Using a Multi-task Recurrent Neural Network with Attention Mechanisms to Predict Hospital Mortality of Patients
Publication in refereed journal

替代計量分析
.

其它資訊
摘要Estimating hospital mortality of patients is important in assisting clinicians to make decisions and hospital providers to allocate resources. This paper proposed a multi-task recurrent neural network with attention mechanisms to predict patients’ hospital mortality, using reconstruction of patients’ physiological time series as an auxiliary task. Experiments were conducted on a large public electronic health record database, i.e., MIMIC-III. Fifteen physiological measurements during the first 24 h of critical care were used to predict death before hospital discharge. Compared with the conventional simplified acute physiology score (SAPS-II), the proposed multi-task learning model achieved better sensitivity (0.503 ± 0.020 versus 0.365 ± 0.021), when predictions were made based on the same 24-h observation period. The multi-task learning model is recommended to be updated daily with at least a 6-h observation period, in order for it to perform similarly or better than the SAPS-II. In the future, the need for intervention can be considered as another task to further optimize the performance of the multi-task learning model.
著者Ruoxi Yu, Yali Zheng, Ruikai Zhang, Yuqi Jiang, Carmen C.Y. Poon
期刊名稱IEEE Journal of Biomedical and Health Informatics
出版年份2020
月份2
卷號24
期次2
出版社IEEE
頁次486 - 492
國際標準期刊號2168-2194
語言美式英語

上次更新時間 2020-23-10 於 02:39