光谱学与光谱分析, 2012, 32 (8): 2110, 网络出版: 2012-09-26
基于舌诊NIR反射光谱血清总蛋白含量的无创测量
Noninvasive Measurement of Serum Total Protein Content by Near-Infrared Reflection Spectra with Tongue Inspection
近红外反射光谱 舌诊 血清总蛋白(TP) BP神经网络 偏最小二乘(PLS) NIR normalized reflection spectroscopy Tongue inspection Total protein (TP) BP neural networks Partial least squares
摘要
采用舌诊近红外反射光谱对人体血清总蛋白(TP)含量进行无创检测。 采集58例舌尖反射光谱进行反射率归一化并记录相对应的血清总蛋白生化分析值, 将样本分为训练集和预测集, 运用主成分分析结合BP神经网络法和偏最小二乘算法分别建立预测模型。 主成分分析结合BP神经网络模型对预测集进行预测, 平均相对误差为7.35%, 均方根误差为3.069 1 g·L-1, 相关系数为0.902 1。 偏最小二乘模型对预测集进行预测, 平均相对误差为4.77%, 均方根误差为0.130 1 g·L-1, 相关系数为0.971 8。 实验结果证实了舌诊近红外反射光谱可以较为准确地用于总蛋白含量的无创检测。
Abstract
The technology of tongue near-infrared reflectance spectra was used for human serum total protein (TP) content of noninvasive testing for the first time. Reflectance spectrum on the tongue tips of 58 volunteers was collected, and the biochemical values of serum total protein were recorded at the same time. The samples were separated into two parts: training set and prediction set. Two prediction models were established using PCA combined with BP neural network and PLS. Using PCA-BP model to predict the prediction set, the average relative error is 7.35%, RMSEP was 6.377 1 g·L-1, and the correlation coefficient was 0.902 1. Using PLS model to predict the prediction set, the average relative error is 4.77%, RMSEP was 0.130 4 g·L-1, and the correlation coefficient was 0.971 8. It was approved that reflectance spectra of tongue can be used to predict TP accurately and noninvasively.
林凌, 李哲, 李晓霞, 李永成, 李刚, 张宝菊, 宋维. 基于舌诊NIR反射光谱血清总蛋白含量的无创测量[J]. 光谱学与光谱分析, 2012, 32(8): 2110. LIN Ling, LI Zhe, LI Xiao-xia, LI Yong-cheng, LI Gang, ZHANG Bao-ju, SONG Wei. Noninvasive Measurement of Serum Total Protein Content by Near-Infrared Reflection Spectra with Tongue Inspection[J]. Spectroscopy and Spectral Analysis, 2012, 32(8): 2110.