Idioma: en_US
Aparece nas coleções: DEG - Artigos publicados em periódicos

Arquivos neste Item:

Não há arquivos associados para este Item.

Itens protegidos por copyright, com todos os direitos reservados, Salvo indicação em contrário.


Mostrar estatísticas

 


DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard - Feedback