Repeatedly measured predictors: a comparison of methods for prediction modeling.

Marieke WeltenMarlou L A de KroonCarry M RendersEwout W SteyerbergHein RaatJos W R TwiskMartijn W Heymans

Published in: Diagnostic and prognostic research (2018)

The choice of method depends on hypothesized predictor-outcome associations, available data, and requirements of the prediction model. Overall, the growth curve method seems to be the most flexible method capable of incorporating longitudinal predictor information without loss in predictive quality.

Keyphrases

healthcare
cross sectional
machine learning
health information
solid state