Syndrome differentiation and disease diagnosis are central to Traditional Asian Medicine (TAM) because they guide personalized treatment. Yet, most TAM courses give students few structured opportunities to practise these paired skills. We developed Gen-SynDi, a knowledge-guided generative-AI framework that links syndrome differentiation with disease diagnosis to improve training. Using standardized patient files from the National Institute for Korean Medicine Development, we built a fatigue-focused dataset covering five Western-defined diseases and seven TAM syndromes. Carefully designed prompts and a large language model produced 28 virtual patient cases by joining compatible disease–syndrome pairs while preserving clinical realism. Inside an interactive web simulation, students conduct history-taking, receive free-text answers, and propose both syndrome and disease diagnoses; immediate feedback highlights missing questions, reasoning gaps, and overall accuracy. A built-in scoring module supplies quantitative measures of inquiry coverage and diagnostic precision, plus brief explanations of overlooked clues. A prompt-component role analysis confirmed that our prompt design improves response fidelity, and external experts endorsed the scenarios’ realism and educational value. Gen-SynDi therefore offers a scalable bridge between textbook knowledge and clinical practice, strengthening learners’ skills in differential diagnosis and syndrome differentiation.

Psoriasis is a chronic inflammatory skin disorder characterized by the hyperproliferation of keratinocytes and immune system dysregulation, with significant needs due to the limitations and adverse effects of current treatments. In this study, we sought to discover novel herbal candidates and their active compounds for psoriasis by leveraging a multiscale network analysis. We conducted a comprehensive analysis of data from 348 medicinal herbs and their active compounds, identifying Piperis longi fructus, Pini koraiensis semen, Schisandrae fructus, and Cnidi fructus as top candidates without reported evidence. Key active compounds, such as piperine, piperlongumine, α-humulene, schizandrin A, schizandrin II, and torilin, were prioritized for their ability to target psoriasis-associated proteins, including STAT3, TNF, IL-6, and NF-κB. These compounds are involved in the modulation of critical inflammatory pathways, notably the MAPK signaling cascade, which plays a central role in psoriasis pathogenesis. Our findings suggest that these herbal compounds may not only mitigate inflammation but also regulate keratinocyte hyperproliferation, addressing fundamental mechanisms underlying the disease. This approach highlights the utility of multiscale network analysis in identifying promising natural therapies, offering new insights and potential avenues for safer and more effective psoriasis management.