Precise classification of traditional Chinese medicine sources using intelligent fusion of hyperspectral imaging-mass spectrometry data combined with machine learning: A case study of American ginseng
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2025-08 · 336 · 126066
DOI: 10.1016/j.saa.2025.126066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2025-08. Verfasst von Hui Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmaceutical Science, Zhejiang University of Technology, No. 18, Chaowang Road, Hangzhou 310014, China. Hauptthemen laut MEDLINE: Panax, Medicine, Chinese Traditional, Drugs, Chinese Herbal, Machine Learning. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: Science and Technology Department of Zhejiang Province, Key Technology Research and Development Program of Shandong, National Natural Science Foundation of China.
Abstract (Originalsprache)
The application of artificial intelligence in traditional Chinese medicine (TCM) has become a hot topic in the scientific community. American ginseng (AG), a perennial herb with a rich history, is widely utilized in clinical settings due to its diverse pharmacological activities and nutritional value. However, the quality of AG in the market is often compromised by the presence of similar-looking adulterants from different regions. Rapid and precise identification of its origin is crucial for consumers. This study proposes a novel approach, employing a Mid-Level-Fusion method that combines hyperspectral imaging (HSI) and ultra performance liquid chromatography-quadrupole linear ion trap mass spectrometry (UPLC-QTRAP-MS/MS) techniques to successfully identify origins of AG. Firstly, the 1D-Gradient-weighted class activation mapping (1D-GradCAM) algorithm was utilized for feature selection on HSI data, visualizing wavelengths contributing significantly to classification results and using the 1D-GradCAM algorithm, the spectral features were reduced from 510 to 91, achieving 105 % of the performance of the full-wavelength model. Simultaneously, redundant data in UPLC-QTRAP-MS/MS were eliminated using Cars-PLS, reducing the number of indicator components from 23 to 11. Subsequently, a Mid-Level Fusion matrix was generated based on the filtered HSI and UPLC-QTRAP-MS/MS data to establish an AG origin tracing model, achieving a detection accuracy of up to 96.15 %. Finally, the established HSI-UPLC-QTRAP-MS/MS-Mid-Level-Fusion model enabled pixel-level recognition of origin tracing. In conclusion, HSI combined with UPLC-QTRAP-MS/MS Mid-Level-Fusion presents a feasible method for tracing AG origins, playing a crucial role in quality control at the source in TCM production.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Pharmaceutical Science, Zhejiang University of Technology, No. 18, Chaowang Road, Hangzhou 310014, China.
- State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, Beijing 100191, China.
- Pharmaceutical Informatics Institute, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China.
- College of Pharmaceutical Science, Zhejiang University of Technology, No. 18, Chaowang Road, Hangzhou 310014, China. Electronic address: yjz@zjut.edu.cn.
- State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, Beijing 100191, China. Electronic address: yongjiang@bjmu.edu.cn.
Förderung
- Science and Technology Department of Zhejiang Province
- Key Technology Research and Development Program of Shandong
- National Natural Science Foundation of China
Zitieren
APA
Zhang, H., Zhang, H., Wu, S., Gong, X., Zhu, J., Yan, J., & Jiang, Y. (2025). Precise classification of traditional Chinese medicine sources using intelligent fusion of hyperspectral imaging-mass spectrometry data combined with machine learning: A case study of American ginseng. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 336, 126066. https://doi.org/10.1016/j.saa.2025.126066
Vancouver
Zhang H, Zhang H, Wu S, Gong X, Zhu J, Yan J, et al. Precise classification of traditional Chinese medicine sources using intelligent fusion of hyperspectral imaging-mass spectrometry data combined with machine learning: A case study of American ginseng. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2025;336:126066. doi:10.1016/j.saa.2025.126066
BibTeX
@article{Zhang2025,
author = {Zhang, Hui and Zhang, HongXu and Wu, ShouRong and Gong, XingChu and Zhu, JieQiang and Yan, JiZhong and Jiang, Yong},
title = {Precise classification of traditional Chinese medicine sources using intelligent fusion of hyperspectral imaging-mass spectrometry data combined with machine learning: A case study of American ginseng},
journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
year = {2025},
volume = {336},
pages = {126066},
doi = {10.1016/j.saa.2025.126066}
}
EUVIMED