Sep 2026· Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence· 0 citations· 47 references
TL;DR
MGRec is a framework that shifts learning from discrete prescription prediction to condition-aware modeling in a continuous molecular representation space and introduces a DDI (drug-drug interaction)-guided latent regularization to integrate drug interaction knowledge at the representation level to improve clinical safety.
Abstract
Medication recommendation plays a critical role in clinical decision-making by supporting personalized and safe treatment planning. Existing methods rely heavily on historical co-occurrence patterns and primarily optimize discrete prescription prediction objectives, limiting generalization in rare or emerging disease settings. We propose MGRec, a framework that shifts learning from discrete prescription prediction to condition-aware modeling in a continuous molecular representation space. MGRec treats molecular structure as the primary modeling target and employs a Therapeutic--Safety Factorized Conditional Variational Autoencoder to disentangle therapeutic and safety-related factors in a condition-aware molecular latent space. The model infers treatment-relevant molecular representations conditioned on current patient-specific clinical context, which are mapped to clinically approved medications for final recommendation. To improve clinical safety, we further introduce a DDI (drug-drug interaction)-guided latent regularization to integrate drug interaction knowledge at the representation level. Experiments on two real-world benchmarks demonstrate that MGRec achieves state-of-the-art accuracy and reduced interaction risk, particularly in data-sparse scenarios.
DynMedRec captures fine-grained drug information by modeling the interactions between substructures and employing a clinical-context query mechanism to generate adaptive molecular representations, and integrates structural correlations among medical codes to enhance visit-level patient representations.
Experimental results demonstrate that MoTRANet outperforms existing mainstream baseline methods in terms of Jaccard, F1, and PRAUC, while achieving a relatively low DDI rate, validating the model's accuracy and safety.
Peng-Tao Jia, Jun-Hao Gao, Jing-Tao Sha et al.· IEEE transactions on computa...· 0 citations
SpecTD-MR, a novel medication recommendation framework for Disease Spectrum-aware and Time-evolving Dependency Learning, is proposed that surpasses state-of-the-art baselines in accuracy, while providing visualizable structural associations to support insights into dynamic disease evolution.
Yi-Shuo Li, Cong Wang, Shou-Jin Wang et al.· ACM Transactions on Informat...· 1 citation
Accurate medication recommendation is central to clinical decision-making, directly determining therapeutic efficacy and patient safety. However, existing methods suffer from two key limitations: drugs are often abstracted as discrete tokens, ignoring their molecular structures and pharmacological mechanisms, and the c...
Jun-Ke Wang, Hong-Shun Ling, Li Zhang et al.· 0 citations
A novel framework named Multi-Knowledge Medication recommendation is proposed, which introduces a cross-modal medication encoder capable of aligning heterogeneous modalities into a unified representation space and explicitly mitigates the bucket effect, enabling robust recommendation performance even in sparse knowledg...
Hai-Xu Ma, Guan-Yong Wu, Shi-Zhuo Mu et al.· Applied intelligence (Boston...· 0 citations
CaMeRe, a Causally-inspired Meta-representation learning framework designed to predict patient-specific clinical Response to drug combinations, exhibited robust multi-domain generalization performance across multiple clinical drug combination response datasets and PDXs drug combination response datasets and generalizat...
Qing-Qing Zhang, Shao-Wu Zhang, Ming-Hui Shi et al.· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.