User-Adaptive Meta-Learning for Cold-Start Medication Recommendation with Uncertainty Filtering

TL;DR

This paper introduces MetaDrug, a novel meta-learning framework that enhances medication recommendations for new patients by using personalized and peer-based adaptation with uncertainty filtering, significantly improving cold-start performance.

Contribution

The paper presents a multi-level, uncertainty-aware meta-learning approach with a two-level adaptation mechanism specifically designed for patient cold-start in EHR-based medication recommendation.

Findings

MetaDrug outperforms existing methods on MIMIC-III and AKI datasets.

Uncertainty filtering improves adaptation quality and recommendation accuracy.

Two-level adaptation effectively captures patient-specific and temporal information.

Abstract

Large-scale Electronic Health Record (EHR) databases have become indispensable in supporting clinical decision-making through data-driven treatment recommendations. However, existing medication recommender methods often struggle with a user (i.e., patient) cold-start problem, where recommendations for new patients are usually unreliable due to the lack of sufficient prescription history for patient profiling. While prior studies have utilized medical knowledge graphs to connect medication concepts through pharmacological or chemical relationships, these methods primarily focus on mitigating the item cold-start issue and fall short in providing personalized recommendations that adapt to individual patient characteristics. Meta-learning has shown promise in handling new users with sparse interactions in recommender systems. However, its application to EHRs remains underexplored due to the unique sequential structure of EHR data. To tackle these challenges, we propose MetaDrug, a multi-level, uncertainty-aware meta-learning framework designed to address the patient cold-start problem in medication recommendation. MetaDrug proposes a novel two-level meta-adaptation mechanism, including self-adaptation, which adapts the model to new patients using their own medical events as support sets to capture temporal dependencies; and peer-adaptation, which adapts the model using similar visits from peer patients to enrich new patient representations. Meanwhile, to further improve meta-adaptation outcomes, we introduce an uncertainty quantification module that ranks the support visits and filters out the unrelated information for adaptation consistency. We evaluate our approach on the MIMIC-III and Acute Kidney Injury (AKI) datasets. Experimental results on both datasets demonstrate that MetaDrug consistently outperforms state-of-the-art medication recommendation methods on cold-start patients.