A Multi-Task Framework for Monitoring Health Conditions via Attention-based Recurrent Neural Networks

• Published in: AMIA ... Annual Symposium proceedings Vol. 2017; pp. 1665 - 1674
• Main Authors: Suo, Qiuling, Ma, Fenglong, Canino, Giovanni, Gao, Jing, Zhang, Aidong, Veltri, Pierangelo, Agostino, Gnasso
• Format: Journal Article
• Language: English
• Published: United States American Medical Informatics Association 2017
• Subjects: Deep Learning; Disease Progression; Electronic Health Records; Humans; Neural Networks, Computer; Patient Care Management - methods
• ISSN: 1559-4076

Monitoring the future health status of patients from the historical Electronic Health Record (EHR) is a core research topic in predictive healthcare. The most important challenges are to model the temporality of sequential EHR data and to interpret the prediction results. In order to reduce the future risk of diseases, we propose a multi-task framework that can monitor the multiple status ofdiagnoses. Patients' historical records are directly fed into a Recurrent Neural Network (RNN) which memorizes all the past visit information, and then a task-specific layer is trained to predict multiple diagnoses. Moreover, three attention mechanisms for RNNs are introduced to measure the relationships between past visits and current status. Experimental results show that the proposed attention-based RNNs can significantly improve the prediction accuracy compared to widely used approaches. With the attention mechanisms, the proposed framework is able to identify the visit information which is important to the final prediction.