Melatonin content was screened in leaves of seven edible herbs used as sleeping aids in Thai traditional medicine. These plants are Piper nigrum L, Sesbania glandiflora (L.) Desv., Sesbania sesban (L.) Merr., Senna tora (L.) Roxb., Moringa oleifera Lam., Momordica charantia L. and Baccaurea ramiflora Lour. Dried leaves were extracted by sonication in methanol for six hours at room temperature, and then melatonin was purified by C18 solid phase extraction (SPE). Melatonin was then quantified by a validated RP-C18 HPLC method with fluorescent detection.

Trust in Traditional Thai Medicine (TTM) among Thai people has been reduced due to a lack of objective standards and the susceptibility of the general population to false information. The emergence of generative artificial intelligence (Gen AI) has significantly impacted various industries, including traditional medicine. However, previous Gen AI models have primarily focused on prescription generation based on Traditional Chinese Medicine (TCM), leaving TTM unexplored. To address this gap, we propose a novel fast-learning fine-tuned language model fortified with TTM knowledge. We utilized textual data from two TTM textbooks, Wat Ratcha-orasaram Ratchaworawihan (WRO), and Tamra Osot Phra Narai (NR), to fine-tune Unsloth’s Gemma-2 with 9 billion parameters. We developed two specialized TTM tasks: treatment prediction (TrP) and herbal recipe generation (HRG). The TrP and HRG models achieved precision, recall, and F1 scores of 26.54%, 28.14%, and 24.00%, and 32.51%, 24.42%, and 24.84%, respectively. Performance evaluation against TCM-based generative models showed comparable precision, recall, and F1 results with a smaller knowledge corpus. We further addressed the challenges of utilizing Thai, a low-resource and linguistically complex language. Unlike English or Chinese, Thai lacks explicit sentence boundary markers and employs an abugida writing system without spaces between words, complicating text segmentation and generation. These characteristics pose significant difficulties for machine understanding and limit model accuracy. Despite these obstacles, our work establishes a foundation for further development of AI-assisted TTM applications and highlights both the opportunities and challenges in applying language models to traditional medicine knowledge systems in Thai language contexts.

Background/Objectives: Unpredictable chronic mild stress exposure is a primary driver of cognitive decline, largely mediated by hypothalamic–pituitary–adrenal (HPA) axis dysregulation and subsequent oxidative neurotoxicity. In traditional Thai medicine, the AYW-KK-04 formulation—a complex polyherbal remedy—has long been utilized as a “Ya Aayu-Wattana” to restore vitality and elemental balance, yet its neurobiological mechanisms remain poorly understood. This study aimed to evaluate the adaptogenic and neuroprotective potential of AYW-KK-04 against cognitive impairment. Methods: Unpredictable Chronic Mild Stress (UCMS)-induced cognitive impairment in a ICR mouse model. Total phenolic and flavonoid contents and antioxidant capacity (ABTS assay) of AYW-KK-04 were determined. Behavioral assessments using Y-maze test, novel object recognition test (NORT), and Morris Water Maze (MWM) test. BDNF, CREB, Nrf and Keap1 mRNA gene expression, SOD and CAT enzymatic activity and lipid peroxidation assay were investigated to clarify the mechanisms of action. Moreover, HPLC chromatography was studied to quantify the active compounds of the AYW-KK-04 formulation. Results: It demonstrated that oral administration of AYW-KK-04 significantly reversed UCMS-induced memory deficits. At the molecular level, AYW-KK-04 effectively upregulated BDNF and CREB mRNA expression in the frontal cortex and hippocampus, suggesting a restoration of synaptic plasticity. Simultaneously, the formulation activated the Nrf2/Keap1 signaling pathway, leading to enhanced SOD and CAT enzymatic activities and a marked reduction in MDA-mediated lipid peroxidation. HPLC analysis confirmed the presence and consistency of key bioactive constituents. Conclusions: These findings suggest that the adaptogenic properties of AYW-KK-04 arise from its dual capacity to reinforce neurotrophic support and bolster the endogenous antioxidant shield, providing a mechanistic support for the traditional use of AYW-KK-04 as an adaptogenic formulation and highlighting its potential as a multi-target intervention for stress-related cognitive dysfunction.