Literature DB >> 23536921

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

Mehmet Kayaalp1.   

Abstract

AIMS: This study aims to accurately predict patient mortality in the ICU. Given all physiologic measurements in the first 48 hours of the ICU stay, the Bayesian model of the study predicts outcome with a posterior probability.
METHODS: This study modeled the outcome as a binary random variable dependent on trends of daily physiologic measures of the patient, where trends were conditionally independent given the outcome. A two-day trend is a sequence of two discrete values, one for each day. Each value (low, medium, high or unmeasured) is a function of the arithmetic mean of that measure on the corresponding day.
RESULTS: The prediction performance of the model was measured as the minimum of sensitivity and positive predictive values. The model yielded a score of 0.39 along with a Hosmer-Lemeshow H statistic of 36, which measures calibration. The perfect scores would be 1.0 and 0, respectively.
CONCLUSION: The prediction performance of the study was an improvement over the established ICU scoring metric SAPS-I, whose score was 0.32. Calibration of the model outputs was comparable to that of SAPS-I.

Entities:  

Year:  2012        PMID: 23536921      PMCID: PMC3607431     

Source DB:  PubMed          Journal:  Comput Cardiol (2010)        ISSN: 2325-887X


  8 in total

1.  Prognostic Bayesian networks I: rationale, learning procedure, and clinical use.

Authors:  Marion Verduijn; Niels Peek; Peter M J Rosseel; Evert de Jonge; Bas A J M de Mol
Journal:  J Biomed Inform       Date:  2007-07-25       Impact factor: 6.317

2.  The application of naive Bayes model averaging to predict Alzheimer's disease from genome-wide data.

Authors:  Wei Wei; Shyam Visweswaran; Gregory F Cooper
Journal:  J Am Med Inform Assoc       Date:  2011 Jul-Aug       Impact factor: 4.497

Review 3.  Prognosis in critical care.

Authors:  Lucila Ohno-Machado; Frederic S Resnic; Michael E Matheny
Journal:  Annu Rev Biomed Eng       Date:  2006       Impact factor: 9.590

4.  Mortality assessment in intensive care units via adverse events using artificial neural networks.

Authors:  Alvaro Silva; Paulo Cortez; Manuel Filipe Santos; Lopes Gomes; José Neves
Journal:  Artif Intell Med       Date:  2005-10-06       Impact factor: 5.326

Review 5.  Recent innovations in intensive care unit risk-prediction models.

Authors:  Andrew L Rosenberg
Journal:  Curr Opin Crit Care       Date:  2002-08       Impact factor: 3.687

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

Authors:  M Kayaalp; G F Cooper; G Clermont
Journal:  Proc AMIA Symp       Date:  2000

7.  Discovery and inclusion of SOFA score episodes in mortality prediction.

Authors:  Tudor Toma; Ameen Abu-Hanna; Robert-Jan Bosman
Journal:  J Biomed Inform       Date:  2007-03-31       Impact factor: 6.317

8.  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

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.