SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation
Preprint
Abstract
Effectively medication recommendation with complex multimorbidity conditions is a critical task in healthcare. Most existing works predicted medications based on longitudinal records, which assumed the information transmitted patterns of learning longitudinal sequence data are stable and intra-visit medical events are serialized. However, the following conditions may have been ignored: 1) A more compact encoder for intra-relationship in the intra-visit medical event is urgent; 2) Strategies for learning accurate representations of the variable longitudinal sequences of patients are different. In this paper, we proposed a novel Sample-adaptive Hierarchical medicAtion Prediction nEtwork, termed SHAPE, to tackle the above challenges in the medication recommendation task. Specifically, we design a compact intra-visit set encoder to encode the relationship in the medical event for obtaining visit-level representation and then develop an inter-visit longitudinal encoder to learn the patient-level longitudinal representation efficiently. To endow the model with the capability of modeling the variable visit length, we introduce a soft curriculum learning method to assign the difficulty of each sample automatically by the visit length. Extensive experiments on a benchmark dataset verify the superiority of our model compared with several state-of-the-art baselines.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Improving de novo molecular design with curriculum learningNature Machine Intelligence, 2022
- An efficient curriculum learning-based strategy for molecular graph learningBriefings in Bioinformatics, 2022
- Multi-channel fusion LSTM for medical event prediction using EHRsJournal of Biomedical Informatics, 2022
- MeSIN: Multilevel selective and interactive network for medication recommendationKnowledge-Based Systems, 2021
- Deep representation learning of patient data from Electronic Health Records (EHR): A systematic reviewJournal of Biomedical Informatics, 2021
- SMR: Medical Knowledge Graph Embedding for Safe Medicine RecommendationBig Data Research, 2021
- Adversarially regularized medication recommendation model with multi-hop memory networkKnowledge and Information Systems, 2020
- A hybrid method of recurrent neural network and graph neural network for next-period prescription predictionInternational Journal of Machine Learning and Cybernetics, 2020
- Scalable and accurate deep learning with electronic health recordsnpj Digital Medicine, 2018
- MIMIC-III, a freely accessible critical care databaseScientific Data, 2016