MeridianFM: A Causal and Safe Foundation Model for Personalizing Traditional Chinese Medicine Therapies

Nonpharmacological therapies like acupuncture, gua sha, and cupping are gain-ing prominence in integrative medicine, yet their application lacks data-driven personalization and rigorous safety assurances. This paper introduces Meridi-anFM, a causal and safe multimodal foundation model framework designed to generate personalized prescriptions for these therapies. MeridianFM integrates four key innovations: (1) a meridian-aware graph neural network that encodes the topological and semantic properties of acupoints; (2) a self-supervised mul-timodal architecture that fuses physiological time series, thermal imagery, elec-tronic health records, and patient-reported outcomes; (3) a causal inference layer employing doubly robust estimation and front-door adjustment to miti-gate confounding in observational data and estimate individualized treatment effects; and (4) a constrained reinforcement learning policy optimized with risk-sensitive objectives (Conditional Value-at-Risk) and a mixed-integer pro-gramming post-processor to enforce clinical safety and feasibility constraints. To ensure reproducibility, we provide a comprehensive evaluation suite based on synthetic and semi-synthetic data, including all source code. Our experi-ments demonstrate that MeridianFM surpasses baseline models in optimizing treatment policies, accurately estimating causal effects, and adhering to safety constraints. While this study establishes methodological feasibility and superior performance in simulated environments, it also lays the groundwork for future clinical validation, representing a significant step toward AI-driven precision in traditional medicine.