Quality Control of Herbal Medicine Based on Analytical Techniques and Machine Learning: Current Advances and Future Perspectives
Yihong Shen, Huan Du, Fenglian Liu, Xiaolin Gou, Yiwen Tao, Xinge Lan, Jing Zhang, Yinghao Yin, Qi Li, Gang Fan · Phytochemical Analysis · 2026
INTRODUCTION: This study enhances the quality control (QC) system essential for the modernization and global acceptance of herbal medicines (HMs). OBJECTIVES: This review systematically explores the transformative integration of modern analytical technologies (e.g., IR, MS, and NMR) with machine learning (ML) for advancing HMs QC. Focusing on research from the past 10 years, we highlight groundbreaking applications in three pivotal areas: geographical origin tracing, adulteration detection, and species identification of HMs. METHODS: A comprehensive review of the literature from the past 10 years was conducted, focusing on geographical origin tracing, adulteration detection, and species identification of HMs. RESULTS: Providing a structured overview of analytical technologies and ML algorithmic principles demonstrates how ML models decode complex, high-dimensional chemical data to establish predictive and holistic quality assessment frameworks that transcend the limitations of single-marker analysis. CONCLUSION: This synthesis maps the current research landscape and is a foundational reference for guiding future efforts toward standardized, data-driven, and intelligent quality assurance in HMs.