Linear Bayes Classification for Mortality Prediction

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00194925" target="_blank" >RIV/68407700:21230/12:00194925 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Linear Bayes Classification for Mortality Prediction

Original language description

This paper describes our solution for PhysioNet challenge 2012. Its main aim is to predict mortality of ICU patients and obtain good sensitivity, positive predictivity and Hosmer-Lemeshow H statistic. Each record can be understood as consisting of 37 time series of different lengths, each corresponding to one variable measured during the patient's stay at ICU. For each person, we extracted high number of features. The original feature set was further reduced using some preprocessing and selection and used to train linear Bayes classifier.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JC - Computer hardware and software

OECD FORD branch

—

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2012

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Computing in Cardiology 2012

ISBN

978-1-4673-2074-0

ISSN

2325-8861

e-ISSN

—

Number of pages

4

Pages from-to

1-4

Publisher name

IEEE

Place of publication

New York

Event location

Krakow

Event date

Sep 9, 2012

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—