Long-Time-Health: Modelos Conjuntos para Dados Longitudinais e Tempo-até-Evento em Ciências da Saúde
Universidade do Minho; ISPUP;
Medical data at patient level, in portuguese hospitals, is not establish in systematic data bases to be used directly for statistical analysis. Usually, patients being follow-
up at hospital after diagnostic, or treatment, generate repeated measurements of a biomarker of interest. The longitudinal sequence will terminate due to an event or censoring. It is of interest to learn about longitudinal progression as well as risk factors and the implications of these on time-to-event. However, it is known that joint models, accounting for a joint distribution, for longitudinal and time-to-event data are necessary to analyze these data. Therefore, in this project the development of joint models is proposed, following a proposal for individual predictions under this model. Moreover, these solutions are implemented in a computer software, to be used by the medical community, that also manages a data base, collected systematically, in real time.