Abstract: Herbal formulations remain important to global health, despite their complex compositions and lack of standardized biomarkers, which make the dissolution profiling less valuable. Dissolution testing, which is known to be an ideal reflector of the in vivo drug release, guarantees the safety as well as therapeutic effectiveness of formulations, but its utilization in herbal medicines is still restricted. In this context, Artificial Intelligence (AI) supported by Machine Learning (ML) and Deep Learning (DL) offers significant potential in interpreting complex datasets that traditional methodologies find challenging to elucidate. By improving drug dissolution conditions and discerning elusive patterns within herbal matrices, AI would be able to refine in vitro–in vivo correlations, which would accelerate formulation development. This review attempts to examine and explore the developing convergence of artificial intelligence and dissolution studies in herbal therapeutics, emphasizing both transformative possibilities—such as enhanced bioavailability predictions and tailored medical approaches—and significant challenges, including data integrity, AI model transparency, and ethical considerations. Recent technological breakthroughs and case studies are also discussed to highlight how AI-driven tactics could close long-standing gaps between traditional herbal knowledge and modern pharmacological expertise. Combining AI with dissolution science could lead to more dependable, standardized, and widely accepted herbal formulations in the near future.
Das et al. (Wed,) studied this question.