A curated list of awesome research on medication recommendation

• Instance-based methods
• Longitudinal-based methods
• Others
• Datasets
• Contribute

Instance-based methods focus on the patient’s current health status.

• LEAP: Learning to Prescribe Effective and Safe Treatment Combinations for Multimorbidity scholar KDD 2017 code
• SMR: Medical Knowledge Graph Embedding for Safe Medicine Recommendation scholar Big Data Research 2021

Longitudinal-based methods leverage the temporal dependencies among clinical event.

• Dual memory neural computer for asynchronous two-view sequential learning scholar KDD 2018 code
• GAMENet：Graph Augmented MEmory Networks for Recommending Medication Combination scholar AAAI 2019 code
• Order-free Medicine Combination Prediction with Graph Convolutional Reinforcement Learning scholar CIKM 2019 code
• PREMIER: Personalized REcommendation for Medical prescrIptions from Electronic Records scholar arXiv 2020
• RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism scholar arXiv 2016 code
• Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation scholar KDD 2018 code

• Adversarially regularized medication recommendation model with multi-hop memory network scholar KAIS 2021 code
• Change Matters: Medication Change Prediction with Recurrent Residual Networks scholar arXiv 2021
• GATE: Graph-Attention Augmented Temporal Neural Network for Medication Recommendation scholar IEEE 2020
• Pre-training of Graph Augmented Transformers for Medication Recommendation scholar arXiv 2019 code
• SafeDrug: Dual Molecular Graph Encoders for Safe Drug Recommendations scholar arXiv 2021 code

Datasets used in medication recommendation.

• MIMIC Critical Care Database - Medical Information Mart for Intensive Care.
• DDI Data - Drug-Drug Interaction Data.
• DrugBank - A curated pharmaceutical knowledge base, with products commercially available for precision medicine, telehealth, and drug discovery.

Contributions welcome! Read the contribution guidelines first.