Literature DB >> 16360558

Models developed by three techniques did not achieve acceptable prediction of binary trauma outcomes.

Rory Wolfe1, Dean P McKenzie, James Black, Pam Simpson, Belinda J Gabbe, Peter A Cameron.   

Abstract

BACKGROUND AND OBJECTIVES: To develop prediction models for outcomes following trauma that met prespecified performance criteria. To compare three methods of developing prediction models: logistic regression, classification trees, and artificial neural networks.
METHODS: Models were developed using a 1996-2001 dataset from a major trauma center in Victoria, Australia. Developed models were subjected to external validation using the first year of data collection, 2001-2002, from a state-wide trauma registry for Victoria. Different authors developed models for each method. All authors were blinded to the validation dataset when developing models.
RESULTS: Prediction models were developed for an intensive care unit stay following trauma (prevalence 23%) using information collected at the scene of the injury. None of the three methods gave a model that satisfied the performance criteria of sensitivity >80%, positive predictive value >50% in the validation dataset. Prediction models were also developed for death (prevalence 2.9%) using hospital-collected information. The performance criteria of sensitivity >95%, specificity >20% in the validation dataset were not satisfied by any model.
CONCLUSION: No statistical method of model development was optimal. Prespecified performance criteria provide useful guides to interpreting the performance of developed models.

Entities:  

Mesh:

Year:  2005        PMID: 16360558     DOI: 10.1016/j.jclinepi.2005.05.007

Source DB:  PubMed          Journal:  J Clin Epidemiol        ISSN: 0895-4356            Impact factor:   6.437


  8 in total

1.  Predicting future depression in adolescents using the Short Mood and Feelings Questionnaire: a two-nation study.

Authors:  Dean P McKenzie; John W Toumbourou; Andrew B Forbes; Andrew J Mackinnon; Barbara J McMorris; Richard F Catalano; George C Patton
Journal:  J Affect Disord       Date:  2011-06-13       Impact factor: 4.839

2.  Using an Artificial Neural Networks (ANNs) Model for Prediction of Intensive Care Unit (ICU) Outcome and Length of Stay at Hospital in Traumatic Patients.

Authors:  Changiz Gholipour; Fakher Rahim; Abolghasem Fakhree; Behrad Ziapour
Journal:  J Clin Diagn Res       Date:  2015-04-01

3.  Enhancing the fever workup utilizing a multi-technique modeling approach to diagnose infections more accurately.

Authors:  Adam M A Fadlalla; Joseph F Golob; Jeffrey A Claridge
Journal:  Surg Infect (Larchmt)       Date:  2010-07-28       Impact factor: 2.150

4.  Nonlinear association between serum testosterone levels and coronary artery disease in Iranian men.

Authors:  Nader Fallah; Kazem Mohammad; Keramat Nourijelyani; Mohammad Reza Eshraghian; Seyyed Ali Seyyedsalehi; Maria Raiessi; Maziar Rahmani; Hamid Reza Goodarzi; Soodabeh Darvish; Hojjat Zeraati; Gholamreza Davoodi; Saeed Sadeghian
Journal:  Eur J Epidemiol       Date:  2009-04-09       Impact factor: 8.082

5.  Prehospital identification of major trauma patients.

Authors:  Gürbey Ocak; Leontien M Sturms; Josephine M Hoogeveen; Saskia Le Cessie; Gerrolt N Jukema
Journal:  Langenbecks Arch Surg       Date:  2008-06-26       Impact factor: 3.445

6.  Artificial neural networks versus proportional hazards Cox models to predict 45-year all-cause mortality in the Italian Rural Areas of the Seven Countries Study.

Authors:  Paolo Emilio Puddu; Alessandro Menotti
Journal:  BMC Med Res Methodol       Date:  2012-07-23       Impact factor: 4.615

7.  Evaluation of a complex, population-based injury claims management intervention for improving injury outcomes: study protocol.

Authors:  Alex Collie; Belinda Gabbe; Michael Fitzharris
Journal:  BMJ Open       Date:  2015-05-12       Impact factor: 2.692

8.  Stratification of the severity of critically ill patients with classification trees.

Authors:  Javier Trujillano; Mariona Badia; Luis Serviá; Jaume March; Angel Rodriguez-Pozo
Journal:  BMC Med Res Methodol       Date:  2009-12-09       Impact factor: 4.615

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.