This study presents the combination of Raman spectroscopy with machine learning algorithms as a prospective diagnostic tool capable of detecting and monitoring relevant variations of pH and lactate as recognized biomarkers of several pathologies. The applicability of the method proposed here is tested both in vitro and ex vivo. In a first step, Raman spectra of aqueous solutions are evaluated for the identification of characteristic patterns resulting from changes in pH or in the concentration of lactate. The method is further validated with blood and plasma samples. Principal component analysis is used to highlight the relevant features that differentiate the Raman spectra regarding their pH and concentration of lactate. Partial least squares regression models are developed to capture and model the spectral variability of the Raman spectra. The performance of these predictive regression models is demonstrated by clinically accurate predictions of pH and lactate from unknown samples in the physiologically relevant range. These results prove the potential of our method to develop a noninvasive technology, based on Raman spectroscopy, for continuous monitoring of pH and lactate in vivo.

No abstract

This work demonstrates a novel strategy to improve the sensing performance of a prism-coupled surface plasmon resonance system by Gaussian beam shaping and multivariate data analysis. The propagation of the beam along the optical system has been studied using the Gaussian beam approximation to design the incident beam such that the beam waist is aligned precisely and that stability is assured at the metal−dielectric interface. This renders a collimated incident beam, hence least angular dispersion, yielding a stronger and sharper plasmonic resonance. Moreover, we use the multivariate analysis method partial least squares that combines multiple features of the surface plasmon resonance curve and allows for a more precise analysis of the plasmonic response. Compared to univariate analysis, partial least squares improves typical sensing performance parameters remarkably. The combination of both aspects, beam shaping and multivariate analysis, overcomes current limitations of plasmonic detection systems. Thereby, we improve analytical sensitivity by a factor of 16, decrease the prediction error of the concentration of an unknown analyte by a factor of 11, and enhance resolution to the order of 5 × 10 −7 RIU in angular interrogation.

No abstract