GRAIN：分子并非合适的粒度——面向安全药物推荐的活性成分建模
GRAIN: Molecules Are Not the Right Granularity -- Active-Ingredient Modeling for Safe Medication Recommendation
- Beijing Normal–Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对药物推荐的粒度问题，提出基于活性成分的GRAIN框架，结合多源知识与比例控制器权衡准确性和安全性，在MIMIC-IV数据集上优于基线模型，同时降低了DDI率。
AI中文摘要：
从电子健康记录进行药物推荐时，必须在预测准确性与多药联用下药物间不良相互作用（DDI）的风险之间取得平衡。现有感知安全性的推荐系统采用两种粒度之一：药物代码，将每种药物视为不可分割的标记；或分子亚结构，其粒度比药理相互作用知识的实际组织更细。本文认为活性成分是缺失的粒度，并引入围绕其构建的药物推荐框架GRAIN。GRAIN采用选择性状态空间主干对患者纵向轨迹（诊断、操作、既往药物）进行编码，该主干以线性时间处理长且不规则的就诊序列。在此基础上，引入联合目标，统一三种与通用药物词汇对齐的知识源：药物级DDI图、通过RxNorm将药物代码标准化为活性成分得到的成分级DDI图，以及来自电子健康记录的联合处方图。比例控制器根据观察到的验证集DDI率调整准确性-安全性权衡，而非预先固定。在严格匹配的设置（相同的预处理、队列、词汇、划分和评估代码）下，GRAIN在MIMIC-IV数据集上的所有标准多标签指标均优于重新实现的MambaHealth基线：Jaccard指数从0.4488提升至0.4983，PRAUC从0.6911提升至0.7485，F1值从0.5989提升至0.6453，同时将药物级DDI率从0.1875降至0.0948。本文进一步定义了成分级DDI率，这是一种药物代码级评估无法感知的安全指标。结果表明，成分级标准化恢复了代码级聚合抹去的预测信号，且其与准确的序列建模是互补关系，而非竞争关系。
英文摘要：
Medication recommendation from electronic health records must balance predictive accuracy against the risk of adverse drug-drug interactions (DDIs) under polypharmacy. Existing safety-aware recommenders operate at one of two granularities: the drug code, which treats each medication as an indivisible token, or the molecular substructure, which is finer than pharmacological interaction knowledge is actually organized. We argue that the active ingredient is the missing granularity, and introduce GRAIN, a medication recommendation framework built around it. GRAIN encodes longitudinal patient trajectories (diagnoses, procedures, past medications) with a selective state space backbone that handles long, irregular visit sequences in linear time. On top of it we introduce a joint objective unifying three knowledge sources aligned to a common medication vocabulary: a drug-level DDI graph, an ingredient-level DDI graph obtained by normalizing medication codes to active ingredients via RxNorm, and an EHR-derived co-prescription graph. A proportional controller adapts the accuracy-safety trade-off to the observed validation DDI rate rather than fixing it a priori. Under strictly matched settings -- identical preprocessing, cohort, vocabulary, split, and evaluation code -- GRAIN improves over a re-implemented MambaHealth baseline on MIMIC-IV across all standard multi-label metrics (Jaccard 0.4488 to 0.4983, PRAUC 0.6911 to 0.7485, F1 0.5989 to 0.6453) while reducing the drug-level DDI rate from 0.1875 to 0.0948. We further define an ingredient-level DDI rate, a safety measure invisible to drug-code-level evaluation. The results indicate that ingredient-level normalization recovers predictive signal erased by code-level aggregation, and that it is complementary to, rather than in competition with, accurate sequence modeling.
