Predicting Concentrations of Mixed Sugar Solutions with a Combination of Resonant Plasmon-Enhanced SEIRA and Principal Component Analysis.

The detection and quantification of glucose concentrations in human blood or in the ocular fluid gain importance due to the increasing number of diabetes patients. A reliable determination of these low concentrations is hindered by the complex aqueous environments in which various biomolecules are present. In this study, we push the detection limit as well as the discriminative power of plasmonic nanoantenna-based sensors towards the physiological limit. We utilize plasmonic surface-enhanced infrared absorption spectroscopy (SEIRA) to study aqueous solutions of mixtures of up to five different physiologically relevant saccharides, namely the monosaccharides glucose, fructose, and galactose, as well as the disaccharides maltose and lactose. Resonantly tuned plasmonic nanoantennas in a reflection flow cell geometry allow us to enhance the specific vibrational fingerprints of the mono- and disaccharides. The obtained spectra are analyzed via principal component analysis (PCA) using a machine learning algorithm. The high performance of the sensor together with the strength of PCA allows us to detect concentrations of aqueous mono- and disaccharides solutions down to the physiological levels of 1 g/L. Furthermore, we demonstrate the reliable discrimination of the saccharide concentrations, as well as compositions in mixed solutions, which contain all five mono- and disaccharides simultaneously. These results underline the excellent discriminative power of plasmonic SEIRA spectroscopy in combination with the PCA. This unique combination and the insights gained will improve the detection of biomolecules in different complex environments.

Machine Learning Methods of Regression for Plasmonic Nanoantenna Glucose Sensing.

The measurement and quantification of glucose concentrations is a field of major interest, whether motivated by potential clinical applications or as a prime example of biosensing in basic research. In recent years, optical sensing methods have emerged as promising glucose measurement techniques in the literature, with surface-enhanced infrared absorption (SEIRA) spectroscopy combining the sensitivity of plasmonic systems and the specificity of standard infrared spectroscopy. The challenge addressed in this paper is to determine the best method to estimate the glucose concentration in aqueous solutions in the presence of fructose from the measured reflectance spectra. This is referred to as the inverse problem of sensing and usually solved via linear regression. Here, instead, several advanced machine learning regression algorithms are proposed and compared, while the sensor data are subject to a pre-processing routine aiming to isolate key patterns from which to extract the relevant information. The most accurate and reliable predictions were finally made by a Gaussian process regression model which improves by more than 60% on previous approaches. Our findings give insight into the applicability of machine learning methods of regression for sensor calibration and explore the limitations of SEIRA glucose sensing.