2026/07/01 by Chao Ma, Wenxuan Zhao, Mingkun Zhang +3
Biochemistry, Genetics and Molecular Biology · Chemistry · Medicine · #Ginseng Biological Effects and Applications #Spectroscopy and Chemometric Analyses #Traditional Chinese Medicine Analysis
paper · doi:10.1016/j.jfca.2026.109404
openalex publication_date 2026/07/01 · openalex created_date 2026/07/30 · openalex updated_date 2026/07/30
American ginseng (Panax quinquefolius L., PQL) is a high-value medicinal material that is frequently subjected to adulteration and counterfeiting due to its high market value and strong visual similarity between authentic and non-authentic products. This similarity poses a major challenge for rapid and non-destructive authenticity identification. To overcome the low efficiency and subjectivity of traditional sensory evaluation and physicochemical methods, this study proposes a rapid identification approach for PQL authenticity and inferior processing based on multispectral imaging combined with machine learning. Genuine PQL was successfully discriminated from three representative non-authentic scenarios, including low-quality PQL, morphologically similar non–Panax quinquefolius ginseng slices (simulating species substitution adulteration), and boiled–dried processed PQL. The results demonstrate that spectral preprocessing and feature selection strategies significantly influence classification performance. Among all evaluated models, the SG-PCA-RF combination achieved the best overall performance, yielding a test-set accuracy of 98.10%, together with high F1-score and Kappa coefficient values. The SG-LDA-SVM combination also showed strong stability and generalization ability. Overall, the proposed method provides a rapid, non-destructive, and reliable solution for authenticity identification and quality evaluation of PQL and other medicinal materials.