VITA: 'Carefully Chosen and Weighted Less' Is Better in Medication Recommendation
This work addresses medication recommendation for patients by enhancing visit relevance modeling, representing an incremental improvement over existing methods.
The paper tackles the medication recommendation problem by proposing VITA, a framework that improves accuracy by better capturing the relevance between current and past patient visits, achieving up to 5.56% higher Jaccard accuracy than the best competitor.
We address the medication recommendation problem, which aims to recommend effective medications for a patient's current visit by utilizing information (e.g., diagnoses and procedures) given at the patient's current and past visits. While there exist a number of recommender systems designed for this problem, we point out that they are challenged in accurately capturing the relation (spec., the degree of relevance) between the current and each of the past visits for the patient when obtaining her current health status, which is the basis for recommending medications. To address this limitation, we propose a novel medication recommendation framework, named VITA, based on the following two novel ideas: (1) relevant-Visit selectIon; (2) Target-aware Attention. Through extensive experiments using real-world datasets, we demonstrate the superiority of VITA (spec., up to 5.56% higher accuracy, in terms of Jaccard, than the best competitor) and the effectiveness of its two core ideas. The code is available at https://github.com/jhheo0123/VITA.