Advanced Statistical Techniques for Noninvasive Hyperglycemic States Detection in Mice Using Millimeter-Wave Spectroscopy

Abstract

In this article, we discuss the use of advanced statistical techniques (functional data analysis) in millimeter-wave (mm-wave) spectroscopy for biomedical applications. We employ a W-band transmit–receive unit with a reference channel to acquire spectral data. The choice of the W-band is based on a tradeoff between penetration through the skin providing an upper bound for the frequencies and spectral content across the band. The data obtained are processed using functional principal component logit regression (FPCLoR), which enables to obtain a predictive model for sustained hyperglycemia, typically associated with diabetes. The predictions are based on the transmission data from noninvasive mm-wave spectrometer at W-band. We show that there exists a frequency range most suitable for identification, classification, and prediction of sustained hyperglycemia when evaluating the functional parameter of the functional logit model ( β ). This allows for the optimization of the spectroscopic instrument in the aim to obtain a compact and potential low-cost noninvasive instrument for hyperglycemia assessment. Furthermore, we also demonstrate that the statistical tools alleviate the problem of calibration, which is a serious obstacle in similar measurements at terahertz and IR frequencies.