TY - JOUR
T1 - Medication Combination Prediction Using Temporal Attention Mechanism and Simple Graph Convolution
AU - Wang, Haiqiang
AU - Wu, Yinying
AU - Gao, Chao
AU - Deng, Yue
AU - Zhang, Fan
AU - Huang, Jiajin
AU - Liu, Jiming
N1 - Funding Information:
Manuscript received October 1, 2020; revised April 13, 2021; accepted May 17, 2021. Date of publication May 21, 2021; date of current version October 5, 2021. This work was supported by the National Natural Science Foundation of China under Grants 61976181, 11931015, and in part by the Key Technology Research and Development Program of Science and Technology-Scientific and Technological Innovation Team of Shaanxi Province under Grant 2020TD-013. (Corresponding author: Chao Gao.) Haiqiang Wang, Yue Deng, and Fan Zhang are with the College of Computer and Information Science, Southwest University, Chongqing 400715, China (e-mail: [email protected]; [email protected]; [email protected]).
Publisher Copyright:
© 2013 IEEE.
PY - 2021/10
Y1 - 2021/10
N2 - 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.
AB - 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.
KW - attention mechanism
KW - critical patients
KW - medical records
KW - Medication combination prediction
KW - medication knowledge
KW - simple graph convolution
KW - temporal sequence
UR - http://www.scopus.com/inward/record.url?scp=85107184968&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2021.3082548
DO - 10.1109/JBHI.2021.3082548
M3 - Journal article
C2 - 34018940
SN - 2168-2194
VL - 25
SP - 3995
EP - 4004
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 10
ER -