For this reason the risk assessment tool is based on selected parameters which are known predictors for outcome of hepatic liver tumor resection [ 5].
We selected predictors based on a priori hypotheses of determinants of health behavior, including unobservable risk preferences vis-à-vis the risk game choice and observable sociodemographic characteristics.
The logit 6 (manually selected predictors based on the p-values) had lower classification accuracy (73%) in comparison to the NBCMM.
To further understand the association between reported practicing of certain health behaviors and a set of selected predictors based on our conceptual framework, we performed a series of logistic regression analyses.
The model based on NT-proBNP consisting of all selected predictors in this study, including age, New York Heart Association class IV CHF, plasma albumin, neutrophils/lymphocytes, and NT-proBNP, had a moderately higher c-statistic compared with the SHFS (0.846 versus 0.796, P=0.066).
We selected predictors a priori based on previous studies, clinical judgment, and differences between one-year survivors and non-survivors in patients with AKI.
Moreover, this analysis formulated a risk-evaluation model based on NT-proBNP values consisting of all selected predictors in the current analysis, including age, New York Heart Association class IV CHF, plasma albumin, neutrophils/lymphocytes, and NT-proBNP values.
The model based on NT-proBNP values consisting of all selected predictors in the current analysis, including age, New York Heart Association class IV CHF, plasma albumin, neutrophils/lymphocytes, and NT-proBNP values, had a moderately higher c-statistic compared with the SHFS (0.846 versus 0.796, P=0.066).
The selected predictors were: Social class: Based on the father's occupation, social class was assigned as: social class I + II vs social class III [ 25].
The search process is based on a four-objective optimization problem that minimizes the number of selected predictors, maximizes the predictive accuracy of a data-driven model and optimizes two information theoretic metrics of relevance and redundancy, which guarantee that the selected subsets are highly informative and with little intra-subset similarity.
