An Attention-based Recurrent Neural Networks Framework for Health Data Analysis

Qiuling Suo, Fenglong Ma, Giovanni Canino, Jing Gao, Aidong Zhang, Agostino Gnasso, Giuseppe Tradigo, Pierangelo Veltri

Research output: Contribution to journalConference article

Abstract

In this paper we focus on prediction of health status of patients from the historical Electronic Health Records (EHR). We propose a multi-task framework that can monitor the multiple status of diagnoses. Patients’ historical records are 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. Experimental results show that prediction accuracy is reliable if compared to widely used approaches 1.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2161
StatePublished - Jan 1 2018
Event26th Italian Symposium on Advanced Database Systems, SEBD 2018 - Castellaneta Marina (Taranto), Italy
Duration: Jun 24 2018Jun 27 2018

Fingerprint

Recurrent neural networks
Health

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Suo, Q., Ma, F., Canino, G., Gao, J., Zhang, A., Gnasso, A., ... Veltri, P. (2018). An Attention-based Recurrent Neural Networks Framework for Health Data Analysis. CEUR Workshop Proceedings, 2161.
Suo, Qiuling ; Ma, Fenglong ; Canino, Giovanni ; Gao, Jing ; Zhang, Aidong ; Gnasso, Agostino ; Tradigo, Giuseppe ; Veltri, Pierangelo. / An Attention-based Recurrent Neural Networks Framework for Health Data Analysis. In: CEUR Workshop Proceedings. 2018 ; Vol. 2161.
@article{53111cabf830420b86e1407ff79cea8a,
title = "An Attention-based Recurrent Neural Networks Framework for Health Data Analysis",
abstract = "In this paper we focus on prediction of health status of patients from the historical Electronic Health Records (EHR). We propose a multi-task framework that can monitor the multiple status of diagnoses. Patients’ historical records are 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. Experimental results show that prediction accuracy is reliable if compared to widely used approaches 1.",
author = "Qiuling Suo and Fenglong Ma and Giovanni Canino and Jing Gao and Aidong Zhang and Agostino Gnasso and Giuseppe Tradigo and Pierangelo Veltri",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2161",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

Suo, Q, Ma, F, Canino, G, Gao, J, Zhang, A, Gnasso, A, Tradigo, G & Veltri, P 2018, 'An Attention-based Recurrent Neural Networks Framework for Health Data Analysis', CEUR Workshop Proceedings, vol. 2161.

An Attention-based Recurrent Neural Networks Framework for Health Data Analysis. / Suo, Qiuling; Ma, Fenglong; Canino, Giovanni; Gao, Jing; Zhang, Aidong; Gnasso, Agostino; Tradigo, Giuseppe; Veltri, Pierangelo.

In: CEUR Workshop Proceedings, Vol. 2161, 01.01.2018.

Research output: Contribution to journalConference article

TY - JOUR

T1 - An Attention-based Recurrent Neural Networks Framework for Health Data Analysis

AU - Suo, Qiuling

AU - Ma, Fenglong

AU - Canino, Giovanni

AU - Gao, Jing

AU - Zhang, Aidong

AU - Gnasso, Agostino

AU - Tradigo, Giuseppe

AU - Veltri, Pierangelo

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this paper we focus on prediction of health status of patients from the historical Electronic Health Records (EHR). We propose a multi-task framework that can monitor the multiple status of diagnoses. Patients’ historical records are 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. Experimental results show that prediction accuracy is reliable if compared to widely used approaches 1.

AB - In this paper we focus on prediction of health status of patients from the historical Electronic Health Records (EHR). We propose a multi-task framework that can monitor the multiple status of diagnoses. Patients’ historical records are 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. Experimental results show that prediction accuracy is reliable if compared to widely used approaches 1.

UR - http://www.scopus.com/inward/record.url?scp=85051845046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051845046&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85051845046

VL - 2161

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -