CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation

doi:10.1016/j.artmed.2023.102613

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation
	Sun, Mengxuan 1,2; Niu, Jinghao 1; Yang, Xuebing 1; Gu, Yifan 1,2; Zhang, Wensheng 1,2,3
刊名	ARTIFICIAL INTELLIGENCE IN MEDICINE
	2023-09-01
卷号	143 页码:13
关键词	Medication recommendation EHR Hierarchical multi-label classification Curriculum learning
ISSN号	0933-3657
DOI	10.1016/j.artmed.2023.102613
通讯作者	Yang, Xuebing(yangxuebing2013@ia.ac.cn) ; Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	The medication recommendation (MR) or medication combination prediction task aims to predict effective prescriptions given accurate patient representations derived from electronic health records (EHRs), which contributes to improving the quality of clinical decision-making, especially for patients with multi-morbidity. Although in recent years deep learning technology has achieved great success in MR, the performance of current multi-label based MR solutions is unsatisfactory. They mainly focus on improving the patient representation module and modeling the medication label dependencies such as drug-drug interaction (DDI) correlation and co-occurrence relationship. However, the hierarchical dependency among medication labels and diversity of difficulty among MR training examples lack sufficient consideration. In this paper, we propose a framework of Curriculum learning Enhanced Hierarchical multi-label classification for MR (CEHMR). Motivated by the category hierarchy of medications which organizes standard medication codes in a hierarchical structure, we utilize it to provide more trustworthy prior knowledge for modeling label dependency. Specifically, we design a hierarchical multi-label classifier with a learnable gate fusion layer, to simultaneously capture the level-independent (local) and level-dependent (global) hierarchical information in the medication hierarchy. In addition, to overcome the diversity of training example difficulties, and progressively achieve a smoother training process, we introduce a bootstrap-based curriculum learning strategy. Hence, the example difficulty can be measured based on the predictive performance of the MR model, and then all training examples would be retrained from easy to hard under the guidance of a predefined training scheduler. Experiments on the real-world medical MIMIC-III database demonstrate that the proposed framework can achieve state-of-theart performance compared with seven representative baselines, and extensive ablation studies validate the effectiveness of each component of CEHMR.
资助项目	National Key R&D Program of China[2021ZD0111005] ; National Key R&D Program of China[61976212] ; National Key R&D Program of China[62006139] ; National Key R&D Program of China[62203437] ; National Key R&D Program of China[61976213]
WOS研究方向	Computer Science ; Engineering ; Medical Informatics
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:001061845300001
资助机构	National Key R&D Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53170]
专题	多模态人工智能系统全国重点实验室
通讯作者	Yang, Xuebing; Zhang, Wensheng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Guangzhou Univ, Guangzhou, Peoples R China
推荐引用方式 GB/T 7714	Sun, Mengxuan,Niu, Jinghao,Yang, Xuebing,et al. CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation[J]. ARTIFICIAL INTELLIGENCE IN MEDICINE,2023,143:13.
APA	Sun, Mengxuan,Niu, Jinghao,Yang, Xuebing,Gu, Yifan,&Zhang, Wensheng.(2023).CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation.ARTIFICIAL INTELLIGENCE IN MEDICINE,143,13.
MLA	Sun, Mengxuan,et al."CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation".ARTIFICIAL INTELLIGENCE IN MEDICINE 143(2023):13.