Literature DB >> 11079917

Predicting ICU mortality: a comparison of stationary and nonstationary temporal models.

M Kayaalp1, G F Cooper, G Clermont.   

Abstract

OBJECTIVE: This study evaluates the effectiveness of the stationarity assumption in predicting the mortality of intensive care unit (ICU) patients at the ICU discharge.
DESIGN: This is a comparative study. A stationary temporal Bayesian network learned from data was compared to a set of (33) nonstationary temporal Bayesian networks learned from data. A process observed as a sequence of events is stationary if its stochastic properties stay the same when the sequence is shifted in a positive or negative direction by a constant time parameter. The temporal Bayesian networks forecast mortalities of patients, where each patient has one record per day. The predictive performance of the stationary model is compared with nonstationary models using the area under the receiver operating characteristics (ROC) curves.
RESULTS: The stationary model usually performed best. However, one nonstationary model using large data sets performed significantly better than the stationary model.
CONCLUSION: Results suggest that using a combination of stationary and nonstationary models may predict better than using either alone.

Entities:  

Mesh:

Year:  2000        PMID: 11079917      PMCID: PMC2243937     

Source DB:  PubMed          Journal:  Proc AMIA Symp        ISSN: 1531-605X


  3 in total

1.  Learning temporal probabilistic causal models from longitudinal data.

Authors:  A Riva; R Bellazzi
Journal:  Artif Intell Med       Date:  1996-07       Impact factor: 5.326

2.  Microbial contamination of intravenous and arterial catheters.

Authors:  S E Tebbs; A Ghose; T S Elliott
Journal:  Intensive Care Med       Date:  1996-03       Impact factor: 17.440

3.  Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: results of a multicenter, prospective study. Working group on "sepsis-related problems" of the European Society of Intensive Care Medicine.

Authors:  J L Vincent; A de Mendonça; F Cantraine; R Moreno; J Takala; P M Suter; C L Sprung; F Colardyn; S Blecher
Journal:  Crit Care Med       Date:  1998-11       Impact factor: 7.598

  3 in total
  4 in total

1.  Mining time-dependent patient outcomes from hospital patient records.

Authors:  Bharat R Rao; Sathyakama Sandilya; Radu Niculescu; Colin Germond; A Goel
Journal:  Proc AMIA Symp       Date:  2002

2.  From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system.

Authors:  Eren Gultepe; Jeffrey P Green; Hien Nguyen; Jason Adams; Timothy Albertson; Ilias Tagkopoulos
Journal:  J Am Med Inform Assoc       Date:  2013-08-19       Impact factor: 4.497

3.  ICU Outcome Predictions using Physiologic Trends in the First Two Days.

Authors:  Mehmet Kayaalp
Journal:  Comput Cardiol (2010)       Date:  2012

4.  Predicting ICU survival: a meta-level approach.

Authors:  Lefteris G Gortzis; Filippos Sakellaropoulos; Ioannis Ilias; Konstantinos Stamoulis; Ioanna Dimopoulou
Journal:  BMC Health Serv Res       Date:  2008-07-26       Impact factor: 2.655

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.