Noninvasive detection and analysis of human globulin based on dynamic spectrum

Noninvasive detection of blood components is the most ideal and effective method to prevent and detect many clinical diseases. However, the accuracy of noninvasive detection based on the spectrum is not always satisfactory. The influence of various interferences in measurement limits the accuracy of the analysis. The dynamic spectrum theory can theoretically eliminate the individual differences and measurement environment influence and improve measurement accuracy. The concentration of globulin is closely related to the status of the immune system, which is of great significance for clinical diagnosis. This paper improves the signal-to-noise ratio from all links of dynamic spectrum data processing to realize the noninvasive detection of globulin. Through reasonable pretreatment, extraction, quality evaluation, and variable screening, the valid information of the spectrum gets maximum utilization. Finally, using the partial least squares prediction model to predict globulin concentration. The results show that the model established by dynamic spectrum treated by this method has a good predictive performance for globulin. The correlation coefficient of the prediction set is 0.962, the root-mean-square error of the prediction set is only 1.058 g/L, the correlation coefficient of the calibration set is 0.996, and the root-mean-square error of the calibration set is 0.332 g/L. The experimental results show that reasonable data processing of dynamic spectrum can effectively improve the signal-to-noise ratio of the data, make the established model have good prediction accuracy and performance, and realize the high-precision prediction globulin. This paper provides a complete research idea and method for the noninvasive detection of blood components. It is hopeful to realize the noninvasive quantitative detection of trace components in blood. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

Noninvasive detection of blood components is an ideal and effective method for preventing and detecting clinical diseases. This study improves the signal-to-noise ratio in all aspects of dynamic spectrum data processing to achieve noninvasive detection of globulin. Through reasonable pretreatment, extraction, quality evaluation, and variable screening, the valid information of the spectrum is maximized. The results show that the model established by dynamic spectrum treated by this method has good predictive performance for globulin.