Progress on the Industrial Development of Traditional Chinese Medicine Based on Artificial Intelligence

• Abstract
• Introduction
• Application of Artificial Intelligence in the Entire Production Process of Traditional Chinese Medicine-Based Drugs
• Application of Artificial Intelligence in the Selection and Harvesting of Traditional Chinese Medicine Raw Materials
• Application of Artificial Intelligence in Traditional Chinese Medicine Processing
• Application of Artificial Intelligence in the Extraction and Purification of Traditional Chinese Medicine Raw Materials
• Application of Artificial Intelligence in the Formulation and Shaping of Traditional Chinese Medicine-Based Drugs
• Application of Artificial Intelligence in Traditional Chinese Medicine Quality Control
• Summary and Prospect
• Discussion
• References

Abstract

With the increasing demands for drug quality and safety, the traditional Chinese medicine (TCM) pharmaceutical industry is in urgent need of transformation and upgrading. This paper provides an overview of the current application and prospects of artificial intelligence (AI) in the TCM pharmaceutical field. It delves into the specific applications and advantages of AI in various stages such as the selection and harvesting of TCM materials, processing, extraction and purification, formulation, and quality control. The paper points out new directions for the application and development of AI in the TCM pharmaceutical industry, offering a new perspective and approach for the intelligent upgrade of the TCM industry. The aim is to promote the industry's transition toward intelligence and high-quality development, with the hope of providing valuable insights and references for the innovation and upgrade of the entire TCM industry.

Introduction

Traditional Chinese medicine (TCM), which is regarded as a treasure of China's traditional medicine, has a long history and remarkable curative effects. TCM is particularly important in clinical applications. In China, there are 18,817 types of TCM resources, including 15,227 species of medicinal plants, 2,611 species of medicinal animals, 153 species of medicinal minerals, and 826 species of medicinal fungi, making the TCM resources abundant.[1] According to statistics, the market size of China's pharmaceutical industry was 477.2 billion yuan in 2023, and the TCM market share was 26.5% of the pharmaceutical market.[2] As an important part of China's traditional medicine, the TCM quality and safety are directly related to the health and life safety of patients. However, with the development of modern technology and the increasing demand for drug quality, safety, and efficiency, the problems in the traditional production process of TCM-based drugs have increased. In the traditional production process of TCM-based drugs, there are often issues, such as inconsistent quality and efficacy due to the limitations in the control methods, resulting in certain risks to clinical applications.[3] This inconsistency is caused by differences in the origin, cultivation methods, harvesting times, and production processes of TCM raw materials. The control methods used mainly rely on technical experience and traditional craftsmanship, which makes it difficult to effectively manage these factors. The promotion and application of new processes and technologies in TCM production are insufficient, and the quality of the TCM-based drugs is inconsistent, which seriously restricts the TCM industry development. The TCM-based drug production process urgently needs high integration with digital and intelligent technologies. The demand for intelligent transformation in the TCM manufacturing industry is imminent.

The emergence of AI technology has brought new opportunities to the entire production of TCM-based drugs. Using intelligent control, it is possible to achieve accurate control over the production process of TCM-based drugs, thus improving their quality and clinical safety.[4] Specifically, AI can play a significant role in the following aspects.

First, AI can achieve accurate identification and classification of TCM raw materials. The variety of TCM raw materials with uneven quality is huge, making the traditional manual identification and classification methods not only inefficient but also prone to errors. AI, which employs image recognition and spectral analysis, can rapidly and accurately identify and classify the TCM raw materials, ensuring the reliability of the subsequent drug production process.[5]

Second, AI can optimize the TCM extraction and purification processes. These processes, which are essential in the production of TCM-based drugs, directly affect drug quality and efficacy. AI can monitor and analyze the extraction and purification processes of TCM raw materials in real time, thus optimizing the process parameters to enhance the extraction and purification efficiency, ensuring the quality and consistency of the TCM-produced drugs.

In addition, AI provides real-time monitoring and early warning to achieve high TCM–drug quality. The traditional quality testing methods for TCM-based drugs often require a significant amount of time and labor, resulting in certain delays. In contrast, AI can perform real-time monitoring and analysis of various data during the TCM-based drug production process, promptly detect quality issues, and provide early warnings for applying appropriate measures.

Investigating the use of AI for the intelligent control of the TCM-based drug production process is of high significance for improving the quality and clinical safety of TCM-produced drugs. In the future, with the continuous development and application of AI technology, TCM-based drug production will be broadly developed.

Application of Artificial Intelligence in the Entire Production Process of Traditional Chinese Medicine-Based Drugs

The production process of TCM-based drugs is a multifaceted endeavor, initiated with the meticulous selection, harvesting, processing, extraction, and purification of raw materials. This foundational work is followed by the precise formulation and stringent quality control of the final drug products, ensuring their efficacy, safety, and consistency.

Recently, AI, a domain within computer science dedicated to creating machines capable of performing tasks usually requiring human intelligence, has witnessed significant advancements. AI operates by harnessing algorithms, extensive datasets, and substantial computational power to analyze patterns, make decisions, and resolve issues.[6] Its growing advantages and potential have made it indispensable across various industries, notably in the realm of intelligent manufacturing, particularly for TCM-based pharmaceuticals.

Within this context, AI provides a sophisticated platform for data analysis, prediction, and optimization in the manufacturing of TCM-based drugs. Leveraging advanced algorithms, AI processes extensive data pertaining to TCM raw materials, production processes, and quality control measures. This capability enables the identification of trends, patterns, and potential areas for improvement, thereby facilitating more accurate and efficient management of the entire production chain, from raw material procurement to final product formulation.

Furthermore, AI's predictive analytics capability allows for anticipating potential production issues, enabling manufacturers to intervene promptly and maintain the quality and consistency of the drugs.[7] By embedding AI within the production process, manufacturers can enhance decision-making processes, optimize production workflows, and ultimately elevate the overall quality and efficiency of TCM-based drug manufacturing ([Fig. 1]).

Application of Artificial Intelligence in the Selection and Harvesting of Traditional Chinese Medicine Raw Materials

Intelligent manufacturing technology stands as a pivotal technology for the digital transformation and upgrading of the TCM industry. TCM enterprises have achieved significant advancements in constructing real-time databases, developing information systems, and performing industrial data analysis and modeling. These endeavors have facilitated the effective collection, analysis, and management of structured data related to manufacturing elements such as personnel, machines, materials, methods, and the environment. These structured data have been successfully applied to various business activities, including medicinal material quality traceability, production process optimization, process quality control, production management, and warehousing and logistics management.[8]

In optimizing the quality of medicinal materials, AI, combined with DNA barcoding technology, emerges as a rapid and accurate means of identifying plant species. This capability is crucial for detecting adulteration and controlling the quality of TCM raw materials. Challenges such as substandard storage facilities leading to moisture absorption and mold growth in medicinal materials[9] or the use of aluminum phosphide for fumigation[10] can degrade product quality. AI provides a solution for rapid identification in such scenarios. It is noteworthy that AI algorithms and DNA barcoding technology have been applied in molecular identification and automated analysis of TCM materials. Studies have shown that the integration of these two technologies can significantly enhance the efficiency and accuracy of raw material quality testing, and this technology has already been practically implemented in multiple TCM enterprises.[11]

Furthermore, the combination of AI with hyperspectral imaging (HSI) technology has brought revolutionary changes to the quality assessment of TCM, providing a rapid, nondestructive, intelligent, and accurate evaluation method. HSI technology is capable of capturing the complete spectral data of samples, and when combined with machine learning (ML) algorithms, it achieves rapid and accurate analysis of the quality of TCM raw materials. Studies have shown that deep learning-based methods can effectively differentiate Pinellia ternata and its processed products, as well as various species of Fritillariae cirrhosae, with an accuracy rate as high as 99%.[12] This technology has not only achieved positive results in classifying, detecting, and evaluating TCM raw materials but is also continuously broadening its application scope, encompassing quality evaluations of multiple TCM raw materials.[13] [14] [15]

To enhance the efficiency of material harvesting, AI plays a vital role in determining the optimal harvesting time for TCM raw materials through big data analysis and ML algorithms. The content of active components varies across different growth stages of various TCM raw materials. By analyzing meteorological, soil, and plant growth data, AI can predict the optimal harvesting time, thereby maximizing the efficacy of the medicinal materials. A study on the optimal harvesting time of the Chinese herbal medicine Dendrobium officinale focused on utilizing ML algorithms combined with Fourier Transform Infrared spectroscopy data to train models, resulting in an improvement in prediction accuracy from c to b to a ([Fig. 2A]). Meanwhile, dry matter content was employed as a crucial indicator to assess the yield levels of Dendrobium officinale across different months ([Fig. 2B]). Ultimately, this study determined the optimal harvesting time as well as the best content of active ingredients.[16]

Furthermore, intelligent harvesting equipment incorporating image recognition and path planning technology has been leveraged for the automated harvesting of TCM raw materials. This equipment has contributed to reduced labor costs and improved accuracy and efficiency in harvesting. Studies reporting the application of intelligent equipment in the harvesting and processing of TCM raw materials have documented certain achievements.[17]

In conclusion, the application of AI in the selection and harvesting of TCM raw materials is indispensable in the intelligent manufacturing of TCM-based pharmaceuticals. It not only elevates the accuracy and efficiency of selecting and harvesting TCM raw materials but also fosters the automation, intelligence, and refined development of TCM-based pharmaceuticals, thereby infusing new vitality into the innovative development of the TCM industry.

Application of Artificial Intelligence in Traditional Chinese Medicine Processing

Processing of Chinese Materia Medica represents the quintessence of traditional pharmaceutical technology, encompassing preparation steps like cleansing, cutting, and stir-frying to ensure the quality and efficacy of botanical drugs. The rapid development of AI has propelled the manufacturing industry toward digitization and intelligence,[18] particularly in the processing of raw materials for TCM, where the application of AI offers extensive research prospects and significantly enhances the accuracy, efficiency, and standardization of the processing procedures.

AI's capacity to enhance data processing during TCM raw material processing stands out due to the abundance of unstructured data within production and quality inspection records, as well as research and development reports. Traditional methods struggle to efficiently process and utilize these unstructured data, whereas AI exhibits considerable advantages in handling such vast amounts of information, effectively analyzing and extracting valuable insights.[8] For instance, AI leveraging natural language processing techniques can extract pertinent information from text data, such as TCM raw material names, processing methods, and pharmacological effects, transforming unstructured text into structured data that facilitates further analysis and utilization ([Fig. 3A], [B]).[19] [20]

Moreover, AI plays a pivotal role in optimizing the processing techniques of TCM raw materials. By utilizing mathematical modeling and numerical simulation methods, AI can simulate the physicochemical changes occurring during complex processing procedures, allowing for the optimization of process parameters to guarantee the quality and efficacy of medicinal materials.[21] This capability addresses the inherent complexities and abstractions often associated with traditional TCM processing methods, which lack objective measurement standards.

Employing AI helps standardize and quantify these processes, improving the quality of processed TCM raw materials. AI can analyze the impact of different processing methods on material quality during TCM raw material processing. ML and deep learning models further enable the optimization and control of key processing parameters.[22]

Additionally, AI plays a crucial role in the optimization and decision support for processing TCM raw materials. For instance, data mining technology, by establishing an orderly and efficient data processing system, can effectively optimize the parameters in the production process of medications based on TCM, thereby enhancing production efficiency and product quality ([Fig. 3C]).[23] These application instances fully demonstrate the extensive potential and practical application value of AI in the field of TCM processing.

Despite demonstrating high potential in processing Chinese herbal materials, AI still encounters several challenges. Enhancing the accuracy and robustness of AI algorithms necessitates large datasets and highly accurate models. Furthermore, practical applications require further investigation into issues such as data standardization and model interpretability. By addressing these challenges, AI can continue to revolutionize the processing of TCM raw materials, ensuring the preservation and enhancement of traditional pharmaceutical technology.

Application of Artificial Intelligence in the Extraction and Purification of Traditional Chinese Medicine Raw Materials

The application of AI in the extraction and purification of TCM showcases remarkable characteristics that underscore its transformative potential. Notably, AI significantly enhances the optimization of TCM extraction processes. In the case of continuous countercurrent extraction for Angelica dahurica formula granules, the integration of a near-infrared microspectrometer with AI technology facilitated rapid prediction of the content of six characteristic components ([Fig. 4A]).[24] This method establishes a scientific foundation for AI in analyzing and monitoring TCM production processes online, thereby dramatically improving the precision and efficiency of extraction processes.[24] This application instance not only demonstrates the technical advantages of AI in TCM extraction but also indicates its broad application potential in the production process of TCM.

Yang et al further demonstrated a novel approach, leveraging deep learning tools to optimize process parameters for the simultaneous extraction of camphor essential oil and lignin, thereby boosting the utilization rate of biological resources and enhancing economic benefits.[25] By employing ML and the Response Surface Methodology (RSM), key extraction process parameters, including solvent concentration, temperature, time, and pressure, can be precisely optimized to elevate the extraction rate and purity of target compounds. For instance, RSM was effectively utilized to optimize the extraction rate and purity during the ultrasonic-assisted extraction of flavonoids from Scutellaria baicalensis, leading to significant improvements in extraction efficiency and purity.[26] Ding et al combined RSM with Artificial Neural Networks (ANN) to predict and validate the optimal processing method for Schizonepetae Herba Carbonisata.[27]

Moreover, the adoption of ML-assisted data-driven optimization methods facilitates a comprehensive understanding and optimization of multistage processes involved in extracting polysaccharides and secondary metabolites from natural products.[28] Based on this method, the extraction, separation, and purification processes of baicalin from Scutellaria baicalensis were optimized ([Fig. 4B]). Specifically, the highest extraction yield of baicalin, which reached 91.84%, was achieved using ethanol as the solvent for ultrasonic-assisted extraction from dry powder. Additionally, the optimal process conditions for extracting baicalin from fresh slices in boiling water were determined, yielding an extraction rate of 70.72%.[29] Chen et al combined ML models with intelligent optimization algorithms to optimize the extraction of active ingredients from Salvia miltiorrhiza Bunge, significantly improving the extraction yield compared with traditional methods.[30] These application examples further demonstrate the importance and practicality of AI in the extraction process of TCM. Furthermore, in situations where sample data are limited during the extraction process, virtual sample data can effectively increase the sample size, thereby enabling the optimization of models trained on semisynthetic samples to obtain reliable process parameters.[31] This method not only addresses the issue of insufficient sample data but also provides a new approach for quality control in the process of TCM extraction using AI.

Advanced ML algorithms hold theoretical promise in improving the quality control optimization of TCM extraction processes.[32] By coupling AI with advanced extraction and purification equipment, such as microwave-assisted extraction and ultrasonic-assisted extraction systems, and optimizing parameters using AI, the extraction process can be automated and intellectualized, leading to enhanced operational efficiency and product quality.[33] Automated equipment and systems streamline repetitive tasks like weighing, mixing, filtering, and purifying, significantly boosting production efficiency and reducing labor costs.[34] The application of AI and automation equipment to optimize chemical separation processes has profoundly elevated both the efficiency and quality of these processes through automated and intelligent methodologies.[35]

In summary, AI's application in the extraction and purification of TCM exemplifies its ability to revolutionize traditional practices through precise optimization, enhanced process understanding, and automated operation, ultimately leading to improved product quality and operational efficiency.

Application of Artificial Intelligence in the Formulation and Shaping of Traditional Chinese Medicine-Based Drugs

The application of AI in the formulation and shaping of TCM-based drugs is progressively emerging as a focal point of research. AI and ML represent promising avenues for refining the design process of pharmaceutical formulations. These technologies expedite the formulation design process while enhancing drug consistency and bioavailability, particularly excelling in the estimation of degradation kinetics and the optimization of formulation parameters.[36]

At the level of formulation optimization, traditional TCM formulations often undergo adjustment through extensive experimental validation and data analysis. The integration of AI with ML algorithms enables the efficient analysis of extensive historical datasets, facilitating the precise identification of optimal formulation parameters. Specifically, ML techniques swiftly evaluate the impact of diverse components and process parameters on drug formulation consistency, thereby determining the optimal formulation ratio and production process.[37]

In the realm of formulation enhancement, Lu et al developed an improved version of ginsenoside Rh2 through the synergistic use of AI technology and molecular dynamics simulations, resulting in significant enhancements in its water solubility, dissolution rate, and bioavailability ([Fig. 5A]).[38] This achievement was facilitated by the application of predictive and optimization tools such as the “PharmSD” model, which possesses the capability to efficiently predict the physical stability, dissolution type, and dissolution rate of solid dispersions. By integrating these predictive results, PharmSD can construct virtual screening pipelines to assist users in screening various drug–polymer combinations to identify the optimal formulation ([Fig. 5B]). Additionally, Dong et al have introduced Formulation AI, a comprehensive web-based platform that simplifies formulation design by merely inputting basic information about drugs and excipients, thus streamlining the pharmaceutical manufacturing process.[39] Qian et al utilized a stepwise regression model to analyze the relationship between critical formulation process factors and the rheological properties of TCM ointments, combining ML to optimize the preparation process of these ointments.[40] Concurrently, a deep learning approach that combines automatic data segmentation and customized evaluation criteria tailored for pharmaceutical formulations has been developed to predict formulation performance. The emergence of this method heralds a gradual shift from an empirical paradigm to a data-driven paradigm in drug research.[41]

In terms of numerical simulation, the Discrete Element Method (DEM) technique has been applied in the shaping process of TCM-based drug formulations. DEM simulates the movement and interaction of particles during production, providing robust support for optimizing production processes and equipment design. AI methods, including ANNs, genetic algorithms, and fuzzy logic, have been applied in drug formulation to simulate and optimize various variables and their interactions with drug formulation properties.[42] The combination of AI with DEM further enhances the precision and efficiency of simulations, markedly reducing the research and development cycle.[43]

It is noteworthy that traditional single-modal AI models are insufficient for addressing the complexities involved in the formulation and shaping of TCM-based drugs. Therefore, future efforts should focus on integrating multitype data, such as chemical composition analysis data of medicinal materials, production process parameters, and historical experimental data, with AI to construct more comprehensive models. This approach will significantly improve the accuracy of predictions and optimizations in this domain.

Application of Artificial Intelligence in Traditional Chinese Medicine Quality Control

The application of AI in the quality control of TCM exhibits several distinctive attributes, fundamentally altering the methodology to ensure the uniformity and efficacy of these preparations. The procedure involved in the formulation of Chinese medicinal preparations is inherently intricate, influenced by a multitude of factors and parameters, often resulting in variability in quality.[44] AI has introduced substantial technological innovations into the assessment and regulation of TCM, not only enhancing the precision of quality control but also broadening the dimensions of quality evaluation.

Among the many applications of AI technology, a notable aspect is the use of ML methods, particularly Support Vector Machines, to assess the quality of TCM decoction pieces. This is achieved by extracting image features from their sliced morphology, providing an accurate and nondestructive method for quality control.[45]

Moreover, the amalgamation of Near-Infrared Spectroscopy (NIRS) with AI offers a swift and efficient mode for the analysis and quality control of TCM raw materials. This technology facilitates the simultaneous prediction of multiple quality attributes, such as total flavonoid content, xanthine oxidase inhibitory activity, and antioxidant activity, thereby augmenting the overall proficiency of quality control in Chinese herbal medicines.[46]

Ultra-high-performance liquid chromatography coupled with high-resolution mass spectrometry (UHPLC-HRMS) holds a pivotal role in the quality control of TCM.[47] When fused with AI technology, this methodology promises heightened analytical efficiency, enabling the rapid identification and quantification of drug constituents. For instance, the utilization of UHPLC-quadrupole (UHPLC-Q)/Orbitrap HRMS in conjunction with molecular networking has established a rapid analysis protocol for components in Qinggu San.[48]

Additionally, the integration of diverse spectroscopic techniques, including Raman spectroscopy, HSI, and terahertz time-domain spectroscopy, with AI has provided supplementary efficient detection methodologies for quality control in the manufacturing of TCM-based pharmaceuticals.[49] These techniques, coupled with AI algorithms, present a holistic approach to identifying and quantifying chemical indicators in Chinese herbal medicines.

Furthermore, AI has been harnessed to explore the intricate relationships between quality indicators and the overall functionality of TCM. For example, UHPLC-Q/time-of-flight mass spectrometry combined with partial least squares-discriminant analysis (UHPLC-Q/TOF-MS-PLS-DA) was used to screen chemical indicators, and a bioactivity-oriented evaluation method was employed to select quality markers (Q-markers). Quantitative assessment was then conducted using NIRS based on the characteristic wavenumber regions or characteristic points of the Q-markers. AI algorithms then scrutinize these data to offer novel insights and perspectives for TCM quality management ([Fig. 6]).[50]

With the emergence of high-throughput sequencing and systems biology, the investigation of TCM has transitioned from traditional experimental techniques to an omics-based paradigm. Wang et al exemplified this by utilizing a combination of UHPLC-Q-Orbitrap HRMS and UHPLC-MS/MS in conjunction with network pharmacological analysis to provide an innovative strategy for the quality control of complex TCM formulations.[51] This integration of AI and multiomic data effectively uncovers the multitarget action mechanisms of TCM compounds, fostering a deeper understanding and control of TCM quality and efficacy.[52] [53]

Automation technology, in tandem with AI, has also led to significant advancements in the standardization and uniformity of TCM production processes. By achieving full-process automation from raw materials to finished products, human intervention is minimized, resulting in enhanced production efficiency and quality uniformity.[54] The implementation of automation technology in the production process of Yunnan White Ointment exemplifies this, yielding improved production efficiency, quality uniformity, and reduced preparation costs.[55]

In conclusion, the incorporation of AI has presented unprecedented prospects for the standardization of TCM production processes. By amalgamating AI with various technologies, such as NIRS, UHPLC-HRMS, and automation, a comprehensive and efficient methodology for quality control in TCM pharmaceutical production is attained. However, we should also recognize that the application of AI technology in the quality control of TCM is still under continuous exploration and improvement. Further technical research and application promotion are needed in the future to promote the sustainable and healthy development of the TCM industry.

Summary and Prospect

The application of AI in the production of TCM and their preparations not only demonstrates numerous significant advantages but also continues to expand in practical scope. AI combined with DNA barcoding technology and HSI has achieved rapid and accurate identification and quality assessment of the TCM raw materials during their selection and harvesting. Furthermore, using big data analysis and ML algorithms, AI can predict the optimal harvesting time for TCM raw materials, thus improving the efficiency of herb collection.

In the selection of Chinese medicinal materials, AI can improve data processing, optimize processing techniques, and provide standardization and quantification, thus improving the quality of processed TCM materials. During the extraction and purification of TCM raw materials, AI can optimize the extraction process, accurately control key parameters, and improve the extraction rate and purity. Additionally, by integrating advanced extraction and purification equipment, AI can implement the automation and intelligentization of the extraction process.

In the formulation and shaping of TCM-based drugs, AI and ML algorithms can accelerate drug formula design, improve drug consistency and bioavailability, and further shorten the research and development cycle via numerical simulation techniques. Regarding quality control, AI combined with NIRS and Raman spectroscopy can provide new methods for the rapid analysis and quality control of TCM raw materials and produced drugs. Furthermore, the integration of AI with multiomic data provides a better understanding and control of the multitarget action mechanisms in TCM compounds, enhancing the comprehension and regulation of TCM quality and efficacy.

Notably, AI technology has also contributed to the construction of digital pharmaceutical production lines, enabling continuous production, effectively eliminating downtime between steps, and significantly reducing the likelihood of human error, further enhancing overall production efficiency. However, despite the significant progress made in the application of AI technology in the TCM industry, there are still certain differences in its prevalence and application scope. Currently, AI technology is mainly widely used in large TCM enterprises and scientific research institutions, with relatively limited application in small- and medium-sized enterprises and remote areas. This phenomenon limits the comprehensive promotion and maximization of the benefits of AI technology throughout the TCM industry. In the future, as technology continues to mature and costs further decrease, the application scope of AI technology in the TCM industry is expected to further expand, injecting more vitality into the innovative development of the TCM industry.

Although the application of AI technology in the TCM pharmaceutical industry is still in a rapid development stage, there has been a gradual increase in its application instances in various aspects such as the identification, material selection, extraction, purification, formulation design, quality control, and automation of production lines of TCM materials, demonstrating a broad application prospect. For example, AI technology can rapidly screen millions of TCM components and predict their pharmacological effects, toxicity, and interactions. This capability has greatly improved the efficiency and accuracy of TCM research and development, providing strong technical support for new drug discovery.

In summary, the application of AI technology in multiple key aspects of TCM materials and finished products has not only significantly improved the production efficiency and product quality of the TCM pharmaceutical industry but also effectively reduced manufacturing costs, promoting the intelligent transformation and innovative development of the TCM industry.

Discussion

When exploring the application of AI technology in the field of intelligent manufacturing of TCM, we note that reliable equipment is a crucial element for achieving precise control, especially in the context of the transformation toward intelligent manufacturing. However, research on engineering equipment that suits various TCM characteristics is still limited. Issues, such as nonuniform standards, and lack of support for real-time data collection and uploading, have resulted in a low number of related equipment patent applications.[56] To address these issues, effective actions must be taken.

First, it is necessary to strengthen the collection and processing supervision of raw materials to ensure the quality and safety of medicinal herbs. Second, it is important to promote the modernization and standardization of TCM production processes to improve product consistency and safety. Additionally, quality control and supervision must be improved to ensure that TCM products meet the qualification standards. And modern technology must be actively applied to improve the efficiency, quality, and safety of the TCM production process. Finally, continuous efforts should be made to improve the quality and availability of TCM pharmaceutical data by strengthening the standardization and management of the data collection process to ensure data accuracy and completeness. For example, it is essential to establish unified data collection standards and procedures, standardize data obtained from different sources to reduce discrepancies and errors, and increase the investment in research on data cleaning and denoising technologies to improve data quality.

Additionally, the establishment and improvement of data-sharing mechanisms must be promoted. Although data sharing currently faces challenges, such as privacy protection, effective methods to balance data sharing and privacy protection must be developed via technological innovation and policy guidance. For example, encryption technology and secure protocols can be used to ensure the safety of shared data; furthermore, data-sharing platforms must be established, and clear data usage rules, as well as permission management mechanisms, must be developed to promote the full flow and utilization of data under legal and compliance conditions.

The stability and interpretability of the algorithms are essential for the future development of AI pharmaceutical equipment. To improve algorithm stability, it is necessary to continuously optimize the design and implementation of algorithms and strengthen the monitoring and evaluation of algorithm performance. New algorithm optimization techniques, such as adaptive learning rate adjustment and regularization methods, can be introduced to improve the convergence speed and stability of the algorithms. Additionally, an algorithm performance evaluation index system must be established to comprehensively assess algorithm performance in different scenarios and promptly identify and resolve issues within the algorithms. Regarding interpretability, research on black-box algorithms, such as deep learning, should be enhanced to investigate the development of interpretable AI algorithms. For example, using visualization techniques to display the decision-making process of algorithms can help pharmaceutical researchers better understand the operating principles and results of the algorithms, thereby increasing the trust in these algorithms and their application effectiveness.

Conflict of Interest

None declared.

• References

• 1 Liu Y, Duan T, Li J, Bao H. New records of investigation and distribution of medicinal plant resources in Junan County of Shandong Province by the fourth national general investigation of natural resources of Chinese materia medica [in Chinese]. J Gansu Univ Chin Med 2019; 36 (06) 45-48
  Search in Google Scholar
• 2 China Commerce Industry Research Institute. Forecast and Analysis of the Market Scale of China's Pharmaceutical Industry and Its Sub-sectors; 2024 [in Chinese]. Accessed November 24, 2024 at: https://www.askci.com/reports/20200527/1550004636881713.shtml
• 3 Liu C. Quality markers of traditional Chinese medicine: a new concept for quality control of traditional Chinese medicine products. Yaowu Pingjia Yanjiu 2019; 42 (01) 1-12
  Search in Google Scholar
• 4 Zhou E, Shen Q, Hou Y. Integrating artificial intelligence into the modernization of traditional Chinese medicine industry: a review. Front Pharmacol 2024; 15: 1181183
  Search in Google Scholar
• 5 Zhou BW, Zhu LL, Zhu L. et al. Exploration of a novel universal method for identification of Chinese medicines varieties based on artificial intelligence with fingerprints on multi-elements and multi-data [in Chinese]. Fenxi Ceshi Xuebao 2021; 40 (01) 106-111
  Search in Google Scholar
• 6 Xu Y, Liu X, Cao X. et al. Artificial intelligence: a powerful paradigm for scientific research. Innovation (Camb) 2021; 2 (04) 100179
  Search in Google Scholar
• 7 Arinez JF, Chang Q, Gao RX, Xu C, Zhang J. Artificial intelligence in advanced manufacturing: current status and future outlook. J Manuf Sci Eng 2020; 142 (11) 110804
  Search in Google Scholar
• 8 Xiong HS, Wang BX, Hou J. et al. Application scenario design and prospect of generative artificial intelligence (AI) in intelligent manufacturing and supply chain of traditional Chinese medicine [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (14) 3963-3970
  Search in Google Scholar
• 9 Zhang X, Jiao X, Su C. et al. Research progresses in and management strategies for aflatoxin contamination of fruits and seeds medicinal materials in China [in Chinese]. Plant Protection 2023; 49 (05) 118-126
  Search in Google Scholar
• 10 Qi P, Wang Y, Xu X. et al. Study on the degradation of aluminum phosphide residues in Chinese medicinal materials [in Chinese]. Asia-Pacific Tradit Med 2024; 20 (01) 72-75
  Search in Google Scholar
• 11 Unnikrishnan R, Sumod M, Jayaraj R, Sujanapal P, Dev SA. The efficacy of machine learning algorithm for raw drug authentication in Coscinium fenestratum (Gaertn.) Colebr. employing a DNA barcode database. Physiol Mol Biol Plants 2021; 27 (03) 605-617
  Search in Google Scholar
• 12 Wu C. Research on identification method of traditional Chinese medicine based on deep learning [in Chinese]. Master's thesis. Chengdu: Sichuan University; 2021
  Search in Google Scholar
• 13 Pan Y, Zhang H, Chen Y, Gong X, Yan J, Zhang H. Applications of hyperspectral imaging technology combined with machine learning in quality control of traditional Chinese medicine from the perspective of artificial intelligence: a review. Crit Rev Anal Chem 2024; 54 (08) 2850-2864
  Search in Google Scholar
• 14 Wang H, Liu SY, Wang H, Li W, Lyu M. Research and application of intelligent hyperspectral analysis technology for Chinese materia medica [in Chinese]. Zhongguo Zhongyao Zazhi 2023; 48 (16) 4320-4327
  Search in Google Scholar
• 15 Tao Y, Chen L, Jiang EC, Yang JZ. Application and prospects of hyperspectral imaging and deep learning in traditional Chinese medicine in context of AI and industry 4.0 [in Chinese]. Zhongguo Zhongyao Zazhi 2020; 45 (22) 5438-5442
  Search in Google Scholar
• 16 Li P, Shen T, Li L, Wang Y. Optimization of the selection of suitable harvesting periods for medicinal plants: taking Dendrobium officinale as an example. Plant Methods 2024; 20 (01) 43
  Search in Google Scholar
• 17 Li Q, Wang J, Zhang Y. Exploring the public space model of smart recreation for Chinese medicine cultivation based on artificial intelligence and blockchain technology. In: Gan J, Pan Y, Zhou J, Liu D, Song X, Lu Z. eds. Computer Science and Educational Informatization. CSEI 2023. Communications in Computer and Information Science, vol 1900. Springer, Singapore; 2024
  Search in Google Scholar
• 18 Zhang W, Zhang C, Cao L. et al. Application of digital-intelligence technology in the processing of Chinese materia medica. Front Pharmacol 2023; 14 (00) 1208055
  Search in Google Scholar
• 19 Chung MC, Su LJ, Chen CL, Wu LC. AI-assisted literature exploration of innovative Chinese medicine formulas. Front Pharmacol 2024; 15: 1347882
  Search in Google Scholar
• 20 Zhang T, Huang Z, Wang Y, Wen C, Peng Y, Ye Y. Information extraction from the text data on traditional Chinese medicine: a review on tasks, challenges, and methods from 2010 to 2021. Evid Based Complement Alternat Med 2022; 2022: 1679589
  Search in Google Scholar
• 21 Wu YF, Wang ZQ, Wan XH. et al. Application of discrete element method (DEM) in pharmaceutical process of solid traditional Chinese medicine preparations [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (12) 3152-3159
  Search in Google Scholar
• 22 Xue QL, Miao KH, Yu Y, Li Z. Methodology for adaptive decision–making research on manufacturing process of traditional Chinese medicine based on deep reinforcement learning [in Chinese]. Zhongguo Zhongyao Zazhi 2023; 48 (02) 562-568
  Search in Google Scholar
• 23 Li X, Yue H, Yin J. et al. Research on optimization of process parameters of traditional Chinese medicine based on data mining technology. Comput Intell Neurosci 2022; 2022: 2278416
  Search in Google Scholar
• 24 Zhang M, Lin B, Ma X. et al. Application of artificial intelligence combined with near infrared spectroscopy in the continuous counter-current extraction process of Angelica dahurica formula granules. Spectrochim Acta A Mol Biomol Spectrosc 2024; 322: 124748
  Search in Google Scholar
• 25 Yang H, Zhou P, Li X, Shen L. A green and efficient approach for the simultaneous extraction and mechanisms of essential oil and lignin from Cinnamomum camphora: process optimization based on deep learning. Int J Biol Macromol 2024; 277 (Pt 4, P4) 134215
  Search in Google Scholar
• 26 Ge Z, Zhao Y, Xu L, Zhu C, Hao X. Ultrasound-assisted aqueous two-phase extraction of flavonoids from scutellariae radix and evaluation of their bioactivities in vitro . Curr Anal Chem 2024; 20 (02) e300124226476
  Search in Google Scholar
• 27 Ding X, Wang H, Li H. et al. Optimization of the processing technology of schizonepetae herba carbonisata using response surface methodology and artificial neural network and comparing the chemical profiles between raw and charred schizonepetae herba by UPLC-Q-TOF-MS. Heliyon 2023; 9 (02) e13398
  Search in Google Scholar
• 28 Mu J, Yu J, Ren X. et al. Machine learning-assisted data-driven optimization and understanding of the multiple-stage process for extraction of polysaccharides and secondary metabolites from natural products. Green Chem 2023; 25 (08) 3057-3068
  Search in Google Scholar
• 29 Liu L, Zhang M, Cao B. et al. Optimization of extraction, separation, and purification of baicalin in Scutellaria baicalensis using response surface methodology. Ind Crops Prod 2024; 214: 118555
  Search in Google Scholar
• 30 Chen B, Zhao Y, Yu D. et al. Optimizing the extraction of active components from Salvia miltiorrhiza by combination of machine learning models and intelligent optimization algorithms and its correlation analysis of antioxidant activity. Prep Biochem Biotechnol 2024; 54 (03) 358-373
  Search in Google Scholar
• 31 Guan Y, Chen J, Dong C. Application of virtual sample generation and screening in process parameter optimization of botanical medicinal materials. Curr Top Med Chem 2023; 23 (08) 618-626
  Search in Google Scholar
• 32 Cai X, Chen Z. Application of machine learning in the extraction process of traditional Chinese medicine [in Chinese]. J Shandong Normal Univ 2023; 38 (04) 326-334
  Search in Google Scholar
• 33 Wang C, Pan Y, Fan G, Chai Y, Wu Y. Application of an efficient strategy based on MAE, HPLC-DAD-MS/MS and HSCCC for the rapid extraction, identification, separation and purification of flavonoids from Fructus Aurantii Immaturus. Biomed Chromatogr 2010; 24 (03) 235-244
  Search in Google Scholar
• 34 Zou F, Yang R. Design and application of intelligent instrument management system [in Chinese]. Zidonghua Yu Yibiao 2013; 28 (10) 5-10
  Search in Google Scholar
• 35 Wang W, Xiong H, Zhang D. et al. Intelligent chemical purification technique based on machine learning. ArXiv. Preprint. April 14, 2024. Accessed April 14, 2024 at: https://doi-org.accesdistant.sorbonne-universite.fr/10.48550/arXiv.2404.09114
• 36 Dey H, Arya N, Mathur H, Chatterjee N, Jadon R. Exploring the role of artificial intelligence and machine learning in pharmaceutical formulation design. Int J Newgen Res Pharm Healthc 2024; 2 (01) 30-41
  Search in Google Scholar
• 37 Dong J, Gao H, Ouyang D. PharmSD: A novel AI-based computational platform for solid dispersion formulation design. Int J Pharm 2021; 604: 120705
  Search in Google Scholar
• 38 Lu T, Wu T, Zhong H. et al. Computer-driven formulation development of Ginsenoside Rh2 ternary solid dispersion. Drug Deliv Transl Res 2025; 15 (02) 700-716
  Search in Google Scholar
• 39 Dong J, Wu Z, Xu H, Ouyang D. FormulationAI: a novel web-based platform for drug formulation design driven by artificial intelligence. Brief Bioinform 2023; 25 (01) bbad419
  Search in Google Scholar
• 40 Qian X, Wang K, Ma Y. et al. Refining the rheological characteristics of high drug loading ointment via SDS and machine learning. PLoS One 2024; 19 (05) e0303199
  Search in Google Scholar
• 41 Yang Y, Ye Z, Su Y, Zhao Q, Li X, Ouyang D. Deep learning for in vitro prediction of pharmaceutical formulations. Acta Pharm Sin B 2019; 9 (01) 177-185
  Search in Google Scholar
• 42 Landin M, Rowe RC. Artificial neural networks technology to model, understand, and optimize drug formulations. In: Aguilar JE. eds. Formulation Tools for Pharmaceutical Development. Woodhead Publishing; 2013: 7-37
  Search in Google Scholar
• 43 Gu Q, Wu H, Sui X. et al. Leveraging numerical simulation technology to advance drug preparation: a comprehensive review of application scenarios and cases. Pharmaceutics 2024; 16 (10) 1304
  Search in Google Scholar
• 44 Yang AH, Shi GL, Liu YL. et al. Application of multivariate models in whole process control of solid preparations [in Chinese]. Zhongguo Zhongyao Zazhi 2022; 47 (14) 3701-3708
  Search in Google Scholar
• 45 Guo J, Li J, Ding P. The application of machine learning and artificial intelligence technology in the production quality management of traditional Chinese medicine decoction pieces. Int J Interact Des Manuf 2023; 18 (01) 239-251
  Search in Google Scholar
• 46 Hao JW, Chen ND, Fan XX. et al. Rapid determination of total flavonoid content, xanthine oxidase inhibitory activities, and antioxidant activity in Prunus mume by near-infrared spectroscopy. J Pharm Biomed Anal 2024; 246: 116164
  Search in Google Scholar
• 47 Ma J, Li K, Shi S, Li J, Tang S, Liu L. The application of UHPLC-HRMS for quality control of traditional Chinese medicine. Front Pharmacol 2022; 13: 922488
  Search in Google Scholar
• 48 Xiao LJ, Ai JH, Huang FF. et al. Identification of chemical components in Qinggu San reference sample of classical prescription based on UHPLC-Q/Orbitrap HRMS combined with molecular network technology [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (13) 3526-3539
  Search in Google Scholar
• 49 Wan XH, Tao Q, Wang ZQ. et al. Rapid non-destructive detection technology for traditional Chinese medicine preparations based on machine learning: a review [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (24) 6541-6548
  Search in Google Scholar
• 50 Bai G, Zhang T, Hou Y, Ding G, Jiang M, Luo G. From quality markers to data mining and intelligence assessment: a smart quality-evaluation strategy for traditional Chinese medicine based on quality markers. Phytomedicine 2018; 44: 109-116
  Search in Google Scholar
• 51 Wang X, Zhou W, Wang Q. et al. A novel and comprehensive strategy for quality control in complex Chinese medicine formula using UHPLC-Q-Orbitrap HRMS and UHPLC-MS/MS combined with network pharmacology analysis: take Tangshen formula as an example. J Chromatogr B Analyt Technol Biomed Life Sci 2021; 1183: 122889
  Search in Google Scholar
• 52 Zhu X, Yao Q, Yang P. et al. Multi-omics approaches for in-depth understanding of therapeutic mechanism for traditional Chinese medicine. Front Pharmacol 2022; 13: 1031051
  Search in Google Scholar
• 53 Deng X, Lei HY, Ren YS. et al. A novel strategy for active compound efficacy status identification in multi-tropism Chinese herbal medicine (Scutellaria baicalensis Georgi) based on multi-indexes spectrum-effect gray correlation analysis. J Ethnopharmacol 2023; 300: 115677
  Search in Google Scholar
• 54 Yan DX, Wang Y, Mi HM. Application of automation technology in the pharmaceutical industry [in Chinese]. Zuo Wu Xue Bao 2024; 46 (08) 988
  Search in Google Scholar
• 55 Deng W. Application of automatic boiling equipment in the research and development of Yunnan white ointment. Front Med Sci Res 2024; 6 (08) 22-28
  Search in Google Scholar
• 56 Zhang YT, Wang XC, Huang Y. et al. Research status of traditional Chinese medicine processing equipment and its technology upgrade approach strategy [in Chinese]. Zhong Cao Yao 2022; 53 (05) 1540-1547
  Search in Google Scholar

Address for correspondence

Publication History

Received: 19 December 2024

Accepted: 18 April 2025

Article published online:
27 May 2025

© 2025. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany

• References

• 1 Liu Y, Duan T, Li J, Bao H. New records of investigation and distribution of medicinal plant resources in Junan County of Shandong Province by the fourth national general investigation of natural resources of Chinese materia medica [in Chinese]. J Gansu Univ Chin Med 2019; 36 (06) 45-48
  Search in Google Scholar
• 2 China Commerce Industry Research Institute. Forecast and Analysis of the Market Scale of China's Pharmaceutical Industry and Its Sub-sectors; 2024 [in Chinese]. Accessed November 24, 2024 at: https://www.askci.com/reports/20200527/1550004636881713.shtml
• 3 Liu C. Quality markers of traditional Chinese medicine: a new concept for quality control of traditional Chinese medicine products. Yaowu Pingjia Yanjiu 2019; 42 (01) 1-12
  Search in Google Scholar
• 4 Zhou E, Shen Q, Hou Y. Integrating artificial intelligence into the modernization of traditional Chinese medicine industry: a review. Front Pharmacol 2024; 15: 1181183
  Search in Google Scholar
• 5 Zhou BW, Zhu LL, Zhu L. et al. Exploration of a novel universal method for identification of Chinese medicines varieties based on artificial intelligence with fingerprints on multi-elements and multi-data [in Chinese]. Fenxi Ceshi Xuebao 2021; 40 (01) 106-111
  Search in Google Scholar
• 6 Xu Y, Liu X, Cao X. et al. Artificial intelligence: a powerful paradigm for scientific research. Innovation (Camb) 2021; 2 (04) 100179
  Search in Google Scholar
• 7 Arinez JF, Chang Q, Gao RX, Xu C, Zhang J. Artificial intelligence in advanced manufacturing: current status and future outlook. J Manuf Sci Eng 2020; 142 (11) 110804
  Search in Google Scholar
• 8 Xiong HS, Wang BX, Hou J. et al. Application scenario design and prospect of generative artificial intelligence (AI) in intelligent manufacturing and supply chain of traditional Chinese medicine [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (14) 3963-3970
  Search in Google Scholar
• 9 Zhang X, Jiao X, Su C. et al. Research progresses in and management strategies for aflatoxin contamination of fruits and seeds medicinal materials in China [in Chinese]. Plant Protection 2023; 49 (05) 118-126
  Search in Google Scholar
• 10 Qi P, Wang Y, Xu X. et al. Study on the degradation of aluminum phosphide residues in Chinese medicinal materials [in Chinese]. Asia-Pacific Tradit Med 2024; 20 (01) 72-75
  Search in Google Scholar
• 11 Unnikrishnan R, Sumod M, Jayaraj R, Sujanapal P, Dev SA. The efficacy of machine learning algorithm for raw drug authentication in Coscinium fenestratum (Gaertn.) Colebr. employing a DNA barcode database. Physiol Mol Biol Plants 2021; 27 (03) 605-617
  Search in Google Scholar
• 12 Wu C. Research on identification method of traditional Chinese medicine based on deep learning [in Chinese]. Master's thesis. Chengdu: Sichuan University; 2021
  Search in Google Scholar
• 13 Pan Y, Zhang H, Chen Y, Gong X, Yan J, Zhang H. Applications of hyperspectral imaging technology combined with machine learning in quality control of traditional Chinese medicine from the perspective of artificial intelligence: a review. Crit Rev Anal Chem 2024; 54 (08) 2850-2864
  Search in Google Scholar
• 14 Wang H, Liu SY, Wang H, Li W, Lyu M. Research and application of intelligent hyperspectral analysis technology for Chinese materia medica [in Chinese]. Zhongguo Zhongyao Zazhi 2023; 48 (16) 4320-4327
  Search in Google Scholar
• 15 Tao Y, Chen L, Jiang EC, Yang JZ. Application and prospects of hyperspectral imaging and deep learning in traditional Chinese medicine in context of AI and industry 4.0 [in Chinese]. Zhongguo Zhongyao Zazhi 2020; 45 (22) 5438-5442
  Search in Google Scholar
• 16 Li P, Shen T, Li L, Wang Y. Optimization of the selection of suitable harvesting periods for medicinal plants: taking Dendrobium officinale as an example. Plant Methods 2024; 20 (01) 43
  Search in Google Scholar
• 17 Li Q, Wang J, Zhang Y. Exploring the public space model of smart recreation for Chinese medicine cultivation based on artificial intelligence and blockchain technology. In: Gan J, Pan Y, Zhou J, Liu D, Song X, Lu Z. eds. Computer Science and Educational Informatization. CSEI 2023. Communications in Computer and Information Science, vol 1900. Springer, Singapore; 2024
  Search in Google Scholar
• 18 Zhang W, Zhang C, Cao L. et al. Application of digital-intelligence technology in the processing of Chinese materia medica. Front Pharmacol 2023; 14 (00) 1208055
  Search in Google Scholar
• 19 Chung MC, Su LJ, Chen CL, Wu LC. AI-assisted literature exploration of innovative Chinese medicine formulas. Front Pharmacol 2024; 15: 1347882
  Search in Google Scholar
• 20 Zhang T, Huang Z, Wang Y, Wen C, Peng Y, Ye Y. Information extraction from the text data on traditional Chinese medicine: a review on tasks, challenges, and methods from 2010 to 2021. Evid Based Complement Alternat Med 2022; 2022: 1679589
  Search in Google Scholar
• 21 Wu YF, Wang ZQ, Wan XH. et al. Application of discrete element method (DEM) in pharmaceutical process of solid traditional Chinese medicine preparations [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (12) 3152-3159
  Search in Google Scholar
• 22 Xue QL, Miao KH, Yu Y, Li Z. Methodology for adaptive decision–making research on manufacturing process of traditional Chinese medicine based on deep reinforcement learning [in Chinese]. Zhongguo Zhongyao Zazhi 2023; 48 (02) 562-568
  Search in Google Scholar
• 23 Li X, Yue H, Yin J. et al. Research on optimization of process parameters of traditional Chinese medicine based on data mining technology. Comput Intell Neurosci 2022; 2022: 2278416
  Search in Google Scholar
• 24 Zhang M, Lin B, Ma X. et al. Application of artificial intelligence combined with near infrared spectroscopy in the continuous counter-current extraction process of Angelica dahurica formula granules. Spectrochim Acta A Mol Biomol Spectrosc 2024; 322: 124748
  Search in Google Scholar
• 25 Yang H, Zhou P, Li X, Shen L. A green and efficient approach for the simultaneous extraction and mechanisms of essential oil and lignin from Cinnamomum camphora: process optimization based on deep learning. Int J Biol Macromol 2024; 277 (Pt 4, P4) 134215
  Search in Google Scholar
• 26 Ge Z, Zhao Y, Xu L, Zhu C, Hao X. Ultrasound-assisted aqueous two-phase extraction of flavonoids from scutellariae radix and evaluation of their bioactivities in vitro . Curr Anal Chem 2024; 20 (02) e300124226476
  Search in Google Scholar
• 27 Ding X, Wang H, Li H. et al. Optimization of the processing technology of schizonepetae herba carbonisata using response surface methodology and artificial neural network and comparing the chemical profiles between raw and charred schizonepetae herba by UPLC-Q-TOF-MS. Heliyon 2023; 9 (02) e13398
  Search in Google Scholar
• 28 Mu J, Yu J, Ren X. et al. Machine learning-assisted data-driven optimization and understanding of the multiple-stage process for extraction of polysaccharides and secondary metabolites from natural products. Green Chem 2023; 25 (08) 3057-3068
  Search in Google Scholar
• 29 Liu L, Zhang M, Cao B. et al. Optimization of extraction, separation, and purification of baicalin in Scutellaria baicalensis using response surface methodology. Ind Crops Prod 2024; 214: 118555
  Search in Google Scholar
• 30 Chen B, Zhao Y, Yu D. et al. Optimizing the extraction of active components from Salvia miltiorrhiza by combination of machine learning models and intelligent optimization algorithms and its correlation analysis of antioxidant activity. Prep Biochem Biotechnol 2024; 54 (03) 358-373
  Search in Google Scholar
• 31 Guan Y, Chen J, Dong C. Application of virtual sample generation and screening in process parameter optimization of botanical medicinal materials. Curr Top Med Chem 2023; 23 (08) 618-626
  Search in Google Scholar
• 32 Cai X, Chen Z. Application of machine learning in the extraction process of traditional Chinese medicine [in Chinese]. J Shandong Normal Univ 2023; 38 (04) 326-334
  Search in Google Scholar
• 33 Wang C, Pan Y, Fan G, Chai Y, Wu Y. Application of an efficient strategy based on MAE, HPLC-DAD-MS/MS and HSCCC for the rapid extraction, identification, separation and purification of flavonoids from Fructus Aurantii Immaturus. Biomed Chromatogr 2010; 24 (03) 235-244
  Search in Google Scholar
• 34 Zou F, Yang R. Design and application of intelligent instrument management system [in Chinese]. Zidonghua Yu Yibiao 2013; 28 (10) 5-10
  Search in Google Scholar
• 35 Wang W, Xiong H, Zhang D. et al. Intelligent chemical purification technique based on machine learning. ArXiv. Preprint. April 14, 2024. Accessed April 14, 2024 at: https://doi-org.accesdistant.sorbonne-universite.fr/10.48550/arXiv.2404.09114
• 36 Dey H, Arya N, Mathur H, Chatterjee N, Jadon R. Exploring the role of artificial intelligence and machine learning in pharmaceutical formulation design. Int J Newgen Res Pharm Healthc 2024; 2 (01) 30-41
  Search in Google Scholar
• 37 Dong J, Gao H, Ouyang D. PharmSD: A novel AI-based computational platform for solid dispersion formulation design. Int J Pharm 2021; 604: 120705
  Search in Google Scholar
• 38 Lu T, Wu T, Zhong H. et al. Computer-driven formulation development of Ginsenoside Rh2 ternary solid dispersion. Drug Deliv Transl Res 2025; 15 (02) 700-716
  Search in Google Scholar
• 39 Dong J, Wu Z, Xu H, Ouyang D. FormulationAI: a novel web-based platform for drug formulation design driven by artificial intelligence. Brief Bioinform 2023; 25 (01) bbad419
  Search in Google Scholar
• 40 Qian X, Wang K, Ma Y. et al. Refining the rheological characteristics of high drug loading ointment via SDS and machine learning. PLoS One 2024; 19 (05) e0303199
  Search in Google Scholar
• 41 Yang Y, Ye Z, Su Y, Zhao Q, Li X, Ouyang D. Deep learning for in vitro prediction of pharmaceutical formulations. Acta Pharm Sin B 2019; 9 (01) 177-185
  Search in Google Scholar
• 42 Landin M, Rowe RC. Artificial neural networks technology to model, understand, and optimize drug formulations. In: Aguilar JE. eds. Formulation Tools for Pharmaceutical Development. Woodhead Publishing; 2013: 7-37
  Search in Google Scholar
• 43 Gu Q, Wu H, Sui X. et al. Leveraging numerical simulation technology to advance drug preparation: a comprehensive review of application scenarios and cases. Pharmaceutics 2024; 16 (10) 1304
  Search in Google Scholar
• 44 Yang AH, Shi GL, Liu YL. et al. Application of multivariate models in whole process control of solid preparations [in Chinese]. Zhongguo Zhongyao Zazhi 2022; 47 (14) 3701-3708
  Search in Google Scholar
• 45 Guo J, Li J, Ding P. The application of machine learning and artificial intelligence technology in the production quality management of traditional Chinese medicine decoction pieces. Int J Interact Des Manuf 2023; 18 (01) 239-251
  Search in Google Scholar
• 46 Hao JW, Chen ND, Fan XX. et al. Rapid determination of total flavonoid content, xanthine oxidase inhibitory activities, and antioxidant activity in Prunus mume by near-infrared spectroscopy. J Pharm Biomed Anal 2024; 246: 116164
  Search in Google Scholar
• 47 Ma J, Li K, Shi S, Li J, Tang S, Liu L. The application of UHPLC-HRMS for quality control of traditional Chinese medicine. Front Pharmacol 2022; 13: 922488
  Search in Google Scholar
• 48 Xiao LJ, Ai JH, Huang FF. et al. Identification of chemical components in Qinggu San reference sample of classical prescription based on UHPLC-Q/Orbitrap HRMS combined with molecular network technology [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (13) 3526-3539
  Search in Google Scholar
• 49 Wan XH, Tao Q, Wang ZQ. et al. Rapid non-destructive detection technology for traditional Chinese medicine preparations based on machine learning: a review [in Chinese]. Zhongguo Zhongyao Zazhi 2024; 49 (24) 6541-6548
  Search in Google Scholar
• 50 Bai G, Zhang T, Hou Y, Ding G, Jiang M, Luo G. From quality markers to data mining and intelligence assessment: a smart quality-evaluation strategy for traditional Chinese medicine based on quality markers. Phytomedicine 2018; 44: 109-116
  Search in Google Scholar
• 51 Wang X, Zhou W, Wang Q. et al. A novel and comprehensive strategy for quality control in complex Chinese medicine formula using UHPLC-Q-Orbitrap HRMS and UHPLC-MS/MS combined with network pharmacology analysis: take Tangshen formula as an example. J Chromatogr B Analyt Technol Biomed Life Sci 2021; 1183: 122889
  Search in Google Scholar
• 52 Zhu X, Yao Q, Yang P. et al. Multi-omics approaches for in-depth understanding of therapeutic mechanism for traditional Chinese medicine. Front Pharmacol 2022; 13: 1031051
  Search in Google Scholar
• 53 Deng X, Lei HY, Ren YS. et al. A novel strategy for active compound efficacy status identification in multi-tropism Chinese herbal medicine (Scutellaria baicalensis Georgi) based on multi-indexes spectrum-effect gray correlation analysis. J Ethnopharmacol 2023; 300: 115677
  Search in Google Scholar
• 54 Yan DX, Wang Y, Mi HM. Application of automation technology in the pharmaceutical industry [in Chinese]. Zuo Wu Xue Bao 2024; 46 (08) 988
  Search in Google Scholar
• 55 Deng W. Application of automatic boiling equipment in the research and development of Yunnan white ointment. Front Med Sci Res 2024; 6 (08) 22-28
  Search in Google Scholar
• 56 Zhang YT, Wang XC, Huang Y. et al. Research status of traditional Chinese medicine processing equipment and its technology upgrade approach strategy [in Chinese]. Zhong Cao Yao 2022; 53 (05) 1540-1547
  Search in Google Scholar