MR-KPA: medication recommendation by combining knowledge-enhanced pre-training with a deep adversarial network

Shaofu Lin; Mengzhen Wang; Chengyu Shi; Zhe Xu; Lihong Chen; Qingcai Gao; Jianhui Chen

doi:10.1186/s12859-022-05102-1

MR-KPA: medication recommendation by combining knowledge-enhanced pre-training with a deep adversarial network

BMC Bioinformatics. 2022 Dec 19;23(1):552. doi: 10.1186/s12859-022-05102-1.

Authors

Shaofu Lin¹, Mengzhen Wang¹, Chengyu Shi¹, Zhe Xu¹, Lihong Chen^{1

2}, Qingcai Gao^{1

2}, Jianhui Chen^{3

4

5

6

7}

Affiliations

¹ Faculty of Information Technology, Beijing University of Technology, Beijing, China.
² Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing University of Technology, Beijing, China.
³ Faculty of Information Technology, Beijing University of Technology, Beijing, China. chenjianhui@bjut.edu.cn.
⁴ Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing University of Technology, Beijing, China. chenjianhui@bjut.edu.cn.
⁵ Beijing Key Laboratory of MRI and Brain Informatics, Beijing University of Technology, Beijing, China. chenjianhui@bjut.edu.cn.
⁶ Engineering Research Center of Intelligent Perception and Autonomous Control, Ministry of Education, Beijing, China. chenjianhui@bjut.edu.cn.
⁷ Engineering Research Center of Digital Community, Ministry of Education, Beijing, China. chenjianhui@bjut.edu.cn.

Abstract

Background: Medication recommendation based on electronic medical record (EMR) is a research hot spot in smart healthcare. For developing computational medication recommendation methods based on EMR, an important challenge is the lack of a large number of longitudinal EMR data with time correlation. Faced with this challenge, this paper proposes a new EMR-based medication recommendation model called MR-KPA, which combines knowledge-enhanced pre-training with the deep adversarial network to improve medication recommendation from both feature representation and the fine-tuning process. Firstly, a knowledge-enhanced pre-training visit model is proposed to realize domain knowledge-based external feature fusion and pre-training-based internal feature mining for improving the feature representation. Secondly, a medication recommendation model based on the deep adversarial network is developed to optimize the fine-tuning process of pre-training visit model and alleviate over-fitting of model caused by the task gap between pre-training and recommendation.

Result: The experimental results on EMRs from medical and health institutions in Hainan Province, China show that the proposed MR-KPA model can effectively improve the accuracy of medication recommendation on small-scale longitudinal EMR data compared with existing representative methods.

Conclusion: The advantages of the proposed MR-KPA are mainly attributed to knowledge enhancement based on ontology embedding, the pre-training visit model and adversarial training. Each of these three optimizations is very effective for improving the capability of medication recommendation on small-scale longitudinal EMR data, and the pre-training visit model has the most significant improvement effect. These three optimizations are also complementary, and their integration makes the proposed MR-KPA model achieve the best recommendation effect.

Keywords: Adversarial training; Electronic medical record; Graph attention network; Medication recommendation; Pre-training model.

MeSH terms

China
Electronic Health Records*
Knowledge Bases*

Abstract

MeSH terms

Grants and funding