Assessing the Performance of Prediction Models: A Framework for Traditional and Novel Measures
It is suggested that reporting discrimination and calibration will always be important for a prediction model and decision-analytic measures should be reported if the predictive model is to be used for clinical decisions.
Consistent Estimation of the Expected Brier Score in General Survival Models with Right‐Censored Event Times
- T. Gerds, M. Schumacher
- Mathematics, ChemistryBiometrical journal. Biometrische Zeitschrift
- 1 December 2006
It is shown that a modified version of this estimator is consistent even when censoring and event times are only conditionally independent given the covariates, and is derived on the basis of regression models for the censoring distribution.
Predicting cumulative incidence probability by direct binomial regression
We suggest a new simple approach for estimation and assessment of covariate effects for the cumulative incidence curve in the competing risks model. We consider a semiparametric regression model…
Estimating a time‐dependent concordance index for survival prediction models with covariate dependent censoring
The existing methodology for applications where the length of the follow-up period depends on the predictor variables is extended and a class of inverse probability of censoring weighted estimators is discussed in which the estimates rely on a working model for the conditional censoring distribution.
Efron‐Type Measures of Prediction Error for Survival Analysis
It is found that flexible rules, like artificial neural nets, classification and regression trees, or regression splines can be assessed, and compared to less flexible rules in the same data where they are developed.
Evaluating Random Forests for Survival Analysis using Prediction Error Curves.
The R package pec is surveyed, showing how the functionality of pec can be extended to yet unsupported prediction models, and implemented support for random forest prediction models based on the R-packages randomSurvivalForest and party.
On pseudo-values for regression analysis in competing risks models
The pseudo-values suggested for competing risks models and some conjectures regarding their asymptotics are analyzed and proved and a second order von Mises expansion of the Aalen-Johansen estimator yields an appropriate representation of the pseudo- values.
A genome-wide association study of men with symptoms of testicular dysgenesis syndrome and its network biology interpretation
The association of single-nucleotide polymorphisms in the TGFBR3 and BMP7 genes, which belong to the transforming growth factor β signalling pathway, suggests a role for this pathway in the pathogenesis of TDS.
Association of Angiotensin-Converting Enzyme Inhibitor or Angiotensin Receptor Blocker Use With COVID-19 Diagnosis and Mortality.
Findings do not support discontinuation of ACEI/ARB medications that are clinically indicated in the context of the COVID-19 pandemic, and prior use ofACEI/ARBs was not significantly associated with CO VID-19 diagnosis among patients with hypertension or with mortality or severe disease among patients diagnosed as having COIDs.