A mixed-ensemble model for hospital readmission

Highlights • A mixed-ensemble model for hospital readmission is proposed. • The mixed-ensemble model enables controlling the tradeoff between reasoning transparency and predictive accuracy, by taking into account the unique characteristics of the learned database. • The mixed-ensemble model also increases the classification accuracy for positive readmission instances, particularly when strong predictors are not available. • An optimization approach for the mixed-ensemble model is proposed. • Implementation of the mixed-ensemble method for predicting all-cause hospital readmissions of CHF patients allows overcoming some of the limitations of the classifiers considered individually, and of other traditional ensembling methods.