Wolfe Rory, McKenzie Dean P, Black James, Simpson Pam, Gabbe Belinda J, Cameron Peter A
Department of Epidemiology and Preventive Medicine, Monash University, Central and Eastern Clinical School, Melbourne, Victoria 3004, Australia.
J Clin Epidemiol. 2006 Jan;59(1):26-35. doi: 10.1016/j.jclinepi.2005.05.007. Epub 2005 Nov 2.
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.
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.
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.
No statistical method of model development was optimal. Prespecified performance criteria provide useful guides to interpreting the performance of developed models.
开发符合预先设定性能标准的创伤后结局预测模型。比较三种开发预测模型的方法：逻辑回归、分类树和人工神经网络。
使用来自澳大利亚维多利亚州一家主要创伤中心的1996 - 2001年数据集开发模型。使用来自维多利亚州全州创伤登记处2001 - 2002年数据收集的第一年数据对开发的模型进行外部验证。不同作者针对每种方法开发模型。所有作者在开发模型时均对验证数据集不知情。
利用在受伤现场收集的信息，针对创伤后入住重症监护病房（患病率23%）开发了预测模型。在验证数据集中，三种方法均未得出满足敏感性>80%、阳性预测值>50%性能标准的模型。还利用医院收集的信息针对死亡（患病率2.9%）开发了预测模型。在验证数据集中，没有任何模型满足敏感性>95%、特异性>20%的性能标准。
没有一种模型开发的统计方法是最优的。预先设定的性能标准为解释开发模型的性能提供了有用的指导。
