Conditional Generation Net for Medication Recommendation

TL;DR

This paper introduces COGNet, a novel model for automatic medication recommendation that mimics doctors' decision processes by copying or predicting medicines, improving accuracy over existing methods.

Contribution

The paper proposes COGNet with a copy-or-predict mechanism for medication recommendation, capturing the decision process of doctors and outperforming prior models.

Findings

COGNet outperforms state-of-the-art methods on MIMIC dataset.

The copy-or-predict mechanism effectively models doctor decision processes.

Experimental results demonstrate improved recommendation accuracy.

Abstract

Medication recommendation targets to provide a proper set of medicines according to patients' diagnoses, which is a critical task in clinics. Currently, the recommendation is manually conducted by doctors. However, for complicated cases, like patients with multiple diseases at the same time, it's difficult to propose a considerate recommendation even for experienced doctors. This urges the emergence of automatic medication recommendation which can help treat the diagnosed diseases without causing harmful drug-drug interactions.Due to the clinical value, medication recommendation has attracted growing research interests.Existing works mainly formulate medication recommendation as a multi-label classification task to predict the set of medicines. In this paper, we propose the Conditional Generation Net (COGNet) which introduces a novel copy-or-predict mechanism to generate the set of medicines. Given a patient, the proposed model first retrieves his or her historical diagnoses and medication recommendations and mines their relationship with current diagnoses. Then in predicting each medicine, the proposed model decides whether to copy a medicine from previous recommendations or to predict a new one. This process is quite similar to the decision process of human doctors. We validate the proposed model on the public MIMIC data set, and the experimental results show that the proposed model can outperform state-of-the-art approaches.