Abstract: Monitoring the future health status of patients from the historical Electronic Health Record (EHR) is a core research topic in personalized 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 of diagnoses. 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.
Learning Objective 1: This work will result in an effective tool for the physicians to monitor disease progression for early treatment in a more efficient way.
Qiuling Suo, University at Buffalo
Fenglong Ma, University at Buffalo
Giovanni Canino, Magna Graecia University
Jing Gao, University at Buffalo
Aidong Zhang (Presenter)
University at Buffalo
Pierangelo Veltri, Magna Graecia University
Agostino Gnasso, Mater Domini Hospital, Magna Graecia University