Prognosis and prognostic research validating a prognostic model
METHODS There were two distinct phases to the overall study; the development and the validation phases.
RESULTS Significant predictors of the development of complications were age, number of rib fractures, chronic lung disease, use of pre-injury anticoagulants and oxygen saturation levels.
Temporal validation is important in medicine due to the effects of population drift implying changes in patient mix, technologies and treatment policies.
These changes can affect model future performance  and .
The actual use of prognostic models for any application, however, requires trust in it and this trust is in turn influenced by the clinical credibility and the validity of the models  and .
There are different methods and types of prognostic models including logistic regression, neural networks, and classification trees (also called decision trees) .