The authenticity and quality of traditional Chinese medicine (TCM) directly impact clinical efficacy and safety. Quality assessment of traditional Chinese medicine (QATCM) is a global concern due to increased demand and shortage of resources. Recently, modern analytical technologies have been extensively investigated and utilized to analyze the chemical composition of TCM. However, a single analytical technique has some limitations, and judging the quality of TCM only from the characteristics of the components is not enough to reflect the overall view of TCM. Thus, the development of multi-source information fusion technology and machine learning (ML) has further improved QATCM. Data information from different analytical instruments can better understand the connection between herbal samples from multiple aspects. This review focuses on the use of data fusion (DF) and ML in QATCM, including chromatography, spectroscopy, and other electronic sensors. The common data structures and DF strategies are introduced, followed by ML methods, including fast-growing deep learning. Finally, DF strategies combined with ML methods are discussed and illustrated for research on applications such as source identification, species identification, and content prediction in TCM. This review demonstrates the validity and accuracy of QATCM-based DF and ML strategies and provides a reference for developing and applying QATCM methods.

Background: The identification and enumeration of medicinal plants at high elevations is an important part of accurate yield calculations. However, the current assessment of medicinal plant reserves continues to rely on field sampling surveys, which are cumbersome and time-consuming. Recently, unmanned aerial vehicle (UAV) remote sensing and deep learning (DL) have provided ultrahigh-resolution imagery and high-accuracy object recognition techniques, respectively, providing an excellent opportunity to improve the current manual surveying of plants. However, accurate segmentation of individual plants from drone images remains a significant challenge due to the large variation in size, geometry, and distribution of medicinal plants. Results: In this study, we proposed a new pipeline for wild medicinal plant detection and yield assessment based on UAV and DL that was specifically designed for detecting wild medicinal plants in an orthomosaic. We used a drone to collect panoramic images of Lamioplomis rotata Kudo (LR) in high-altitude areas. Then, we annotated and cropped these images into equally sized sub-images and used a DL model Mask R-CNN for object detection and segmentation of LR. Finally, on the basis of the segmentation results, we accurately counted the number and yield of LRs. The results showed that the Mask R-CNN model based on the ResNet-101 backbone network was superior to ResNet-50 in all evaluation indicators. The average identification precision of LR by Mask R-CNN based on the ResNet-101 backbone network was 89.34%, while that of ResNet-50 was 88.32%. The cross-validation results showed that the average accuracy of ResNet-101 was 78.73%, while that of ResNet-50 was 71.25%. According to the orthomosaic, the average number and yield of LR in the two sample sites were 19,376 plants and 57.93 kg and 19,129 plants and 73.5 kg respectively. Conclusions: The combination of DL and UAV remote sensing reveals significant promise in medicinal plant detection, counting, and yield prediction, which will benefit the monitoring of their populations for conservation assessment and management, among other applications.

Tibetan medicine Bang Jian refers to a range of botanical drugs within the Gentiana genus. It serves as a prominent traditional Tibetan botanical drug primarily found in the ethnic minority regions of the Qinghai-Tibet Plateau in China. Traditionally, the dried flowers of Bang Jian, known as “Longdanhua” have been employed in Tibetan medicine to address detoxification, pharyngeal relief, acute and chronic bronchitis, bronchiectasis, lung infections, pulmonary fibrosis, and throat disorders. Surprisingly, there has been no comprehensive review published to date on Tibetan medicine Bang Jian. This passage systematically presents and critically assesses recent advancements in botanical characterization, traditional applications, phytochemistry, pharmacology, and clinical uses of Bang Jian, aiming to provide a scientific foundation for its reasonable use and further exploration. To date, researchers have isolated and identified 92 structurally diverse compounds, with a predominant presence of iridoids, flavonoids, xanthones, and triterpenoids. The crude extracts and metabolites derived from Bang Jian have been found to exhibit a wide range of pharmacological effects, encompassing anti-inflammatory, anti-tumor, anti-bacterial, antiviral, antioxidant, hepatoprotective properties, and protect the respiratory system. Nevertheless, detailed data on the biological effects, metabolic activities, and mechanistic research concerning active monomer metabolites remain insufficient. Consequently, there is a pressing need for comprehensive and in-depth research to guide rational clinical drug usage and evaluate the medicinal attributes of Bang Jian.

Background: Shilajit is a commonly used Tibetan medicine, and its water extract is mainly used for various heat-related syndrome, especially that of stomach, liver and kidney. Shilajit is found to exudate from rocks of cliff at an altitude of 2000–4000 m as a water-soluble mixture of black paste and animal feces of Trodocterus spp. or Ochotona spp. Because it is difficult to reach the exudation points so as to explain the its formation process, the source of Shilajit still remains unclear and controversial, which severely impedes its safety and efficacy in clinical application. Methods: In this work, a series of investigations as rock flakes identification, porosity determination, rock mineral analysis, scanning electron microscopy (SEM), and energy dispersive spectrometer (EDS) have been carried out to clarify the source of Shilajit, including the storage condition and exudation process of its organic matter, and to investigate the geological structure of the exudation points as well as physical and chemical characteristics of the mother rocks. Results: The Shilajit exudation points were mainly distributed on the steep cliffs, where there were cavities and sections that could not be eroded by rainwater. The fundamental structure of the exudation points was determined by the rock’s bedding planes, joints, fracture surfaces and faults, and developed into micro-topography later. The exudation points were distributed in the Triassic strata and scattered in the Early Mesozoic granitoids. The lithologic features were mainly slate, carbonaceous slate and sandy slate etc. The background rocks were characterized by intergranular pores, dissolved pore, joint and fracture development. Organic matter was widely distributed in these pores and fissures, which had condition for storage and exudation of organic matter. Conclusions: Shilajit mainly distributed on sunny steep slopes and cliffs with a slope of 60° or above at altitude of 2000–4000 m. The lithology character of the Shilajit exudation area were mainly various metamorphic rocks of sedimentary rocks that were rich in organic carbon. The organic matter in Shilajit was found to flow out naturally from rocks along pore, structural plane and even accumulate on the surface of rock as a result of storage environment change caused by rock tectonic action.

Nitrogen (N) is one of the three major elements required for plant growth and development. It is of great significance to study the effects of different nitrogen application levels on the growth and root exudates of Phlomoides rotata, and can provide a theoretical basis for its scientific application of fertilizer to increase production. In this study, Phlomoides rotata were grown under different nitrogen conditions for two months. Soil and plant analyzer development (SPAD) values, bioaccumulation, root morphology, root exudate composition, nitrogen metabolism enzyme and antioxidant enzyme activity were evaluated. The results showed that compared with CK (no N fertilizer), N2 (CO(NH2)2 80 mg/kg) and N3 (CO(NH2)2 160 mg/kg) through significantly improved the activities of nitrogen metabolism enzyme nitrite reductase (NiR), glutamate dehydrogenase (GDH) and glutamine synthetase (GS), enhanced the nitrogen metabolism process, and increased the accumulation of plant soluble sugars (SS) and soluble protein (SP), thus improving Phlomoides rotata biomass yield. After 60 days of treatment, low nitrogen (N1, CO(NH2)2 40 mg/kg) increased root length, root volume, root surface area, average root diameter, significantly increased the diversity of organic acids in root exudates, and enhanced the activity of antioxidant enzymes to adapt the nitrogen deficiency environment. This study can provide new ideas for understanding the mechanism of nitrogen tolerance in Phlomoides rotata and developing scientific fertilization management strategies for plateau plants and medicinal plants.

Introduction: Monitoring the growth status and aboveground biomass of wild and cultivated medicinal herbs remains a persistent challenge in precision agriculture.Methods: In this study, we developed machine learning and deep learning models to estimate SPAD values and biomass of Lamiophlomis rotata (Benth.). The models used hyperspectral data and time-series phenotypic traits from 508 samples collected across different altitudes. Regions of interest (ROIs) were manually defined from plant contours. The corresponding mean spectral profiles were then preprocessed. To improve feature selection, we proposed a Dynamic Reptile Search Algorithm-enhanced CARS (DRSA-CARS) method. This method integrates a dynamic behavioral strategy into the CARS framework to identify informative spectral bands. Vegetation indices (VIs) and gray-level co-occurrence matrix (GLCM)-based texture parameters were extracted and combined with spectral features to construct the PLSR, SVR, FNN, and CNN models.Results: Compared to CARS, the DRSA-CARS method reduced feature dimensionality by up to 75.7% for SPAD and 29.2% for biomass, while improving prediction accuracy (R²) by 24.4% and 34.7%, respectively. Among all models, the FNN achieved the highest performance, with R² values of 0.7732 (training) and 0.7502 (testing) for SPAD and 0.8260 and 0.7933 for biomass. Feature fusion further improved predictive accuracy by 11% for SPAD and 30% for biomass compared to models based on individual feature types.Discussion: These results demonstrate that coupling DRSA-CARS-based feature selection with deep learning provides a robust, non-destructive approach for evaluating plant growth status. This framework highlights the potential of hyperspectral imaging as a rapid, reliable, non-invasive tool for precision cultivation of medicinal herbs.