Skip to main content

Publications Nov 2018

News Thumbnail

Predicting the risk of emergency admission with machine learning: Development and validation using linked electronic health records

Description:

Emergency admissions are a major source of healthcare spending. This research paper aimed to derive, validate, and compare conventional and machine learning models for prediction of the first emergency admission. It found that that standard machine learning models not only outperformed the best statistical model but they did so with a substantially better performance and calibration.

Download

More information

Authors:

Fatemeh Rahimian
Jenny Tran
Kazem Rahimi
Milad Nazarzadeh

Type: Journal Articles & Working Papers

Warnings: The flashwrapper plugin may be incompatible with this version of Wheels, please look for a compatible version of the plugin
The shortcodes plugin may be incompatible with this version of Wheels, please look for a compatible version of the plugin
Application: oms_live [Run Tests, View Tests]
Framework: CFWheels 1.4.6
Active Environment: Development
Host Name: duchess
CFML Engine: Lucee 5.2.6.59
Default Data Source: Oms_www
Database Adapter: MySQL
URL Rewriting: On
URL Obfuscation: Off
Plugins: flashwrapper
shortcodes
Route: Publication
Controller: Publications
Action: View
Key(s): 2776
Parameters: t2 = publications
t1 = research
Execution Time: 45ms (action ~22ms, beforefilters ~22ms, view ~15ms)
Help Links: Documentation, Mailing List, Issue Tracker