Risk Stratification with Extreme Learning Machine: A Retrospective Study on Emergency Department PatientsReport as inadecuate




Risk Stratification with Extreme Learning Machine: A Retrospective Study on Emergency Department Patients - Download this document for free, or read online. Document in PDF available to download.

Mathematical Problems in EngineeringVolume 2014 2014, Article ID 248938, 6 pages

Research Article

Department of Emergency Medicine, Singapore General Hospital, Singapore 169608

Institute of Information and Control, Hangzhou Dianzi University, Zhejiang 310018, China

Health Services and Systems Research, Duke-NUS Graduate Medical School, Singapore 169857

Received 4 July 2014; Accepted 12 August 2014; Published 20 August 2014

Academic Editor: Zhan-li Sun

Copyright © 2014 Nan Liu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

This paper presents a novel risk stratification method usingextreme learning machine ELM. ELM was integrated into a scoringsystem to identify the risk of cardiac arrest in emergency departmentED patients. The experiments were conducted on a cohort of 1025critically ill patients presented to the ED of a tertiary hospital. ELM andvoting based ELM V-ELM were evaluated. To enhance the predictionperformance, we proposed a selective V-ELM SV-ELM algorithm. Theresults showed that ELM based scoring methods outperformed supportvector machine SVM based scoring method in the receiver operationcharacteristic analysis.





Author: Nan Liu, Jiuwen Cao, Zhi Xiong Koh, Pin Pin Pek, and Marcus Eng Hock Ong

Source: https://www.hindawi.com/



DOWNLOAD PDF




Related documents