Towards Smarter Clinical Predictions: Foundation Models for Integrating Multi-Source Domain Knowledge in EHRs.

Abstract

Medication recommendation (MR) is a crucial clinical prediction task that supports physicians in prescribing effectively for patients with complex conditions. Effective MR requires integrating diverse medical knowledge and intricate relationships within clinical data. Traditional methods, however, largely focus on modeling relationships among medical entities and learning patient representations, often constrained by their reliance on single-domain knowledge. These constraints limit their ability to address the complexities of real-world scenarios. Recent advancements in foundation models present a promising solution by unifying multi-source data and uncovering rich semantic and structural insights. Yet, their potential in MR remains underexplored. To overcome these challenges, we introduce MEDICS, a foundation-model-driven framework that integrates multi-source domain knowledge and unifies semantic and structural information for enhanced clinical predictions. MEDICS consists of three synergistic modules: KnowRetr for multi-source medical knowledge retrieval, MedChat for LLM-based semantic reasoning, and HyperMed for high-order structural modeling using sub-hypergraphs. MEDICS employs a systematic process to retrieve, organize, and summarize domain knowledge for each medical code, utilizing this knowledge through two specialized modules. The MedChat module leverages large language models (LLMs) to redefine MR as a conversational question-answering task, enabling advanced semantic analysis. Simultaneously, the HyperMed module refines a hypergraph-based model by incorporating textual and structural embeddings to model high-order interactions among medical codes. Additionally, our collaborative training strategy further synergistically harnesses information from both modules. Extensive experiments on real-world EHR datasets (MIMIC-III and MIMIC-IV) demonstrate that MEDICS significantly outperforms state-of-the-art methods, setting a new benchmark for clinical prediction tasks.