Lin Yongzhong, Li Lina, Lin Tianliang
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2015 Dec;32(6):1323-8, 1334.
For the near-infrared (NIR) spectral analysis of the concentration of blood glucose, the calibration accuracy can be affected because of the existing of outlier samples. In this research, a Monte-Carlo cross validation (MCCV) method is constructed for eliminating outlier samples. The human blood plasma experiment in vitro and the human body experiment in vivo were introduced to evaluate the MCCV method for its application effect in NIR spectral analysis of blood glucose. And the uninformative sample elimination method based on modified uninformative variable elimination (MUVE-USE) was employed in this study for the comparison with MCCV. The results indicated that, like the MUVE-USE method, the outlier samples elimination method based on MCCV could be used to eliminate the outlier samples which came from gross errors (such as bad sample) or system errors (such as baseline drift). In addition, the outlier samples from the random errors of uncertain causes which affect model accuracy can be eliminated simultaneously by MCCV. The elimination of multiple outlier samples is beneficial to the improvement of prediction accuracy of calibration model.
对于血糖浓度的近红外（NIR）光谱分析，由于存在异常样本，校准精度可能会受到影响。在本研究中，构建了一种蒙特卡洛交叉验证（MCCV）方法来消除异常样本。引入了人体血浆体外实验和人体体内实验，以评估MCCV方法在血糖近红外光谱分析中的应用效果。并且本研究采用了基于改进的无信息变量消除（MUVE-USE）的无信息样本消除方法与MCCV进行比较。结果表明，与MUVE-USE方法一样，基于MCCV的异常样本消除方法可用于消除由重大误差（如不良样本）或系统误差（如基线漂移）产生的异常样本。此外，MCCV可以同时消除因不确定原因的随机误差而影响模型精度的异常样本。消除多个异常样本有利于提高校准模型的预测精度。
