A sequential logistic regression classifier based on mixed effects with applications to longitudinal data

Making an early classification in longitudinal data is highly desirable. For this purpose, a sequential classifier that incorporates a neutral zone framework is proposed. The classification procedure evaluates each subject sequentially at each longitudinal time point. If there is not adequate confidence in making a classification at a given time point, the decision will wait until the next time point where another measurement is collected. This process continues until there is enough confidence of making a classification or until the last time point where data can be collected is reached. It is demonstrated that the proposed sequential classifier maintains competitive error rates while reducing the overall cost when the cost of time is taken into account. The classifier is applied to a real example of identifying patients that are vulnerable to kidney dysfunction on the basis of up to 7 blood draws sequentially taken from each patient. (C) 2015 Elsevier B.V. All rights reserved.