Application and research progress on artificial intelligence in the quality of Traditional Chinese Medicine

TL;DR

This paper reviews how artificial intelligence is being used to improve the quality control of Traditional Chinese Medicine through advanced data analysis and predictive modeling.

Contribution

The paper provides a comprehensive review of AI applications in TCM quality control, emphasizing integration with multi-omics and addressing technical challenges.

Findings

AI enables efficient handling of heterogeneous TCM data for quality prediction and anomaly detection.

Recent advances include AI-based sensing for authenticity verification, origin tracing, and quality grading.

Integration of AI with multi-omics supports efficacy evaluation and safety assessment of TCM.

Abstract

The clinical safety and therapeutic performance of Traditional Chinese Medicine (TCM) are closely tied to its quality. However, with the rapid expansion of the TCM industry, conventional quality control approaches based on empirical observations and single-metabolite quantification have become increasingly inadequate for addressing the complex and variable requirements of quality assessment. In recent years, artificial intelligence (AI)—with strong capabilities in data processing and pattern recognition—has emerged as a promising tool for establishing predictive models to efficiently handle heterogeneous, multi-source datasets (such as spectra, chromatograms, images, and textual information). This enables intelligent prediction of quality indicators and anomaly detection, and offering novel strategies for modernizing TCM quality control. This review provides a comprehensive synthesis of commonly applied machine learning and deep learning algorithms, systematically outlining recent advances in AI-enabled sensing applications such as image recognition, odor analysis, authenticity verification, origin tracing, quality grading, and storage-age determination. It further emphasizes the integration of AI with multi-omics and bioinformatics approaches for efficacy-oriented evaluation and safety assessment, including identification of Q-markers, elucidation of pharmacodynamic mechanisms, and predictive modeling of both endogenous and exogenous toxic metabolites. It also identifies key challenges and technical bottlenecks, and outlines priorities for building scalable, regulation-aware, data-driven quality-control systems that support the sustainable, high-quality development of the TCM industry.

Figures