A0849
Title: Functional mixture cure model and its application
Authors: Yuko Araki - Tohoku University (Japan) [presenting]
Abstract: A functional mixture cure model with functional covariates measured at the baseline period is considered. Much biostatistical research focuses on the time to event and its association with risk factors. The mixture cure model is based on the idea that the entire population can be divided into cure and un-cure groups. The cure group means that they do not develop the symptom of interest in the future. The mixture cure model has been used in the evaluation of the effects of therapeutic agents on cancer recurrence or a study of patients who did not die after recovering from Covid 19. However, the existing methods do not treat the situation that some covariates of interest during the baseline period are a function of time or space. A functional mixture cure model is proposed, which can deal with such data to reveal the association between risk factors and mortality with some complex changes in clinical measurements.