Abstract

A group of 34 diabetic men, with different degrees of diabetes complications, including skin changes, were studied by near-infrared (NIR) spectroscopy and total body multi-frequency bio-impedance analyses (MFBIA-body). Skin reflectance spectra were measured with a fibre-optic probe in four locations (sites): hand, arm, leg and foot. As control subjects, a group of 23 healthy males were also measured. A combined multivariate analysis of the two types of spectrum was performed. It was concluded that the NIR method has the potential to detect diabetes-related skin conditions and also that the combination of the two techniques provides a higher potential for classification and discrimination of the skin conditions, with correct classification increasing from 63% to 85%

Published in

Medical and Biological Engineering and Computing
2003, Volume: 41, number: 3, pages: 324-329
Publisher: PETER PEREGRINUS LTD

SLU Authors

• Geladi, Paul

  • Department of Forest Biomaterials and Technology, Swedish University of Agricultural Sciences
    

UKÄ Subject classification

Computer Science


Publication identifier

DOI: https://doi.org/10.1007/BF02348438

Permanent link to this page (URI)

https://res.slu.se/id/publ/1100