Repeatedly measured predictors: a comparison of methods for prediction modeling

Autor: Martijn W. Heymans, Carry M. Renders, Jos W. R. Twisk, Hein Raat, Marlou L. A. de Kroon, Ewout W. Steyerberg, Marieke Welten
Přispěvatelé: Public Health, Epidemiology and Data Science, Public and occupational health, ACS - Atherosclerosis & ischemic syndromes, CCA - Imaging and biomarkers, CCA - Cancer Treatment and quality of life, CCA - Biomarkers, CCA - Quality of Life, APH - Personalized Medicine, APH - Methodology
Jazyk: angličtina
Rok vydání: 2018
Předmět:
Zdroj: Diagnostic and Prognostic Research, Vol 2, Iss 1, Pp 1-10 (2018)
Diagnostic and Prognostic Research, 2
Welten, M, de Kroon, M LA, Renders, C M, Steyerberg, E W, Raat, H, Twisk, J WR & Heymans, M W 2018, ' Repeatedly measured predictors: a comparison of methods for prediction modeling ', Diagnostic and Prognostic Research, vol. 2, no. 1, pp. 5 .
Diagnostic and Prognostic Research
Diagnostic and Prognostic Research, 2(1). BioMed Central
ISSN: 2397-7523
Popis: Background In literature, not much emphasis has been placed on methods for analyzing repeatedly measured independent variables, even less so for the use in prediction modeling specifically. However, repeated measurements could especially be interesting for the construction of prediction models. Therefore, our objective was to evaluate different methods to model a repeatedly measured independent variable and a long-term fixed outcome variable into a prediction model. Methods Six methods to handle a repeatedly measured predictor were applied to develop prediction models. Methods were evaluated with respect to the models’ predictive quality (explained variance R2 and the area under the curve (AUC)) and their properties were discussed. The models included overweight and BMI-standard deviation score (BMI-SDS) at age 10 years as outcome and seven BMI-SDS measurements between 0 and 5.5 years as longitudinal predictor. Methods for comparison encompassed developing models including: all measurements; a single (here: the last) measurement; a mean or maximum value of all measurements; changes between subsequent measurements; conditional measurements; and growth curve parameters. Results All methods, except for using the maximum or mean, resulted in prediction models for overweight of similar predictive quality, with adjusted Nagelkerke R2 ranging between 0.230 and 0.244 and AUC ranging between 0.799 and 0.807. Continuous BMI-SDS prediction showed similar results. Conclusions 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. Electronic supplementary material The online version of this article (10.1186/s41512-018-0024-7) contains supplementary material, which is available to authorized users.
Databáze: OpenAIRE
Externí odkaz: