Multivariate analysis of skin impedance data in long-term type 1 diabetic patients

Combined near-infrared spectroscopy and multifrequency bio-impedance investigation of skin alterations in diabetes patients based on multivariate analyses

“…The outcome of the estimation of NG in this investigation and the latest annual control are summarised in Table 2. MFBiA-skin and NIR measurements were taken on four different sites; the ventral forearm, the dorsum of the hand, the shin and the dorsum of the foot; see Fig 2. The same sites were used in LINDHOLM- SETHSON et al (1998) andGELADI et al (2000) The hair was dry shaved at the measuring sites before the MFBiA-body and NIR measurements were taken. First, the NIR measurements were taken, followed by MFBiA-body.…”

“…in two recent papers promising results were presented on the evaluation of skin alterations in diabetic patients using two different, non-invasive techniques: multi-frequency bioelectrical skin impedance analysis (MFBiA-skin) (LINDHOLM-SETHSON et al, 1998) and NIR spectroscopy (GELADI, 2000).…”

Are biosensor arrays in one membrane possible? A combination of multifrequency impedance measurements and chemometrics

“…This methodology allows for the treatment of all data simultaneously without subjective assumptions and educated guesses. This method has previously been shown to be successful in the analysis of electrochemical impedance spectra obtained from phospholipid-coated mercury electrodes [36,37] and in the classification of diabetic skin from skin impedance data [38]. One of the great advantages of a multivariate approach is that all factors that characterise phospholipid interactions can be isolated and related to specific mechanisms.…”

A comparative study of PCA, SIMCA and Cole model for classification of bioimpedance spectroscopy measurements

“…Principal Component Analysis (PCA) and Soft Independent Modeling of Class Analogy (SIMCA) are two techniques that have been reported before as successful feature extraction methods in BIS classification tasks [16][17][18][19][20][21]. PCA maps the whole data on its orthogonal and uncorrelated eigenvectors and extracts the most salient part of information on first eigenvectors as features.…”