Rapid and reagent-free screening of occult hepatitis B virus infection based on plasma Vis-NIR spectral pattern recognition

Abstract

Introduction: Occult hepatitis B virus infection (OBI) is a specific form of hepatitis B virus (HBV) infection characterized by testing negative for Hepatitis B surface antigen (HBsAg) with the presence of HBV DNA in the blood. Due to the complexity and high cost of HBV DNA testing, which is rarely included in routine physical examinations, leading to underdiagnosis of OBI. In this study, plasma visible-near-infrared (Vis-NIR) spectroscopy pattern recognition was employed to develop the discriminant analysis models for distinguishing between OBI from healthy (normal controls) plasma.

Methods: A total of 444 plasma samples from voluntary blood donors (OBI 204, normal controls 240) were collected, and their Vis-NIR spectra were measured. The samples were rigorously divided into training, prediction, and independent external validation sets. Partial least squares-discriminant analysis (PLS-DA) and k-nearest neighbor (kNN) were used as spectral classifiers; standard normal variate (SNV) and norris derivative filtering (NDF) were applied for spectral preprocessing. The integrated algorithm combining separation degree priority combination (SDPC) with wavelength step-by-step phase-out (WSP) was utilized for the optimal wavelength selection.

Results: The plasma spectral discriminant models for OBI and normal control were successfully established. Based on the optimal SNV-NDF preprocessed spectra, the SDPC-WSP-kNN and SDPC-WSP-PLS-DA methods determined the optimal number of wavelengths N to be 5 and 26, respectively. When evaluated on the independent external validation set, the SDPC-WSP-kNN model demonstrated better robustness, achieving sensitivity, specificity, and total recognition accuracy rates of 96.6%, 100%, and 98.7%, respectively. By introducing a grey judgment zone, both SEN and SPE reached 100%, with a detection recovery rate of 96.8%.

Conclusion: These results indicated that Vis-NIR spectroscopy pattern recognition can accurately discriminate between OBI and normal controls' plasma samples. This method is reagent-free, rapid, and simple, making it suitable for large-scale, low-cost rapid screening of OBI. In particular, the proposed few-wavelength model can provide an important reference for the development of small specialized blood analyzers for OBI detection.

Keywords: blood screening; multi-wavelength; norris derivative filtering; occult hepatitis B virus infection; partial least squares-discriminant analysis; separation degree priority combination; step-by-step phase-out; visible-near-infrared spectralpattern recognition.

FIGURE 1

Vis-NIR spectra of all OBI and normal control plasma samples: (a) Raw spectra; (b) SNV-NDF combination preprocessing spectra (d = 2, s = 21, g = 2); (c) SNV-NDF combination preprocessing spectra (d = 2, s = 3, g = 3).

FIGURE 2

Separation degree spectrum of the two spectral populations after preprocessing in modeling: (a) 333–1118 nm (d = 2, s = 21, g = 2); (b) Selected waveband combination of the optimal SDPC-PLS-DA model (d = 2, s = 21, g = 2); (c) 333–1118 nm (d = 2, s = 3, g = 3); (d) Selected waveband combination of the optimal SDPC-kNN model (d = 2, s = 3, g = 3).

FIGURE 3

Preprocessed absorbance at a wavelength in order from smallest to largest for two types of modeling spectra: (a) 592 nm (d = 2, s = 21, g = 2); (b) 584 nm (d = 2, s = 3, g = 3).

FIGURE 4

External validation results of the SDPC-WSP-PLS-DA model with SNV-NDF preprocessing: (a) Prediction value of class variable for OBI and normal control; (b) Schematic diagram of discrimination after introducing the gray area (G, 4.6 < S < 5.2).

FIGURE 5

Prediction class variable labels in the SDPC-WSP-kNN model with SNV-NDF preprocessing.