计算机科学
简单(哲学)
人工智能
图形
病历
基线(sea)
卷积(计算机科学)
数据挖掘
机器学习
医学
理论计算机科学
人工神经网络
海洋学
认识论
放射科
地质学
哲学
作者
Haiqiang Wang,Yinying Wu,Chao Gao,Yue Deng,Fan Zhang,Jiajin Huang,Jiming Liu
出处
期刊:IEEE Journal of Biomedical and Health Informatics
[Institute of Electrical and Electronics Engineers]
日期:2021-10-01
卷期号:25 (10): 3995-4004
被引量:7
标识
DOI:10.1109/jbhi.2021.3082548
摘要
Medication combination prediction can be applied to the clinical treatment for critical patients with multi-morbidity. The suitable medication combination can help cure patients and keep the treatment medication safe. However, the complexity and uncertainty of clinical circumstances limit the predictive accuracy of medication combination. Thus, this paper proposes a new medication combination prediction model based on the temporal attention mechanism (TAM) and the simple graph convolution (SGC), named as TAMSGC. More specifically, the TAM can capture the temporal sequence information in the medical records, and the SGC is implemented to acquire the medication knowledge from the complicated medication combination. Experiments in a real dataset show that TAMSGC surpasses the baseline models on the predictive accuracy of medication combination.
科研通智能强力驱动
Strongly Powered by AbleSci AI