Wavelength selection-based nonlinear calibration for transcutaneous blood glucose sensing using Raman spectroscopy

Abstract

Abstract. While Raman spectroscopy provides a powerful tool for noninvasive and real time diagnostics of biological samples, its translation to the clinical setting has been impeded by the lack of robustness of spectroscopic calibration models and the size and cumbersome nature of conventional laboratory Raman systems. Linear multivariate calibration models employing full spectrum analysis are often misled by spurious correlations, such as system drift and covariations among constituents. In addition, such calibration schemes are prone to overfitting, especially in the presence of external interferences that may create nonlinearities in the spectra-concentration relationship. To address both of these issues we incorporate residue error plot-based wavelength selection and nonlinear support vector regression (SVR). Wavelength selection is used to eliminate uninformative regions of the spectrum, while SVR is used to model the curved effects such as those created by tissue turbidity and temperature fluctuations. Using glucose detection in tissue phantoms as a representative example, we show that even a substantial reduction in the number of wavelengths analyzed using SVR lead to calibration models of equivalent prediction accuracy as linear full spectrum analysis. Further, with clinical datasets obtained from human subject studies, we also demonstrate the prospective applicability of the selected wavelength subsets without sacrificing prediction accuracy, which has extensive implications for calibration maintenance and transfer. Additionally, such wavelength selection could substantially reduce the collection time of serial Raman acquisition systems. Given the reduced footprint of serial Raman systems in relation to conventional dispersive Raman spectrometers, we anticipate that the incorporation of wavelength selection in such hardware designs will enhance the possibility of miniaturized clinical systems for disease diagnosis in the near future. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

Development and comparative assessment of Raman spectroscopic classification algorithms for lesion discrimination in stereotactic breast biopsies with microcalcifications

“…We envision that the final outcome in terms of algorithm development may be a hybrid ensemble of different models (including but not limited to the aforementioned classification techniques), specifically customized for prediction of lesion types with and without microcalcifications. Towards this end, the domain of full-spectral analysis (and its related feature-selected variant [48]) can also be explored, in place of the FC-based analysis outlined in this article.…”

Selective sampling using confocal Raman spectroscopy provides enhanced specificity for urinary bladder cancer diagnosis

“…Also, the absence of Raman fiber signals makes the high-wavenumber approach fairly attractive for endoscopic applications [34], despite its lower molecular specificity in comparison to the fingerprint region. Further, selection of the most informative wavelengths (instead of performing full spectral analysis) [35] as well as application of pre-processing steps (such as standard normal variate transformation) that can account for non-analytespecific baseline variances is currently under investigation. Their proper application is likely to generate a more effective and robust tissue classification algorithm.…”

Raman spectroscopy: techniques and applications in the life sciences

“…Stöckel et al used a hierarchy of SVM and LDA classifiers to identify bacterial species [491]. SVM can also be trained to quantify the concentration of specific chemicals, such as glucose [492].…”