Borohydride Synthesis of Silver Nanoparticles for SERS Platforms: Indirect Glucose Detection and Analysis Using Gradient Boosting

Abstract

In recent years, non-invasive methods for the analysis of biological fluids have attracted growing interest. In this study, we propose a straightforward approach to fabricating silver nanoparticle (AgNP)-coated non-woven polyacrylonitrile substrates for surface-enhanced Raman scattering (SERS). AgNPs were synthesized directly on the substrate using borohydride reduction, ensuring uniform distribution. The optimized SERS substrates exhibited a high enhancement factor (EF) of up to 10⁵ for the detection of 4-mercaptobenzoic acid (4-MBA). To enable glucose sensing, the substrates were further functionalized with glucose oxidase (GOx), allowing detection in the 1-10 mM range. Machine learning classification and regression models based on gradient boosting were employed to analyze SERS spectra, enhancing the accuracy of quantitative predictions (R² = 0.971, accuracy = 0.938, limit of detection = 0.66 mM). These results highlight the potential of AgNP-modified substrates for reliable and reusable biochemical sensing applications.

Keywords: SERS sensors; glucose detection; in situ AgNP synthesis; non-woven materials; polyacrylonitrile.

Figure 1

Schematic of AgNP reduction using the borohydride method on a PAN non-woven material, followed by analyte deposition.

Figure 2

Changes in the absorption spectrum of the silver nanoparticle solution over time, upon dilution with water (1:1, 1:2, 2:1) (a). The dependence of the absorption peak position on time (b).

Figure 3

Effects of NaOH concentration on the absorption spectra of silver nanoparticles, with areas where peak appearance is expected marked in yellow (for spherical) and green (for anisotropic).

Figure 4

SEM images in the electron backscattering mode for substrates obtained using different concentrations of NaOH: 0.001 M (a), 0.01 M (b), 0.1 M (c), 1 M (d). The EDX data are shown below the image. Scale bar is 5 μm.

Figure 5

SEM images for SERS substrates BH1-6 (a–f) and PAN without Ag (g). Scale bar is 10 μm. Backscattered electron mode was implemented.

Figure 6

Most significant regions of the SERS spectra of 4-MBA (10⁻⁴ M) recorded on the surfaces of silver-functionalized PAN substrates, obtained via the borohydride method.

Figure 7

Results of the classification model using gradient boosting on BH2: non-normalized (a,b) and normalized (c,d). Feature importances plots with significant wavenumbers (importance > 1%) indicated with grey lines (a,c). Classification confusion matrices in insets (a,c).

Figure 8

Results of the regression model using gradient boosting on BH2: non-normalized (a,b) and normalized (c,d). Feature importances plots with significant wavenumbers (importance > 1%) indicated with grey lines (a,c). Calibration lines for regression models in insets (a,c).