Prediction-bias-informed slope and bias correction (SBC) for cross-batch near-infrared quantification during herbal extract concentration
Authors:
- Kai YangKYKai Yang
- Xinhao WanXWXinhao Wan
- Yiqin YangYYYiqin Yang
- Yuejie WangYWYuejie Wang
- Wenting ZhuWZWenting Zhu
- Qin ZhengQZQin Zheng
- Yaqi WangYWYaqi Wang
- Zhenfeng WuZWZhenfeng Wu
- Qing TaoQTQing Tao
- Xuecheng WangXWXuecheng Wang
Preprint
- 9 October 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Near-infrared (NIR) spectroscopy offers rapid, nondestructive analysis, but maintaining the predictive performance of quantitative models across new production batches remains a challenge for reliable quality monitoring in complex manufacturing processes. This study developed NIR quantitative models for solid content, narirutin, and hesperidin during the concentration of Jianwei Xiaoshi Tablet extracts. Batches B1–B5, prepared from raw-material batch M1, were used for model development and leave-one-batch-out cross-validation, while B6, prepared from a different raw-material batch (M2), served for independent external validation. Cross-batch predictive performance was compared across different modeling methods, data augmentation, and domain adaptation approaches. Prediction bias was then characterized, and slope and bias correction (SBC) was applied to the model outputs. Most models showed reduced predictive performance on B6, with residual predictive deviation (RPD) values below 3 for all three attributes across all models. For partial least squares regression (PLSR), the root mean square errors of prediction (RMSEPs) for solid content, narirutin, and hesperidin increased by 350%, 89%, and 90%, respectively, on B6 relative to B1–B5. After SBC, the corresponding RMSEPs decreased by 78%, 58%, and 67%. Data augmentation and domain adaptation did not consistently improve external-batch prediction, whereas SBC reduced systematic prediction bias. These findings suggest that prediction-bias-informed model correction can improve the cross-batch applicability of NIR models and inform the future development of online quality monitoring systems integrating model-status assessment with correction as needed.Keywords
This publication has 27 references indexed in Scilit:
- Development of Raman Spectroscopy and Machine Learning Methods for Protein Aggregate Quantification: Application to BSA in Chromatographic ProcessesBiotechnology and Bioengineering, 2026
- Model maintenance, monitoring, and control framework using In-Situ NIR spectroscopy and offline process data for Lactococcus lactis fermentationChemical Engineering Journal, 2025
- Calibration transfer and maintenance in the pharmaceutical industry: a systematic reviewEuropean Journal of Pharmaceutical Sciences, 2025
- Spectral data augmentation for leaf nutrient uptake quantificationBiosystems Engineering, 2024
- Augmenting NIR Spectra in deep regression to improve calibrationChemometrics and Intelligent Laboratory Systems, 2023
- Improving the prediction performance of soluble solids content (SSC) in kiwifruit by means of near-infrared spectroscopy using slope/bias correction and calibration updatingFood Research International, 2023
- Selection of reference samples for updating multivariate calibration models used in the analysis of pig faecesChemometrics and Intelligent Laboratory Systems, 2022
- Handling batch-to-batch variability in portable spectroscopy of fresh fruit with minimal parameter adjustmentAnalytica Chimica Acta, 2021
- Comparison of augmentation and pre-processing for deep learning and chemometric classification of infrared spectraChemometrics and Intelligent Laboratory Systems, 2021
- Preprocessing methods for near‐infrared spectrum calibrationJournal of Chemometrics, 2020