GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation

• URL: http://arxiv.org/abs/2605.20188v1
• Date: Sat, 21 Mar 2026 15:10:54 GMT
• Title: GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation
• Abstract summary: We present GraphDiffMed, a knowledge-constrained medication recommendation framework built on dual-scale Differential Attention v2.<n> Experiments on MIMIC-III and ablation studies show that this design consistently improves recommendation quality and ranking over strong baselines.
• Score: 0.0828720658988688
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recommending safe and effective medication combinations from electronic health records (EHRs) is a core clinical AI problem, yet it remains difficult because patient trajectories are long, noisy, and clinically heterogeneous. Existing methods typically excel at either temporal modeling across visits or pharmacological knowledge integration (e.g., drug-drug interactions, DDIs), but rarely achieve both while robustly suppressing noise. We present GraphDiffMed, a knowledge-constrained medication recommendation framework built on dual-scale Differential Attention v2. Differential attention is applied at both intra-visit and inter-visit levels to filter spurious signals within encounters and across longitudinal history, while pharmacological constraints are incorporated during learning. Experiments on MIMIC-III and ablation studies show that this design consistently improves recommendation quality and ranking over strong baselines while achieving a more favorable safety performance balance. We further find that the strongest-performing configuration uses only demographic auxiliary features under our experimental setting. Overall, GraphDiffMed demonstrates that combining noise-aware attention with pharmacological constraints yields more reliable and clinically meaningful medication recommendation. We open-source our code at https://github.com/saxenakrati09/GraphDiffMed.

Related papers

• DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing [55.45112712244231]
  DrugReason is a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing.<n> Experiments on PharmaDB, DDInter, and DrugBank show that DrugReason improves average performance over strong single-view reasoning baselines.
  arXiv  Detail & Related papers  (2026-09-06T18:54:26Z)
• HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships [42.256653836522936]
  HypeMed is a two-stage hypergraph-based framework unifying intra-visit coherence modeling and inter-visit augmentation.<n>In the first stage, MedRep encodes clinical visits as hyperedges via knowledge-aware contrastive pre-training, creating a globally consistent, retrieval-friendly embedding space.<n>In the second stage, SimMR performs dynamic retrieval within this space, fusing retrieved references with the patient's longitudinal data to refine medication prediction.
  arXiv  Detail & Related papers  (2026-03-19T03:40:02Z)
• Dual-Pathway Fusion of EHRs and Knowledge Graphs for Predicting Unseen Drug-Drug Interactions [5.481037938702276]
  Drug-drug interactions (DDIs) remain a major source of preventable harm.<n>We introduce, to our knowledge, the first system that conditions KG relation scoring on patient-level EHR context.<n>A fusion "Teacher" learns mechanism-specific relations for drug pairs represented in both sources.<n>A distilled "Student" generalizes to new or rarely used drugs without KG access at inference.
  arXiv  Detail & Related papers  (2025-11-10T03:18:16Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• Combating the Bucket Effect:Multi-Knowledge Alignment for Medication Recommendation [7.962835256943926]
  We introduce a cross-modal medication encoder capable of seamlessly aligning data from different modalities.<n>We then combine the multi-knowledge medication representations with patient records for recommendations.<n>Experiments show that MKMed mitigates the "bucket effect" in data, and significantly outperforms state-of-the-art baselines in recommendation accuracy and safety.
  arXiv  Detail & Related papers  (2025-04-25T05:47:15Z)
• Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients [47.68396964741116]
  We propose a novel model called Robust and Accurate REcommendations for Medication (RAREMed) to enhance accuracy for rare diseases. It employs a transformer encoder with a unified input sequence approach to capture complex relationships among disease and procedure codes. It provides accurate drug sets for both rare and common disease patients, thereby mitigating unfairness in medication recommendation systems.
  arXiv  Detail & Related papers  (2024-03-26T14:36:22Z)
• CIDGMed: Causal Inference-Driven Medication Recommendation with Enhanced Dual-Granularity Learning [10.60553153370577]
  Medication recommendation aims to integrate patients' long-term health records to provide accurate and safe medication combinations. Existing methods often fail to deeply explore the true causal relationships between diseases/procedures and medications. We propose the Causal Inference-driven Dual-Granularity Medication Recommendation method (CIDGMed)
  arXiv  Detail & Related papers  (2024-03-01T08:50:27Z)
• StratMed: Relevance Stratification between Biomedical Entities for Sparsity on Medication Recommendation [9.296433860766165]
  StratMed is a stratification strategy that overcomes the long-tailed problem and achieves fuller learning of sparse data. It also utilizes a dual-property network to address the issue of mutual constraints on the safety and accuracy of medication combinations. Our model reduces safety risk by 15.08%, improves accuracy by 0.36%, and reduces training time consumption by 81.66%.
  arXiv  Detail & Related papers  (2023-08-31T14:59:32Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Knowledge-Driven New Drug Recommendation [88.35607943144261]
  We develop a drug-dependent multi-phenotype few-shot learner to bridge the gap between existing and new drugs. EDGE eliminates the false-negative supervision signal using an external drug-disease knowledge base. Results show that EDGE achieves 7.3% improvement on the ROC-AUC score over the best baseline.
  arXiv  Detail & Related papers  (2022-10-11T16:07:52Z)
• Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation [72.0276067144762]
  We discuss and define the two common types of label noise in medical images. We propose an uncertainty estimation-based framework to handle these two label noise amid the medical image classification task.
  arXiv  Detail & Related papers  (2021-02-28T14:56:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.